Human Action Recognition using 3D Convolutional Neural Networks with 3D Motion Cuboids in Surveillance Videos

Arunnehru, J.; Chamundeeswari, G.; Bharathi, S.

doi:10.1016/j.procs.2018.07.059

Cited by 85 publications

(46 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In many cases, the detection and recognition of human actions (like criminal actions) is done by analysis of movement [16][17][18]53,54] or trajectories [12][13][14][15], which implies the processing of several video frames. Nevertheless, when the video camera is mobile, it is very difficult to carry out the trajectory or movement analysis because camera movements may introduce noise to the trajectories or movements to be analyzed.…”

Section: Novel Low Computational Cost Methods For Criminal Activities mentioning

confidence: 99%

“…However, the Colombian National Police does not implement any method for the specific case of the detection of criminal events. The available solutions are not applicable because most of the cameras of the video surveillance system installed in Colombian cities are mobile (Pan-Tilt-Zoom Dome), which makes it difficult to use conventional video analysis techniques focused on human action recognition because most of these methods are based on trajectory [12][13][14][15] or movement analysis [16][17][18] and camera movements interfere with these kinds of studies. The C2IS shows georeferenced information using a Geographic Information System (GIS) of several subsystems [5], such as crime cases reported by emergency calls, the position of the police officers in the streets and real-time video from the video surveillance system [6].…”

Section: Related Work In Crime Events Video Detectionmentioning

confidence: 99%

See 1 more Smart Citation

A Novel Low Processing Time System for Criminal Activities Detection Applied to Command and Control Citizen Security Centers

et al. 2019

View full text Add to dashboard Cite

This paper shows a Novel Low Processing Time System focused on criminal activities detection based on real-time video analysis applied to Command and Control Citizen Security Centers. This system was applied to the detection and classification of criminal events in a real-time video surveillance subsystem in the Command and Control Citizen Security Center of the Colombian National Police. It was developed using a novel application of Deep Learning, specifically a Faster Region-Based Convolutional Network (R-CNN) for the detection of criminal activities treated as “objects” to be detected in real-time video. In order to maximize the system efficiency and reduce the processing time of each video frame, the pretrained CNN (Convolutional Neural Network) model AlexNet was used and the fine training was carried out with a dataset built for this project, formed by objects commonly used in criminal activities such as short firearms and bladed weapons. In addition, the system was trained for street theft detection. The system can generate alarms when detecting street theft, short firearms and bladed weapons, improving situational awareness and facilitating strategic decision making in the Command and Control Citizen Security Center of the Colombian National Police.

show abstract

Section: Novel Low Computational Cost Methods For Criminal Activities mentioning

confidence: 99%

Section: Related Work In Crime Events Video Detectionmentioning

confidence: 99%

A Novel Low Processing Time System for Criminal Activities Detection Applied to Command and Control Citizen Security Centers

et al. 2019

View full text Add to dashboard Cite

show abstract

“…Nowadays, in fact, more and more critical tasks see advanced interactions between complex systems and users, or more in general, between intelligent environments and users, so that the latter can interact, more or less voluntarily, with smart and autonomous applications. A typical example in this direction is represented by the new generation of video surveillance systems [3][4][5][6][7]. In these systems, vehicles and people are detected and tracked over time within video streams and, at the same time, their actions and behaviours are encoded and classified in order to have a sort of smart understanding of what is happening inside a scenario, thus allowing a quick identification of dangerous situations or events of interest.…”

Section: Introductionmentioning

confidence: 99%

Design of a 3D Platform for Immersive Neurocognitive Rehabilitation

2020

View full text Add to dashboard Cite

In recent years, advancements in human–computer interaction (HCI) have enabled the development of versatile immersive devices, including Head-Mounted Displays (HMDs). These devices are usually used for entertainment activities as video-gaming or augmented/virtual reality applications for tourist or learning purposes. Actually, HMDs, together with the design of ad-hoc exercises, can also be used to support rehabilitation tasks, including neurocognitive rehabilitation due to strokes, traumatic brain injuries, or brain surgeries. In this paper, a tool for immersive neurocognitive rehabilitation is presented. The tool allows therapists to create and set 3D rooms to simulate home environments in which patients can perform tasks of their everyday life (e.g., find a key, set a table, do numerical exercises). The tool allows therapists to implement the different exercises on the basis of a random mechanism by which different parameters (e.g., objects position, task complexity) can change over time, thus stimulating the problem-solving skills of patients. The latter aspect plays a key role in neurocognitive rehabilitation. Experiments obtained on 35 real patients and comparative evaluations, conducted by five therapists, of the proposed tool with respect to the traditional neurocognitive rehabilitation methods highlight remarkable results in terms of motivation, acceptance, and usability as well as recovery of lost skills.

show abstract

“…Human action recognition plays an important role in the extraction of specific activity clips from the long duration videos. Human actions are divided as gestures like palm movement, simple actions like walking, interaction like two people shaking hands and group activity like many people walking together [1]. Methods developed for all these action recognition tasks vary as per the application.…”

Section: Introductionmentioning

confidence: 99%

Human Action Recognition using Scaled Convolutional Neural Network

Jahagirdar*,

Nagmode

2019

IJEAT

View full text Add to dashboard Cite

Deep learning is current buzz word in domain of computer vision. In this work, a method for human action recognition based on a variation of General Convolutional Neural Network (GCNN), called Scaled CNN (SCNN) is proposed. In GCNN, weights of the network are updated in every epoch of training to minimize the classification error. In SCNN, the weighs are first computed using gradient descent algorithm as in GCNN, and then multiplied by scaling factor. Scaling factor is calculated using statistical measures, mean and standard deviation of the frames. Since statistical measures vary from video to video, scaling factor adapts to these changes. As the statistical information from the frames is directly used to alter the weights, it results in minimizing the error faster as compared to GCNN. Results of the proposed method prove that higher accuracy can be achieved with less number of epochs if scaling is used.

show abstract

Human Action Recognition using 3D Convolutional Neural Networks with 3D Motion Cuboids in Surveillance Videos

Cited by 85 publications

References 10 publications

A Novel Low Processing Time System for Criminal Activities Detection Applied to Command and Control Citizen Security Centers

A Novel Low Processing Time System for Criminal Activities Detection Applied to Command and Control Citizen Security Centers

Design of a 3D Platform for Immersive Neurocognitive Rehabilitation

Human Action Recognition using Scaled Convolutional Neural Network

Contact Info

Product

Resources

About