Using postural data and recurrent learning to monitor shoplifting activities in megastores

Abstract

Recently, researchers have placed a great deal of emphasis on modeling activity pat terns to better understand human behavior. Several approaches have been researched so far to develop automatic human activity recognition systems that infer detailed semantics from visual images, aiming to understand real human behavior patterns. However, there is still a need for a cost effective solution to distinguish human actions in the real-world environment. With this encouragement, a novel approach is pro posed to recognize shoplifting acts by examining the posture evidence of the human being. This approach begins by obtaining the two-dimensional pose reflecting human’s body joints as a skeleton from the recorded frames. Subsequently, a preprocessing step is used to preprocess skeleton data, which can handle the occlusion too. Pos tural feature generation is then used to extract pertinent features from such pre processed skeletons. Finally, feature deduction is performed to downsize the derived features to a smaller dimension, and activity classification is performed on such reduced features to identify shoplifting behaviors in real time. A synthetic shoplifting dataset and real store recorded videos are used to conduct the experiments, the find ings of which appear more promising than those obtained using other cutting-edge methods, with an accuracy of 97.36% and 91.66% for synthesized and real store recorded inputs.