Relation Tracking of Occluded objects using a Perspective Depth
Hwa-Jin Park · Journal of Digital Contents Society · 2015
Networked multiple CCTV systems are required to effectively trace down long-term abnormal behaviors, such as stalking.However, the occluding event, which often takes place during tracking, may result in critical errors of cessation of tracing, or tracking wrong objects.Thus, utilizing installed regular CCTVs, this study aims to trace the relation tracking in a continuous manner by recognizing distinctive features of each object and its perspective projection depth to address the problem with occluded objects.In addition, this study covers occlusion event between the stationary background objects, such as street lights, or walls, and the targeted object.