An Object Recognition Strategy Base upon Foreground Detection

Unmanned aerial vehicles equipped with surveillance system have begun to play an increasingly important role in recent years, which has provided valuable information for us. Object recognition is necessary in processing video information. However, traditional recognition methods based on object segmentation can hardly meet the system demands for running online. In this paper, we have made use of SVM based upon HOG feature descriptors to achieve online recognizing passersby in an UAV platform, and designed an object recognition framework based on foreground detection. In order to accelerate the processing speed of the system, our scheme adopts recognizing objects only in the foreground areas which largely reduces searching scope. In conclusion, our methods can recognize specified objects and have a strong anti-jamming capability to the background noise.