Video Tracking of Insect Flight Path: Towards Behavioral Assessment

In this paper, we propose a cohort of new methods that cooperate together to improve the detection/tracking of mosquitos in a 2D video clip. A commonly recognized challenge in the biotechnology research field is evaluating the effect of a repellent which entails tracking the unpredictable flight paths of the insects, which may be swift flying or slow moving. Our work presented in this paper provides an efficient tool to deal with tracking the small insects with unpredictable moving patterns by proposing a new dual foreground and background modeling/updating system for target detecting and tracking. The proposed processing elements take advantage of the similarity of the frames and use the estimated speeds to collectively capture the relevant information and contribute in concert to ensure fast and accurate measurement to reach the goal of behavior evaluation of mosquitos in response to a repellent.