Bird tracking and flapping motion recognition for monitoring system

Recently, the increasing bird injury is one of the social problems. To solve this problem, we set our goal to develop the monitoring system. As the first step, we focus the bird tracking and flapping motion recognition both techniques are core technologies of our goal. It is found that Mean Shift tracking based on both the color model and flow model is the most effective to track the target object compared with other well known tracking methods, such as, optical flow, color model based Mean Shift, and Particle Filter. We defined three features the flow gradient and two flow features based on the frequency analysis, and proposed the method for recognizing the flapping motion. We collected 70 scenes including the bird's flying, bird's walking, and person's walking. As the result, the flow gradient feature is the effective for recognizing the flapping motion.