Abstract In today’s scenario human detection and tracking in video surveillance is important aspect because of the abnormal action detection, person identification, activity recognition etc. Detecting human beings and recognizing event in a video surveillance system plays a major role in computer vision. The proposed model finds actions like walking, talking etc. This research work is mainly concentrated on detection of human object and tracking to avoid the challenges involved in difficult condition. The proposed model exhibits a new approach for the human object detection, i.e. based on Cluster segmentation approach. The considered input video will be divided into number of frames using frame generation block, followed by cluster segmentation and feature extraction. Feature extraction is done based on the Histogram of gradient. Classification will be done using Support Vector Machine algorithm; each object activity will be detected based on the result obtained by classification. The proposed model calculates accuracy of detection of each object up to 89.59%.
[1]
Marjorie Skubic,et al.
Fall Detection in Homes of Older Adults Using the Microsoft Kinect
,
2015,
IEEE Journal of Biomedical and Health Informatics.
[2]
Qi Tian,et al.
Recognizing human group action by layered model with multiple cues
,
2014,
Neurocomputing.
[3]
Ling Shao,et al.
Enhanced Computer Vision With Microsoft Kinect Sensor: A Review
,
2013,
IEEE Transactions on Cybernetics.
[4]
Alberto Del Bimbo,et al.
Submitted to Ieee Transactions on Cybernetics 1 3d Human Action Recognition by Shape Analysis of Motion Trajectories on Riemannian Manifold
,
2022
.
[5]
Ling Shao,et al.
Human action segmentation and recognition via motion and shape analysis
,
2012,
Pattern Recognit. Lett..
[6]
Alessio Del Bue,et al.
Human behavior analysis in video surveillance: A Social Signal Processing perspective
,
2013,
Neurocomputing.