Intelligent video surveillance: a review through deep learning techniques for crowd analysis

Sreenu, G.; Durai, M.A. Saleem

doi:10.1186/s40537-019-0212-5

Cited by 321 publications

(129 citation statements)

References 112 publications

Supporting

Mentioning

126

Contrasting

Unclassified

Order By: Relevance

“…D RIVEN by the breakthroughs in deep learning, recent years have witnessed a booming of artificial intelligence (AI) applications and services, ranging from face recognition [1], video analytics [2] to natural language processing [3]. In the meantime, with the proliferation of mobile Internet and Internet of Things (IoT), a large number of mobile and IoT devices are deployed at the network edge and generate a huge amount of data [4], [5].…”

Section: Introductionmentioning

confidence: 99%

Joint Multiuser DNN Partitioning and Computational Resource Allocation for Collaborative Edge Intelligence

Tang

Chen

Zeng

et al. 2021

IEEE Internet Things J.

View full text Add to dashboard Cite

Mobile Edge Computing (MEC) has emerged as a promising supporting architecture providing a variety of resources to the network edge, thus acting as an enabler for edge intelligence services empowering massive mobile and Internet of Things (IoT) devices with AI capability. With the assistance of edge servers, user equipments (UEs) are able to run deep neural network (DNN) based AI applications, which are generally resource-hungry and compute-intensive, such that an individual UE can hardly afford by itself in real time. However the resources in each individual edge server are typically limited. Therefore, any resource optimization involving edge servers is by nature a resource-constrained optimization problem and needs to be tackled in such realistic context. Motivated by this observation, we investigate the optimization problem of DNN partitioning (an emerging DNN offloading scheme) in a realistic multiuser resource-constrained condition that rarely considered in previous works. Despite the extremely large solution space, we reveal several properties of this specific optimization problem of joint multi-UE DNN partitioning and computational resource allocation. We propose an algorithm called Iterative Alternating Optimization (IAO) that can achieve the optimal solution in polynomial time. In addition, we present rigorous theoretic analysis of our algorithm in terms of time complexity and performance under realistic estimation error. Moreover, we build a prototype that implements our framework and conduct extensive experiments using realistic DNN models, whose results demonstrate its effectiveness and efficiency.

show abstract

Section: Introductionmentioning

confidence: 99%

Joint Multiuser DNN Partitioning and Computational Resource Allocation for Collaborative Edge Intelligence

Tang

Chen

Zeng

et al. 2021

IEEE Internet Things J.

View full text Add to dashboard Cite

show abstract

“…The goal of object detection is to detect all objects and class the objects. It has been widely used in autonomous driving [2], pedestrian detection [3], medical imaging [4], industrial detection [5], robot vision [6], intelligent video surveillance [7], remote sensing images [8], etc.…”

Section: Introductionmentioning

confidence: 99%

Object Detection Algorithm Based on Improved YOLOv3

Zhao

2020

Electronics

216

View full text Add to dashboard Cite

The ‘You Only Look Once’ v3 (YOLOv3) method is among the most widely used deep learning-based object detection methods. It uses the k-means cluster method to estimate the initial width and height of the predicted bounding boxes. With this method, the estimated width and height are sensitive to the initial cluster centers, and the processing of large-scale datasets is time-consuming. In order to address these problems, a new cluster method for estimating the initial width and height of the predicted bounding boxes has been developed. Firstly, it randomly selects a couple of width and height values as one initial cluster center separate from the width and height of the ground truth boxes. Secondly, it constructs Markov chains based on the selected initial cluster and uses the final points of every Markov chain as the other initial centers. In the construction of Markov chains, the intersection-over-union method is used to compute the distance between the selected initial clusters and each candidate point, instead of the square root method. Finally, this method can be used to continually update the cluster center with each new set of width and height values, which are only a part of the data selected from the datasets. Our simulation results show that the new method has faster convergence speed for initializing the width and height of the predicted bounding boxes and that it can select more representative initial widths and heights of the predicted bounding boxes. Our proposed method achieves better performance than the YOLOv3 method in terms of recall, mean average precision, and F1-score.

show abstract

“…Different attributes are used to analyze the crowd. These attributes are crowd behavior detection, crowd density estimation, crowd counting and crowd scene analysis [32] [10]. The abnormal behaviour of crowd and its analysis is now a research area of the researcher [8].…”

Section: Introductionmentioning

confidence: 99%

“…Crowd analysis can be carried out in three steps: i) pre-processing ii) object tracking and iii) event and behavior recognition. [10] and RNN for crowd behavior analysis is used. There are a lot of algorithms that have been used for image classification before CNN.…”

Section: Introductionmentioning

confidence: 99%

Crowd Analysis System for Images of CCTV Camera

Bansod*,

Ambhaikar

2020

IJRTE

View full text Add to dashboard Cite

It is important to monitor and analyze the crowd for peaceful event organization and minimum number of persons killed or injured in a stampede, war or accident in public or religious places. Ultimately, crowd management strategies should be adopted for crowd safety. Detecting the abnormal crowd behaviour is the interesting research area. Traditionally to monitor the crowd closed circuit television is used. Video analyses are used in many application areas. This work is a paper of traditional approach and is a study of different attributes of crowd which include crowd counting and estimation of density, detection of crowd motion. It also presents the study about behaviour understanding of crowd and crowd tracking. We have also presents crowd analysis using different deep learning methods. This paper showed results of crowd analysis using convolutional neural network and different recurrent neural network training model.

show abstract

Intelligent video surveillance: a review through deep learning techniques for crowd analysis

Abstract: Bibliographic summary about published papers under the area "Surveillance video analysis through deep learning" in digital repositories like ScienceDirect, IEEExplore and ACM are graphically demonstrated.

Cited by 321 publications

References 112 publications

Joint Multiuser DNN Partitioning and Computational Resource Allocation for Collaborative Edge Intelligence

Joint Multiuser DNN Partitioning and Computational Resource Allocation for Collaborative Edge Intelligence

Object Detection Algorithm Based on Improved YOLOv3

Crowd Analysis System for Images of CCTV Camera

Contact Info

Product

Resources

About