Towards Intelligent Human Behavior Detection for Video Surveillance

Nigam, Swati; Singh, Rajiv; Misra, A. K.

doi:10.4018/978-1-5225-5628-2.ch003

Cited by 2 publications

(1 citation statement)

References 73 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Key frame-based saliency detection and real-time action with 3D deep learning are also part of HAR [41,42]. The arrangement of HAR is created as structures to enable the constant checking and examination of human practices in various zones, for example, clever human action and conduct investigation intelligent human activity and behavior analysis [33,[43][44][45][46], sports injury detection [47], patient rehabilitation [33], monitor activity shifts amid elderly citizens that might be helpful to detect and diagnose serious illness [48,49], monitoring children's surveillance, hospital/patient monitoring [50,51], recognition and classification of the human usual and unusual activities [26,[52][53][54][55][56], human behavior recognition and human activity detection [53,57,58], criminal tracking system [59,60], automatic attendance system [61,62], etc.…”

Section: Literature Reviewmentioning

confidence: 99%

Suspicious Activity Recognition Using Proposed Deep L4-Branched-Actionnet With Entropy Coded Ant Colony System Optimization

et al. 2021

View full text Add to dashboard Cite

Intelligent visual surveillance systems are attracting much attention from research and industry. The invention of smart surveillance cameras with greater processing power has now been the leading stakeholder, making it conceivable to design intelligent visual surveillance systems. It is possible to assure the safety of people in both homes and public places. This work aims to distinguish the suspicious activities for surveillance environments. For this, a 63 layers deep CNN model is suggested and named "L4-Branched-ActionNet". The suggested CNN structure is centered on the alteration of AlexNet with added four blanched sub-structures. The developed framework is first transformed into a pre-trained framework by conducting its training on an object detection dataset called CIFAR-100 with the SoftMax function. The dataset for suspicious activity recognition is then forwarded to this pretrained model for feature acquisition. The acquired deep features are subjected to feature subset optimization. These extracted features are first coded by applying entropy and then an ant colony system (ACS) is utilized on the entropy-based coded features for optimization. The configured features are then fed into numerous SVM and KNN based classification models. The cubic SVM has the highest efficiency scores, with a performance of 0.9924 in terms of accuracy. The proposed model is also validated on the Weizmann action dataset and attained an accuracy of 0.9796. The successful findings indicate the suggested work's soundness.

show abstract