Comparative Evaluations of Human Behavior Recognition Using Deep Learning

Comparative Evaluations of Human Behavior Recognition Using Deep Learning

Jia Lu (Auckland University of Technology, New Zealand) and Wei Qi Yan (Auckland University of Technology, New Zealand)
Copyright: © 2020 |Pages: 14
DOI: 10.4018/978-1-7998-2701-6.ch009
OnDemand PDF Download:
No Current Special Offers


With the cost decrease of security monitoring facilities such as cameras, video surveillance has been widely applied to public security and safety such as banks, transportation, shopping malls, etc. which allows police to monitor abnormal events. Through deep learning, authors can achieve high performance of human behavior detection and recognition by using model training and tests. This chapter uses public datasets Weizmann dataset and KTH dataset to train deep learning models. Four deep learning models were investigated for human behavior recognition. Results show that YOLOv3 model is the best one and achieved 96.29% of mAP based on Weizmann dataset and 84.58% of mAP on KTH dataset. The chapter conducts human behavior recognition using deep learning and evaluates the outcomes of different approaches with the support of the datasets.
Chapter Preview

Human behavior understanding refers to analyze and recognize human motion patterns, and describe it with natural languages (Aggarwal et al., 1997). The motion sequence can be considered as the traversal process of static actions in different state nodes (Guo et al., 1994). The joint probability of traversal process is therefore calculated, its maximum value is taken into consideration for classification (Fujiyoshi et al., 2004).

Complete Chapter List

Search this Book: