Optical flow method is an important and valid method in the field of detection and tracking of moving objects for robot inspection system. Due to the traditional Horn-Schunck optical flow method and Lucas-Kanade optical flow method cannot meet the demands of real-time and accuracy simultaneously, an improved optical flow method based on Gaussian image pyramid is proposed. The layered structure of the images can be obtained by desampling of the original sequential images so that the motion with the high speed can be changed into continuous motion with lower speed. Then the optical flows of corner points of the lowest layer will be calculated by the LK method and be delivered to the upper layer and so on. Thus the estimated optical flow vectors of the original sequential images will be obtained. In this way, the requirement of accuracy and real time could be met for robotic moving obstacle recognition.
Real-Time Detection and Motion Recognition of Human Moving Objects Based on Deep Learning and Multi-Scale Feature Fusion in Video