REVIEW ON DEEP LEARNING BASED TECHNIQUES
FOR PERSON RE-IDENTIFICATION
Abhinav Parkhi
Reaserch Scholar, Department of Electronics & Telecommunication Engineering, YCCE, Nagpur,
(India).
E-mail: abhinav.parkhi@gmail.com
Atish Khobragade
Professor, Department of Electronics Engineering, YCCE, Nagpur, (India).
E-mail: atish_khobragade@rediffmail.com
Reception: 24/11/2022 Acceptance: 09/12/2022 Publication: 29/12/2022
Suggested citation:
Parkhi, A., y Khobragade, A. (2022). Review on deep learning based techniques for person re-identification. 3C
TIC. Cuadernos de desarrollo aplicados a las TIC, 11(2), 208-223. https://doi.org/
10.17993/3ctic.2022.112.208-223
https://doi.org/10.17993/3ctic.2022.112.208-223
3C TIC. Cuadernos de desarrollo aplicados a las TIC. ISSN: 2254-6529
Ed. 41 Vol. 11 N.º 2 August - December 2022
208
ABSTRACT
In-depth study has recently been concentrated on human re-identification, which is a crucial
component of automated video surveillance. Re-identification is the act of identifying someone in
photos or videos acquired from other cameras after they have already been recognized in an image or
video from one camera. Re-identification, which involves generating consistent labelling between
several cameras, or even just one camera, is required to reconnect missing or interrupted tracks. In
addition to surveillance, it may be used in forensics, multimedia, and robotics.Re-identification of the
person is a difficult problem since their look fluctuates across many cameras with visual ambiguity
and spatiotemporal uncertainty. These issues can be largely caused by inadequate video feeds or low-
resolution photos that are full of unnecessary facts and prevent re-identification. The geographical or
temporal restrictions of the challenge are difficult to capture. The computer vision research community
has given the problem a lot of attention because of how widely used and valuable it is. In this article,
we look at the issue of human re-identification and discuss some viable approaches.
KEYWORDS
Person re-identification, Supervised Learning, Unsupervised Learning.
https://doi.org/10.17993/3ctic.2022.112.208-223
3C TIC. Cuadernos de desarrollo aplicados a las TIC. ISSN: 2254-6529
Ed. 41 Vol. 11 N.º 2 August - December 2022
209
1. INTRODUCTION
T
The process of Person Re-identification(Re-ID) has been thoroughly studied as a distinct person
retrieval problem among non-overlapping cameras [1].Re-goal ID's is to determine whether a person of
interest has ever been at a location at a different time that was captured by the same camera at a
different time instant or even the same camera placed somewhere else [2].A photograph [3], a video clip
[4], or even a written explanation [5] might be used to illustrate the subject.Person Re-ID is essential in
smart surveillance technology with substantial academic effect and practical advantage due to the
pressing need for community security and the growing number of security cameras.
The procedure of re-ID is difficult because of a variety of camera motions [6], poor picture resolutions
[7, 8, 9, 10, 11, heterogeneous modalities [11, 12], complicated camera surroundings, background
clutter [12], inaccurate bounding box creation, etc. These provide a lot of variations and uncertainty.
Other elements that significantly increase the difficulties for realistic model deployment include the
dynamically network of upgraded cameras [13], a massive gallery that offers effective restoration [14],
group ambiguity [15], important domain change [16], unknown examining situations [17], and
updating a model progressively [18], and changing clothes [19]. Re-ID still presents a problem as a
result of these issues. This encourages us to carry out an extensive survey, establish a solid baseline for
various Re-ID efforts,
and discuss a wide range of potential future paths. Person Although Re-ID is a difficult process,
enhancing the semantic integrity of the analysis depends on it. Re-ID is crucial for programs that make
use of single-camera surveillance systems. For instance, to find out if a person regularly visits the
same place or if a different person or the same one picks up an abandoned box or bag. In addition to
tracking, it has uses in robotics, multimedia, and more well-known technologies like automatic photo
labeling and photo surfing [20].It is not difficult to comprehend the Person's Re-ID process. Being
human, we always do it with ease. Our sights and minds have been conditioned to locate, identify, and
then re-identify things and people in the actual world. Re-ID, which can be shown in Fig. 1, is the idea
that a person who has been earlier seen would be identified as soon as they make an appearance using
a specific description of the individual.
Even if hand-crafted features had some early success [21] and metric learning [22], the most advanced
Re-ID algorithms currently available are constructed using convolutional neural networks (CNNs),
which, when trained under supervision, need a significant amount of annotated (labelled) data to learn
a stable embedding subspace. Recent deep learning approaches and detailed investigations on person
Re-ID utilizing custom systemsprovided in [23], respectively. Large-scale dataset annotation for Re-
ID is exceedingly labor intensive, time-consuming, and expensive, especially for techniques needing
numerous bounding boxes for each individual to increase accuracy by making generalisations between
two separate activities. One-shot learning and unsupervised learning are combined, for instance, in
[24] and, which employ the Resnet50 [25] architecture with pre-trained networks on ImageNet [26].
Although it has been empirically demonstrated that pre-training and transfer learning significantly
boost neural network performance, they are not appropriate for adjusting parameters across a wide
range of domains or topologies. This article highlights the obstacles and unresolved problems in
human re-identification and datasets, deep learning algorithms, and current research in these areas.
https://doi.org/10.17993/3ctic.2022.112.208-223
3C TIC. Cuadernos de desarrollo aplicados a las TIC. ISSN: 2254-6529
Ed. 41 Vol. 11 N.º 2 August - December 2022
210
Figure
1.
Shows an example of a common DL workflow that involves following five stages (i) Data Collection (ii) Bounding Box
Generation (iii)Data Annotation (iv) Model Training (v) Validation [67].
2. DEEP LEARNING MODERN RESEARCH
In today's Era, intelligent systems and tech sophisticated automation are the main focuses across a
diverse range of domains, including smart cities, e-Health, enterprise intelligence, innovative
treatment, cyber security intellectual ability, and many more [27].Particularly when it comes to
security technologies as a wonderful approach to disclose complicated data structures in high
dimensions, deep learning techniques have substantially improved in terms of effectiveness across a
wide range of applications. In order to create intelligent data-driven systems that satisfy current
expectations, DL techniques might be extremely important because to their exceptional learning
capabilities from past data. DL has the ability to change both the world and how people live since it
can automate procedures and learn from mistakes.
3. DEEP LEARNING TECHNIQUES
This section discusses the various deep neural network techniques. These strategies frequently use
hierarchical structures with numerous levels of information processing to learn. Among the numerous
hidden layers that are frequently observed in deep neural networks are the input and output layers.
Reviewing the different training exercises available, that is (i) Supervised, an approach that is
challenging and utilizes the use of tagged training data, and (ii) Unsupervised, an approach that
examines unlabeled sets of data, is important before diving into the details of DL approaches.
3.1 SUPERVISED OR DISCRIMINATIVE LEARNING NETWORK
The term "supervised learning" refers to a process in which a supervisor doubles as an educator. The
technique of instructing or training a computer system using labelled data is known as supervised
learning. This suggests that the appropriate response has already been given to the given data. The
machine is then given a new collection of examples so that the supervised learning algorithm may
examine the training data (set of training examples) and provide an accurate output from labelled
data.Discriminative deep architectures are frequently developed to give discriminative capability for
pattern classification by modelling the posterior distributions of classes conditioned on observable
data [29]. The three main categories of discriminative architectures are Multi-Layer Perceptron
(MLP), Convolutional Neural Networks (CNN or ConvNet), Recurrent Neural Networks (RNN), and
their variations. Here, we'll briefly discuss these techniques.
3.1.1 MULTI-LAYER PERCEPTRON (MLP)
The feed-forward artificial neural network known as the Multi-layer perceptron (MLP) [30] is a
technique for supervised instruction (ANN). The deep neural network (DNN) or deep learning base
architecture are other names for it. Several activation functions, often referred to as transfer functions,
including ReLU (Rectified Linear Unit), Tanh, Sigmoid, and Softmax determine an MLP network's
output [32].
https://doi.org/10.17993/3ctic.2022.112.208-223
3C TIC. Cuadernos de desarrollo aplicados a las TIC. ISSN: 2254-6529
Ed. 41 Vol. 11 N.º 2 August - December 2022
211
The most popular technique for training MLP is back-propagation [31], a supervised learning method
that is frequently referred to as the fundamental component of a neural network. Throughout the
training phase, a variety of optimization techniques are employed liked Stochastic Gradient Descent
(SGD), Limited Memory BFGS (L-BFGS), and Adaptive Moment Estimation (Adam).
3.1.2 CONVOLUTIONAL NEURAL NETWORK (CNN)
The commonly used deep learning architecture known as a convolutional neural network [33] was
modelled after the visual brain of animals [34]. As seen in fig 2, Originally it had been used
extensively for tasks involving object recognition, but it is currently also being investigated in areas
such as object tracking [35], pose estimation [36], text detection and recognition [37], visual saliency
detection [38], action recognition [39], scene labelling , and many more [40].
Since CNNs are particularly made to control the various 2D forms, they are frequently employed in
visual identification, analyze clinical data, segmenting an image, processing language naturally, and
many other applications [41].Several CNN versions, including visual geometry group (VGG) [42],
AlexNet [43], Xception [44], Inception [45], ResNet [46], etc., may be used in various application
sectors depending on their learning capacity.
1. An illustration of Convolutional Neural Network.
3.1.3 RECURRENT NEURAL NETWORK (RNN)
Using sequential or time-series data, a different well-known neural network provides the result of one
stage as input to the following step. The name for this neural network is recurrent neural network
(RNN) [47]. Recurrent neural networks, like CNN and feed forward, learn from training input, but they
stand out due to their "memory," which enables them to affect current input and output by consulting
information from earlier inputs.While an RNN's output is reliant on what came before it in the
sequence, a typical DNN assumes that inputs and outputs are independent of one another.However,
because to the issue of declining gradients, standard networks with recurrence have difficulty in
learning long data sequences. The popular recurrent network versions thatthe problems and perform
effectively across a variety of real-life application areas are explored next.
3.1.4 LONG SHORT-TERM MEMORY (LSTM)
LSTMs are frequently used in video-based individual task re-ID and are capable of extracting temporal
characteristics. Network for recurrent feature aggregation based on LSTM efficiently reduced
interference brought on by background noise, shadowing, and recognition failure [48]. Among the first
and shallowest LSTM nodes, it gathered cumulative discriminative characteristics. The temporal and
geographical characteristics of the sections that include the probe pictures put were learned by the
breakdown of a video sequence into multiple pieces [49]. The number of identical pedestrians in the
sample is decreased by using this strategy, which also makes it simpler to identify similarity traits. Both
of the aforementioned methods process each video frame independently.The duration of the video
sequence typically has an impact on the characteristics that LSTM extracts. The RNN cannotcatch the
temporalsignals of small details in the picture because it only creates temporal connections on high-
level characteristics [50]. Therefore, research into a more effective technique for extracting spatial-
temporal characteristics is still necessary.
https://doi.org/10.17993/3ctic.2022.112.208-223
3C TIC. Cuadernos de desarrollo aplicados a las TIC. ISSN: 2254-6529
Ed. 41 Vol. 11 N.º 2 August - December 2022
212
3.1.5 GATED RECURRENT UNITS (GRUS)
A popular gating-based variation of the recurrent network techniques to monitor and regulate the flow
of information between neural network units is the Gated Recurrent Unit (GRU) [51]. A reset gate and
an update gate are all that the GRU has, as seen in Fig. 3, making it less complex than an LSTM.The
primary difference between the two devices is the number of gates: an LSTM has three gates compared
to a GRU's two (the reset and update gates). The GRU's characteristics allow dependencies from long
data sequences to be collected adaptively without removing information from previous portions of the
sequence.GRU is a little more compact approach as a consequence, often providing comparable results,
and is significantly faster to compute [52].
Figure 3. A Gated Recurrent Unit’s Basic Structure with a Reset and Update Gate.
3.2 UNSUPERVISED LEARNING NETWORK
DL approaches are widely used to explain the combined statistical parameters of the available data and
the classes that they belong to, as well as the higher predictive properties or features for pattern
recognition or synthesis [53].Since the methods under this category include frequently used to learn
features or data generation and representation, they are fundamentally utilized for unsupervised
learning [54]. Since generative modeling maintains the correctness of the discriminative model, it may
be used as a preliminary step for supervised learning tasks as well. For generative learning or
unsupervised learning, deep neural network algorithms including the Generative Adversarial Network
(GAN), Autoencoder (AE), Restricted Boltzmann Machine (RBM), Self-Organizing Map (SOM), and
Deep Belief Network (DBN), as well as its variations, are often utilized.
3.2.1 GENERATIVE ADVERSARIAL NETWORK (GAN)
․
GANs make use of neural networks' capacity to train a function that can simulate a distribution as
closely as feasible to the real thing. They are particularly capable of producing synthetic pictures with
great visual fidelity and do not rely on prior assumptions about the distribution of the data. This
important characteristic enables the application of GANs to any imbalance issue in computer vision
tasks. GANs give a technique to alter the original picture in addition to being able to create a false
image. There are several GANs with different strengths that have been published in the literature to
address the imbalance issue in computer vision tasks. For example, a specific type of GANs called
AttGAN [55], IcGAN [56], ResAttrGAN [57], etc., is frequently employed for tasks involving
modifying face attributes.
GANs are comprised of two neural networks, as shown in Fig. 4. The discriminator D predicts the
chance that a following sample will be taken from real data as opposed to data given by the generator
G, which generates new data with features similar to the original data.The generator and discriminator
in GAN modeling are then instructed to interact with one another.Healthcare, computer vision, data
augmentation, video production, voice synthesis, epidemic prevention, traffic control, network
security, and many more fields might all benefit from the utilization of GAN networks. In general,
GANs have demonstrated to be a solid field of independent data expansion and a solution to problems
requiring generative techniques.
https://doi.org/10.17993/3ctic.2022.112.208-223
3C TIC. Cuadernos de desarrollo aplicados a las TIC. ISSN: 2254-6529
Ed. 41 Vol. 11 N.º 2 August - December 2022
213
2. Generative Adversarial Networks Framework [58].
3.2.2 AUTO-ENCODER (AE)
A well-known auto-encoder (AE) unsupervised learning approach that makes use of neural networks to
learn representations [59]. Data reduction describes the depiction of a set of data.High-dimensional data
are often processed using auto-encoders. Three parts make up an autoencoder: an encoder, a code, and a
decoder. The encoder creates the code that the decoder uses to reproduce the input by compressing
it.Furthermore, generative data models have been learned using the AEs [60].Numerous unsupervised
learning techniques, including dimension reduction, extraction of features, useful coding, dynamic
modeling, noise removal, outlier or predictive modeling, etc., primarily rely on the auto-encoder. [59,
61]
3.2.3 KOHONEN MAP OR SELF-ORGANIZING MAP (SOM)
Another unsupervised learning method for constructing a low-dimensional (usually two-dimensional)
representation of a higher-dimensional data set while preserving the topological structure of the data is
the Self-Organizing Map (SOM) or Kohonen Map [62].SOM is a neural network-based method for
dimension reduction in clustering [63].We can display huge datasets and identify likely clusters by
using a SOM, which constantly moves a dataset's topological layout by bringing its neurons close to the
data points inside the dataset.The input layer is the initial layer of a SOM, followed by the output layer,
also known as the feature map, is the second layer. SOMs use competitive learning, which makes use of
a neighboring function to preserve the topological properties of the input space, in contrast to other
neural network models that use error-correction learning, such as Backpropagation with gradient
descent [64].Sequence identification, sickness or health diagnosis, fault diagnosis, and virus or parasite
attack detection are just a few of the many activities that SOM is frequently employed for [65].The
main advantage of using a SOM is that it facilitates the discovery and recognition of patterns in high-
dimensional data.
3.2.4 BOLTZMANN MACHINE WITH RESTRICTIONS (RBM)
A generative statistical neural network with the ability to learn a likelihood function over its inputs is
the Restricted Boltzmann Machine (RBM) [66].Each node in a Boltzmann machine can be either
visible or hidden and is linked to every other node.By understanding how the system functions
normally, we can better comprehend anomalies. In RBMs, a subset of Boltzmann machines, there is a
limit on the number of linkages between the accessible and deep layers [67].Due to this constraint,
training techniques for Boltzmann machines in general can be more effective than those for Boltzmann
machines, such as the gradient-based contrastive divergence algorithm [68]. Among the various uses of
RBMs are data reduction, categorization, prediction, content-based- based filtering, pattern recognition,
subject modelling, and many others.
3.2.5 DEEP BELIEF NETWORK (DBN)
A Deep Belief Network (DBN) [69] is a multiple-layer adaptive visuals model composed of so many
unsupervised networks, such as AEs or RBMs, layered one on top of the other and using the hidden
layer of each model as the input for the layer below it or connected sequentially.As a result, there are
two types of DBNs: AE-DBNs, also called as stacked AE, and RBMDBNs, also known as stacked
https://doi.org/10.17993/3ctic.2022.112.208-223
3C TIC. Cuadernos de desarrollo aplicados a las TIC. ISSN: 2254-6529
Ed. 41 Vol. 11 N.º 2 August - December 2022
214
RBMs.The AE-DBN consists of autoencoders, whereas Boltzmann machines with constraints constitute
RBM-DBN, as was already indicated. The final objective is to create a descriptive divergence-based
quicker unsupervised training method for every sub-network [70].The deep structure of DBN allows it
to store a hierarchical representation of incoming data.Network architectures for unsupervised feed-
forward are trained using unlabeled data as the basic tenet of DBN, and the networks are subsequently
fine-tuned using marked input. DBN's potentially significant benefits over traditional shallow learning
networks is its capacity to identify specific patterns, with strengthens logic and the ability to distinguish
between true and wrong data [71].
Thus, the strategies for generative learning that were previously explored frequently allow us to use
research method to build a new set of the data. Deep generative models of these kinds with supervised
or discriminative learning methods may benefit from this preparation and to guarantee model
correctness because improving classifier generalization through unsupervised representation learning.
4. CHALLENGES AND OPEN ISSUES
The fundamental difficulty with Re-ID is the variance in a person's appearance across multiple cameras.
Re-ID is challenging to make self-operating for a variety of reasons.Re-ID networks usually consist of
two essential parts:the capture of a unique individual description and the process of comparing two
models to see if they match or don't match.The capacity to automatically recognize and track
individuals in photos or videos is necessary in order to develop a distinctive person
description.Numerous difficulties and problems are apparent, and they will guide future research in the
area of person Re-ID.
4.1 RE-ID DEPENDING ON DEPTH
Depth photos capture the bones and contours of the body.Re-ID is made possible by this, which is
crucial for applications involving individualized human contact in lighting and clothing variations [88].
In [72], a paradigm based on recurrent attention is put out to solve individual identification based on
depth. Convolutional and recurrent neural networks are used to locate tiny, exclusionary localized parts
of the body in a reinforcement learning framework.
4.2 RE-ID USING VISIBLE-INFRARED TECHNOLOGY
Visible-Infrared Re-ID handles the cross-modality matching between the noticeable and thermal
pictures [88]. Because only infrared cameras can take photographs in low-light conditions, it is essential
[73].Along with the cross- modality shared embedding learning [74] also looks into the classifier level
discrepancy. Recent methods [75] decrease cross-modality disparity at both the picture and feature level
by creating cross-modality person photographs and applying the GAN approach.[76] models the cross-
modal reconstruction using a hierarchy elements. [77] presents a dual-attentive aggregate learning
strategy to identify multi-level links.
4.3 CROSS-RESOLUTION RE-ID
Taking into consideration the major resolution variations [78], Cross-Resolution Re-ID [88] compares
images with different resolutions.The high-resolution human pictures are produced in a cascaded
fashion using a cascaded SR-GAN [79], which also incorporates the identification data. The adversarial
learning method is used by Li et al. [80] to create representations of pictures that are independent of
resolution.
4.4 LABEL NOISE FOR RE-ID
It is typically hard to eliminate label noise when there is an annotation issue [88]. To prevent label
overfitting problems, Zheng et al. use a label smoothing algorithm [81]. To effectively learn a Re-ID
model while avoiding label noise and the consequences of data with high characteristic ambiguity
should be mitigated, a Distribution Net (DNet) is described in [82] that encodes the feature uncertainty.
https://doi.org/10.17993/3ctic.2022.112.208-223
3C TIC. Cuadernos de desarrollo aplicados a las TIC. ISSN: 2254-6529
Ed. 41 Vol. 11 N.º 2 August - December 2022
215
For each identity, there aren't enough data for powerful Re-ID model training, unlike the generic
classification issue [83]. It is also more challenging to learn the potent Re-ID model because of the
unidentified new identities.
4.5 MULTI-CAMERA DYNAMIC NETWORK
The constantly updated multi-camera network [84], which necessitates model change for new cameras
or probes, is another challenging issue. The Re-ID model may be updated and the representation can be
tailored for different probing galleries employing an adaptive learning method with humans in the
loop[85]. Active learning was a component of early research on continuous Re-ID in multi-camera
networks [86]. [87] Introduces an approach for flexibility to adapt relying on the selective use of
limited, non-redundant samples. Utilizing the ideal source camera theory and a geodesic flow kernel
serve as the foundation for the development of a transitive inference strategy. An open-world person
Re-ID system adds a number of contextual limitations (such Camera Topology) while dealing with
large crowds and social interactions[88].
4.6 FEATURE LEARNING
High-level semantic representations of a person's traits, such their hair, gender, and age, can resist
several environmental changes. For deep learning-based person Re-ID systems like those in [89], some
research has used these traits to fill the gap between the photos and high-level conceptual data.Since it
delivered on its predictions, feature recognition is one of the next possibilities.
4.7 ARCHITECTURE FOR AUTOMATED RE-ID
An advanced learning model's architectures must be manually created, which takes time, effort, and is
prone to mistakes. The approach of automating architectural engineering, known as neural architecture
search (NAS) [90], has recently been applied to address this issue. The study of NAS is currently
receiving greater attention. Therefore, one of the essential aspects that must be considered in future
research is the use of NAS for person Re-ID activities, as the majority of NAS techniques don't assure
that there commended CNN is suitable for person Re-ID tasks.
4.8 ACCURACY VERSUS EFFICIENCY
Large models are typically employed to obtain the greatest accuracy, but they can be time and memory
intensive, which reduces their usefulness, particularly when used to mimic real-time video monitoring
systems. The majority of modern models did not consider CPU speed and memory capacity into
account in order to increase accuracy. Authors who work in these fields must strike acompromise
between processing speed and ranking accuracy.
4.9 LIGHTWEIGHT MODEL
The creation of a lightweight Re-ID model is another approach for dealing with the scalability problem.
The issue of changing the network topology to create a light model is investigated [91, 92]. Another
strategy is to employ model distillation. A system for multi-teacher customizable comparison reduction,
for instance, is provided in [93], which in the absence of a primary data source, trains a user-specified
lightweight student model from a number of teacher models.
5. DATASETS AND EVALUATION
Individuals' appearances vary greatly depending on Lighting, stances, view angles, scales, and camera
resolutions may all vary while using different cameras. Visual ambiguities are further increased by
elements like occlusions, a crowded background, and articulated figures. Therefore, it is crucial to
gather data that successfully captures these aspects in order to create viable Re-ID approaches. In
addition to good quality data that replicates actual circumstances, it is essential to compare and assess
the Re-ID methodologies that are developed and find ways to enhance the methodology and databases.
https://doi.org/10.17993/3ctic.2022.112.208-223
3C TIC. Cuadernos de desarrollo aplicados a las TIC. ISSN: 2254-6529
Ed. 41 Vol. 11 N.º 2 August - December 2022
216
5.1 DATASETS BASED ON IMAGES
Person re-ID using images, there have been a variety of datasets; the most common datasets are listed
below.
VIPeR[94]: It is made up of 1,264 photos for 632 people and was taken by 2 non-overlapping cameras.
CUHK01 [95]: It is made up of 3,884 photographs for 971 individuals that were recorded by two
separate cameras on a university campus.
Market-1501 [96]: It is comprised of 32,643 photos for each of the 1,501 people that make up the
sample, which was taken from the front of a shop using 2 to 6 separate cameras.
DukeMTMC-ReID[97]: The dataset consists of 46,261 photos for 1852 individuals that were captured
by 8 non-overlapping cameras on the Duke University campus.
Kinect-REID [98]: It has 71 person sequences that were recorded at the authors' department.
RGBD-ID [99]: There are four groups with various viewpoints, each with the same 80 people. It is
produced on several days and has various aesthetic variants.
RegDB[100]: 412 people are represented by 4120 RGB photos and 4120 thermal photographs. Two
types of cameras are used to capture them.
SYSU-MM01 [101]: It comprises of 491 people's 15,792 infrared photographs and 287,628 RGB
photos. Six cameras, including two infrared cameras and four RGB cameras, are used to capture them
from the writers' section.
5.2 DATASETS BASED ON VIDEOS
PRID2011 [102]: It is constituted of 24541 photos for 934 individuals from 600 recordings taken from
two separate cameras in an airport's multi-camera network.
iLIDSVID[103]: It is made up of 600 movies shot by 2 non-overlapping airport cameras and 42495
photos for 300 people.
MARS [104]: The greatest video-based individual Re-ID dataset resides in this one. It is made up of
around 1191003 photos for 1261 individuals from 200 recordings that were captured by 2 to 6 non-
overlapping cameras.
RPIfield [105]: It consists of 601,581 images for 112 individuals, captured by 2 separate cameras on an
open field at a college.
5.3 EVALUATION METRICS
Cumulative matching characteristics (CMC) [106] and mean average precision (mAP) are the two
mostly used metrics for assessing Re-ID systems [107].
6. CONCLUSION
We have discussed the subject of human re-identification, as well as difficult problems and a summary
of recent research in the discipline of person recognition, in this paper. Both closed set and open set Re-
ID tasks have been taken into consideration. The approaches employed have been grouped, and their
advantages and disadvantages have been covered. Additionally, we have outlined the benefits and
drawbacks of the various Re-ID datasets. Popular Re-ID assessment methods are briefly discussed,
along with potential expansions.In conclusion, person Re-ID is a broad and difficult field with much of
space for growth and research.An effort is made in this work to give a concise overview of the Re-ID
problem, its limitations, and related problems.
https://doi.org/10.17993/3ctic.2022.112.208-223
3C TIC. Cuadernos de desarrollo aplicados a las TIC. ISSN: 2254-6529
Ed. 41 Vol. 11 N.º 2 August - December 2022
217
REFERENCES
(1)
Y.-C. Chen, X. Zhu, W.-S. Zheng, and J.-H. Lai, “Person reidentification by camera
correlation aware feature augmentation,” IEEE TPAMI, vol. 40, no. 2, 2018.
(2)
N. Gheissari, T. B. Sebastian, and R. Hartley,“Person reidentification using spatiotemporal
appearance,” in CVPR, 2006, pp. 1528–1535.
(3)
J. Almazan, B. Gajic, N. Murray, and D. Larlus,“Re-id done right: towards good practices for
person re-identification,” arXiv preprint arXiv:1801.05339, 2018.
(4)
T. Wang, S. Gong, X. Zhu, and S. Wang, “Person re-identification by video ranking,” in ECCV,
2014.
(5)
M. Ye, C. Liang, Z. Wang, Q. Leng, J. Chen, and J. Liu, “Specific person retrieval via
incomplete text description,” in ACM ICMR, 2015, pp. 547–550.
(6)
S. Karanam, Y. Li, and R. J. Radke, “Person re-identification with discriminatively trained
viewpoint invariant dictionaries,” in ICCV, 2015, pp. 4516–4524.
(7)
X. Li, W.-S. Zheng, X. Wang, T. Xiang, and S. Gong, “Multi-scale learning for low-resolution
person re-identification,” in ICCV, 2015, pp. 3765–3773.
(8)
Y. Huang, Z.-J. Zha, X. Fu, andW. Zhang, “Illumination-invariant person re-identification,” in
ACM MM, 2019.
(9)
Y.-J. Cho and K.-J. Yoon, “Improving person re-identification viapose-aware multi-shot
matching,” in CVPR, 2016, pp. 1354–1362.
(10)
H. Huang, D. Li, Z. Zhang, X. Chen, and K. Huang, “Adversarially occluded samples for
person re-identification,” in CVPR, 2018, pp. 5098–5107.
(11)
A. Wu, W.-s. Zheng, H.-X. Yu, S. Gong, and J. Lai, “Rgb-infrared cross-modality person re-
identification,” in ICCV, 2017.
(12)
C. Song, Y. Huang, W. Ouyang, and L. Wang, “Mask-guided contrastive attention model for
person re-identification,” in CVPR, 2018, pp. 1179–1188.
(13)
A. Das, R. Panda, and A. K. Roy-Chowdhury, “Continuous adaptation of multi-camera person
identification models through sparse non-redundant representative selection,” CVIU, vol. 156,
pp. 66–78, 2017.
(14)
J. Garcia, N. Martinel, A. Gardel, I. Bravo, G. L. Foresti, and C. Micheloni, “Discriminant
context information analysis for post-ranking person re-identification,” IEEE Transactions on
ImageProcessing, vol. 26, no. 4, pp. 1650–1665, 2017.
(15)
W.-S. Zheng, S. Gong, and T. Xiang, “Towards open-world person re-identification by one-shot
group-based verification,” IEEE TPAMI, vol. 38, no. 3, 2015.
(16)
A. Das, R. Panda, and A. Roy-Chowdhury, “Active image pair selection for continuous person
re-identification,” in ICIP, 2015, pp. 4263–4267.
(17)
J. Song, Y. Yang, Y.-Z. Song, T. Xiang, and T. M. Hospedales, “Generalizable person re-
identification by domain-invariant mapping network,” in CVPR, 2019.
(18)
A. Das, A. Chakraborty, and A. K. Roy-Chowdhury, “Consistent re-identification in a camera
network,” in ECCV, 2014, pp. 330– 345.
(19)
Q. Yang, A. Wu, and W. Zheng, “Person re-identification by contour sketch under moderate
clothing change.” IEEE TPAMI, 2019.
https://doi.org/10.17993/3ctic.2022.112.208-223
3C TIC. Cuadernos de desarrollo aplicados a las TIC. ISSN: 2254-6529
Ed. 41 Vol. 11 N.º 2 August - December 2022
218
(20)
J. Sivic, C.L. Zitnick, R. Szeliski, Finding people in repeated shots of the same
scene,Proceedings of the British Machine Vision Conference, 2006, pp. 909–918.
(21)
M. Farenzena, L. Bazzani, A. Perina, V. Murino, and M. Cristani. Person re-identification by
symmetry-driven accumulation of local features. In 2010 IEEE Computer Society Conference
(22) S. Liao and S. Z. Li. Efficient psd constrained asymmetric metric learning for person re-
identification. In 2015 IEEE International Conference on Computer Vision (ICCV), pages
3685–3693, 2015.
(23)
Liang Zheng, Yi Yang, and Alexander G. Hauptmann. Person re-identification: Past, present and
future. ArXiv, abs/1610.02984, 2016.
(24)
Yutian Lin, Xuanyi Dong, Liang Zheng, Yan Yan, and Yi Yang. A bottom-up clustering
approach to unsupervised person re-identification. In AAAI, 2019.
(25)
Kaiming He, Xiangyu Zhang, ShaoqingRen, and Jian Sun. Deep residual learning for image
recognition, 2015.
(26)
J. Deng, W. Dong, R. Socher, L. Li, Kai Li, and Li Fei- Fei. Imagenet: A large-scale
hierarchical image database. In 2009 IEEE Conference on Computer Vision and Pattern
Recognition, pages 248–255, 2009.
(27) Sarker IH. Data science and analytics: an overview from datadrivensmart computing, decision-
making and applications perspective.SN Comput Sci. 2021.
(28)
Sarker IH. Machine learning: Algorithms,real-world applications and research directions. SN
Computer. Science. 2021;2(3):1–21.
(29)
Deng L. A tutorial survey of architectures, algorithms, and applications for deep learning.
APSIPA Trans Signal Inf Process. 2014; p. 3.
(30)
Pedregosa F, Varoquaux G, Gramfort A, Michel V, ThirionB,Grisel O, Blondel M, Prettenhofer
P, Weiss R, Dubourg V, et al. Scikit-learn: machine learning in python. J Mach Learn
Res.2011;12:2825–30.
(31) Han J, Pei J, Kamber M. Data mining: concepts and techniques. Amsterdam: Elsevier; 2011.
(32)
Sarker IH. Deep cybersecurity: a comprehensive overview from neural network and deep
learning perspective. SN Computer.Science. 2021;2(3):1–16.
(33)
Ramachandran R, Rajeev DC, Krishnan SG, P Subathra, Deep learning an overview, IJAER,
Volume 10, Issue 10, 2015, Pages 25433-25448.
(34)
D. H. Hubel and T. N. Wiesel, Receptive fields and functional architecture of monkey striate
cortex, The Journal of physiology, 1968.
(35)
J. Fan, W. Xu, Y. Wu, and Y. Gong, Human tracking using convolutional neural networks,
Neural Networks, IEEE Transactions, 2010.
(36)
A. Toshev and C. Szegedy, Deep -pose: Human pose estimation via deep neural networks, in
CVPR, 2014.
(37) M. Jaderberg, A. Vedaldi, and A. Zisserman, Deep features for text spotting, in ECCV, 2014.
(38)
R. Zhao, W. Ouyang, H. Li, and X. Wang, Saliency detection by multicontext deep learning, in
CVPR, 2015.
(39)
J. Donahue, Y. Jia, O. Vinyals, J. Hoffman, N. Zhang, E. Tzeng, and T. Darrell, Decaf: A deep
convolutional activation feature for generic, 2014
https://doi.org/10.17993/3ctic.2022.112.208-223
3C TIC. Cuadernos de desarrollo aplicados a las TIC. ISSN: 2254-6529
Ed. 41 Vol. 11 N.º 2 August - December 2022
219
(40)
Nithin, D Kanishka and Sivakumar, P Bagavathi, Generic Feature Learning in Computer Vision,
Elsevier, Vol.58, Pages202-209, 2015.
(41)
LeCun Y, Bottou L, Bengio Y, Haffner P. Gradient-based learning applied to document
recognition. Proc IEEE. 1998;86(11):2278–324.
(42)
He K, Zhang X, Ren S, Sun J. Spatial pyramid pooling in deep convolutional networks for
visual recognition. IEEE Trans PatternAnal Mach Intell. 2015;37(9):1904–16.
(43)
Krizhevsky A, Sutskever I, Hinton GE. Imagenet classification with deep convolutional neural
networks. In: Advances in neural information processing systems. 2012.
(44)
Chollet F. Xception: Deep learning with depthwise separable convolutions. In: Proceedings of
the IEEE Conference on computer vision and pattern recognition, 2017
(45)
[45] He K, Zhang X, Ren S, Sun J. Deep residual learning for image recognition. In:
Proceedings of the IEEE Conference on computervision and pattern recognition, 2016
(46)
[46] Szegedy C, Liu W, Jia Y, Sermanet P, Reed S, Anguelov D, Erhan D, Vanhoucke V,
Rabinovich A. Going deeper with convolutions.In: Proceedings of the IEEE Conference on
computer vision and pattern recognition, 2015.
(47)
Dupond S. A thorough review on the current advance of neural network structures. Annu Rev
Control. 2019.
(48)
Y. Yan, B. Ni, Z. Song, C. Ma, Y. Yan, X. Yang, Person reidentification via recurrent feature
aggregation, Proceedings of the European Conference on Computer Vision, 2016.
(49)
D. Chen, H. Li, T. Xiao, S. Yi, X. Wang, Video person reidentification with competitive snippet-
similarity aggregation and co-attentive snippet embedding, Proceedings of the IEEE Conference
on Computer Vision and Pattern Recognition, 2018, pp. 1169– 1178
(50) J. Li, S. Zhang, T. Huang, Multi-scale 3d convolution network for video based person re-
identification, Proceedings of the AAAI Conference on Artificial Intelligence, volume 33, 2019,
pp. 8618– 8625
(51)
Chung J, Gulcehre C, Cho KH, Bengio Y. Empirical evaluation of gated recurrent neural
networks on sequence modeling. arXiv preprint arXiv:1412.3555, 2014.
(52)
Gruber N, Jockisch A. Are gru cells more specific and lstm cells more sensitive in motive
classification of text? Front ArtifIntell. 2020;3:40.
(53)
Deng L. A tutorial survey of architectures, algorithms, and applicationsfor deep learning.
APSIPA Trans Signal Inf Process. 2014.
(54)
Da'u A, Salim N. Recommendation system based on deep learning methods: a systematic
review and new directions. Artif Intel Rev. 2020;53(4):2709–48.
(55)
He Z, Zuo W, Kan M, Shan S, Chen X. AttGAN: Facial attribute editing by only changing what
you want. IEEE transactions on image processing . 2019;28:5464–78.
(56)
Perarnau G, van de Weijer J, Raducanu B, Álvarez JM. Invertible Conditional GANs for image
editing. Conference on Neural Information Processing Systems . 2016.
(57) Tao R, Li Z, Tao R, Li B. ResAttr-GAN: Unpaired deep residual attributes learning for multi-
domain face image translation. IEEE Access . 2019;7:132594–608.
(58)
Moacir A. Ponti, Leonardo S. F. Ribeiro, Tiago S. Nazare,Tu Bui, John Collomosse “Everything
you wanted to know about Deep Learning for Computer Vision but were afraid to ask” https://
www.researchgate.net/publication/322413149
https://doi.org/10.17993/3ctic.2022.112.208-223
3C TIC. Cuadernos de desarrollo aplicados a las TIC. ISSN: 2254-6529
Ed. 41 Vol. 11 N.º 2 August - December 2022
220
(59)
Goodfellow I, Bengio Y, Courville A, Bengio Y. Deep learning,vol. 1. Cambridge: MIT Press;
2016.
(60)
Liu W, Wang Z, Liu X, Zeng N, Liu Y, Alsaadi FE. A surveyofdeep neural network architectures
and their applications. Neurocomputing.2017;234:11–26.
(61)
Zhang G, Liu Y, Jin X. A survey of autoencoder-based recommendersystems. Front Comput Sci.
2020;14(2).
(62) Kohonen T. The self-organizing map. Proc IEEE.1990;78(9):1464–80.
(63)
[63] Sarker IH, Salah K. Appspred: predicting context-aware smartphone apps using random
forest learning. Internet of Things. 2019;8:100106.
(64) Han J, Pei J, Kamber M. Data mining: concepts and techniques. Amsterdam: Elsevier; 2011.
(65) Kohonen T. Essentials of the self-organizing map. Neural Netw.2013;37:52–65.
(66)
[66] Marlin B, Swersky K, Chen B, Freitas N. Inductive principles for restricted boltzmann
machine learning. In: Proceedings of the Thirteenth International Conference on artificial
intelligence and statistics, p. 509–16. JMLR Workshop and Conference Proceedings, 2010.
(67) Memisevic R, Hinton GE. Learning to represent spatial transformations with factored higher-
order boltzmann machines. Neural Comput. 2010;22(6):1473–92.
(68)
Hinton GE, Osindero S, Teh Y-W. A fast learning algorithm for deep belief nets. Neural
Comput. 2006;18(7):1527–54.
(69) Hinton GE. Deep belief networks. Scholarpedia.2009;4(5):5947.
(70)
Hinton GE, Osindero S, Teh Y-W. A fast learning algorithm for deep belief nets. Neural
Comput. 2006;18(7):1527–54.
(71)
Ren J, Green M, Huang X. From traditional to deep learning: fault diagnosis for autonomous
vehicles. In: Learning control. Elsevier. 2021; p. 205–19.
(72)
A. Haque, A. Alahi, and L. Fei-Fei, “Recurrent attention models for depth-based person
identification,” in CVPR, 2016, pp. 1229–1238.
(73)
M. Ye, Z. Wang, X. Lan, and P. C. Yuen, “Visible thermal person re-identification via dual-
constrained top-ranking,” in IJCAI, 2018, pp. 1092–1099.
(74)
M. Ye, J. Shen, and L. Shao, “Visible-infrared person re-identification via homogeneous
augmented tri-modal learning,” IEEE TIFS, 2020.
(75)
Z. Wang, Z. Wang, Y. Zheng, Y.-Y. Chuang, and S. Satoh, “Learning to reduce dual-level
discrepancy for infrared-visible person re-identification,” in CVPR, 2019, pp. 618–626.
(76) S. Choi, S. Lee, Y. Kim, T. Kim, and C. Kim, “Hi-cmd: Hierarchical cross-
modalitydisentanglement for visible-infrared person reidentification,” in CVPR, 2020, pp. 257–
266.
(77)
M. Ye, J. Shen, D. J. Crandall, L. Shao, and J. Luo, “Dynamic dual-attentive aggregation
learning for visible-infrared person reidentification,” in ECCV, 2020.
(78)
X. Li, W.-S. Zheng, X. Wang, T. Xiang, and S. Gong, “Multi-scale learning for low-resolution
person re-identification,” in ICCV, 2015, pp. 3765–3773.
(79)
Z.Wang, M. Ye, F. Yang, X. Bai, and S. Satoh, “Cascaded sr-gan for scale-adaptive low
resolution person re-identification.” in IJCAI, 2018, pp. 3891–3897.
https://doi.org/10.17993/3ctic.2022.112.208-223
3C TIC. Cuadernos de desarrollo aplicados a las TIC. ISSN: 2254-6529
Ed. 41 Vol. 11 N.º 2 August - December 2022
221
(80)
Y.-J. Li, Y.-C. Chen, Y.-Y. Lin, X. Du, and Y.-C. F. Wang, “Recover and identify: A generative
dual model for cross-resolution person re-identification,” in ICCV, 2019, pp. 8090–8099.
(81) Z. Zheng, L. Zheng, and Y. Yang, “Unlabeled samples generated by gan improve the person re-
identification baseline in vitro,” in ICCV, 2017, pp. 3754–3762.
(82)
T. Yu, D. Li, Y. Yang, T. Hospedales, and T. Xiang, “Robust person re-identification by
modelling feature uncertainty,” in ICCV, 2019, pp. 552–561.
(83)
M. Ye and P. C. Yuen, “Purifynet: A robust person reidentification model with noisy labels,”
IEEE TIFS, 2020.
(84) A. Das, A. Chakraborty, and A. K. Roy-Chowdhury, “Consistent re-identification in a camera
network,” in ECCV, 2014.
(85) N. Martinel, A. Das, C. Micheloni, and A. K. Roy-Chowdhury, “Temporal model adaptation for
person re-identification,” in ECCV, 2016.
(86) A. Das, R. Panda, and A. Roy-Chowdhury, “Active image pair selection for continuous person
re-identification,” in ICIP, 2015.
(87) A. Das, R. Panda, and A. K. Roy-Chowdhury, “Continuous adaptation of multi-camera person
identification models through sparse non-redundant representative selection,” CVIU, vol.
15.2017.
(88) Mang Ye, JianbingShen, Gaojie Lin, Tao Xiang, Ling Shao, Steven C. H. Hoi, Deep Learning
for Person Re-identification:A Survey and Outlook, IEEE TRANSACTIONS ON PATTERN
ANALYSIS AND MACHINE INTELLIGENCE-2021
(89) C. Su, S. Zhang, J. Xing, W. Gao, and Q. Tian, ``Multi-type attributes driven multi-camera
person re-identi_cation,'' Pattern Recognit., vol. 75, pp. 77_89, Mar. 2018.
(90) T. Elsken, J. H. Metzen, and F. Hutter, ``Correction to: Neural architecture search,'' in
Automated Machine Learning: Methods, Systems, Challenges, F. Hutter, L. Kotthoff, and J.
Vanschoren, Eds. Cham, Switzerland: Springer, 2019.
(91) W. Li, X. Zhu, and S. Gong, “Harmonious attention network for person re-identification,” in
CVPR, 2018, pp. 2285–2294.
(92) K. Zhou, Y. Yang, A. Cavallaro, and T. Xiang, “Omni-scale feature learning for person re-
identification,” in ICCV, 2019, pp. 3702– 3712.
(93) A. Wu, W.-S. Zheng, X. Guo, and J.-H. Lai, “Distilled person reidentification: Towards a more
scalable system,” in CVPR, 2019,pp. 1187–1196.
(94) D. Gray, S. Brennan, and H. Tao, ``Evaluating appearance models for recognition, reacquisition,
and tracking,'' in Proc. 10th Int. Workshop Perform. Eval. Tracking Surveill. (PETS), vol. 3,
2007, pp. 41_47.
(95) W. Li, R. Zhao, and X. Wang, ``Human reidenti_cation with transferred metric learning,'' in
Computer Vision_ACCV (Lecture Notes in Computer Science), vol. 7724. Berlin, Germany:
Springer, 2013, pp. 31_44.
(96) L. Zheng, L. Shen, L. Tian, S. Wang, J. Wang, and Q. Tian, ``Scalable person re-
identi_cation:Abenchmark,'' in Proc. IEEE Int. Conf. Comput Vis. (ICCV), Dec. 2015, pp.
1116_1124.
(97) E. Ristani, F. Solera, R. Zou, R. Cucchiara, and C. Tomasi, ``Performance measures and a data
set for multi-target, multi-camera tracking,'' in Computer Vision_ECCV 2016 Workshops
(Lecture Notes in Computer Science), vol. 9914. Cham, Switzerland: Springer, 2016, pp. 17_35.
https://doi.org/10.17993/3ctic.2022.112.208-223
3C TIC. Cuadernos de desarrollo aplicados a las TIC. ISSN: 2254-6529
Ed. 41 Vol. 11 N.º 2 August - December 2022
222
(98)
F. Pala, R. Satta, G. Fumera, and F. Roli, ``Multimodal person re-identification using RGB-D
cameras,'' IEEE Trans. Circuits Syst. Video Technol., vol. 26, no. 4, pp. 788_799, Apr. 2016.
(99)
I. B. Barbosa, M. Cristani, A. Del Bue, L. Bazzani, and V. Murino,``Re-identi_cation with
RGB-D sensors,'' in Compute Vision_ECCV2012. Workshops and Demonstrations, A. Fusiello,
V. Murino, andR. Cucchiara, Eds. Berlin, Germany: Springer, 2012, pp. 433_442.
(100)
D. T. Nguyen, H. G. Hong, K. W. Kim, and K. R. Park, ``Person recognition system based on a
combination of body images from visible lightand thermal cameras,'' Sensors, vol. 17, no. 3, p.
605, 2017.
(101)
A.Wu,W.-S. Zheng, H.-X. Yu, S. Gong, and J. Lai, ``RGB-infrared crossmodality person re-
identi_cation,'' in Proc. IEEE Int. Conf. Comput. Vis. (ICCV), Oct. 2017.
(102)
M. Hirzer, C. Beleznai, P. M. Roth, and H. Bischof, ``Person re-identification by descriptive and
discriminative classification,'' in Image Analysis (Lecture Notes in Computer Science), vol.
6688. Berlin, Germany:Springer, 2011, pp. 91_102.
(103)
T. Wang, S. Gong, X. Zhu, and S. Wang, ``Person re-identification by video ranking,'' in
Computer Vision_ECCV, D. Fleet, T. Pajdla, B. Schiele, and T. Tuytelaars, Eds. Cham,
Switzerland: Springer, 2014,pp. 688_703.
(104)
L. Zheng, Z. Bie, Y. Sun, J.Wang, C. Su, S.Wang, and Q. Tian, ``MARS: A video benchmark for
large-scale person re-identi_cation,'' in Computer Vision_ECCV (Lecture Notes in Computer
Science), vol. 9910. Cham, Switzerland: Springer, 2016, pp. 868_884.
(105)
M. Zheng, S. Karanam, and R. J. Radke, ``RPI_eld: A new dataset for temporally evaluating
person re-identi_cation,'' in Proc. IEEE/CVF Conf. Comput. Vis. Pattern Recognit. Workshops
(CVPRW), Jun. 2018.
(106)
X. Wang, G. Doretto, T. Sebastian, J. Rittscher, and P. Tu, “Shape and appearance context
modeling,” in ICCV, 2007.
(107)
L. Zheng, L. Shen, L. Tian, S. Wang, J. Wang, and Q. Tian,“Scalable person re-identification: A
benchmark,” in ICCV, 2015,pp. 1116–1124.
https://doi.org/10.17993/3ctic.2022.112.208-223
3C TIC. Cuadernos de desarrollo aplicados a las TIC. ISSN: 2254-6529
Ed. 41 Vol. 11 N.º 2 August - December 2022
223
