Studies have shown that the human capability of monitoring multiple surveillance videos is limited. Computer vision techniques have been developed to detect abnormal events to support human video surveillance; however, their results are often unreliable, thus distracting surveillance operators and making them miss important events. This article presents Hotspot as a surveillance video visualization system that can effectively leverage noisy computer vision techniques to support human video surveillance. Hotspot consists of two views: a designated focus view to summarize videos with detected events and a video-bank view surrounding the focus view to display source surveillance videos. The focus view allows an operator to quickly dismiss false alarms and focus on true alarms. The video-bank view allows for extended human video analysis after an important event is detected. Hotspot further provides visual links to assist quick attention switch from the focus view to the video-bank view. Our experiments show that Hotspot can effectively integrate noisy, automatic computer vision detection results and better support human video surveillance tasks than the baseline video surveillance with no or only basic computer vision support.
Improvement in Classification Accuracy Rate Using Multiple Classifier Fusion Towards Computer Vision Detection of Malaria Parasite (Plasmodium vivax)
