Suspicious Activity Detection Using Deep Learning Approach

Video Surveillance plays a pivotal position in today's global. The technologies have superior an excessive amount of when synthetic intelligence., gadget learning, and deep learning are pitched into the gadget. the usage of the above mixtures, exceptional systems are in a region which helps to differentiate various suspicious behaviors from the live monitoring of photos. Human behavior is the most unpredictable, and it is very difficult to determine whether it is suspicious or normal. In this paper, we have classified human activities into two: Normal and Suspicious. Normal activities include sitting, walking, jogging,hand waving, etc. Suspicious activities include running, boxing, fighting, etc. We achieve this classification by using convolutional neural networks. First, the convolutional neural network is used to extract high- level features from images. The convolutional network classification is taken into account, the final poolinglayer result is extracted and the final prediction is made.