ion generation based on face detection and recognitionXiaokang Wu1, a, Chenggang Xie2, b, Qin Lu2, c1 National University Of Defense Technology, Changsha 410073, China;a172896292@qq.com, bqingqingzijin_k@126.com,Keywords: face detection, face recognition, key frame, video abstractionAbstract. In order to facilitate users browse the behaviors and expressions of interesting objects in a video quickly, need to remove the redundancy information and extract key frames related to the object interested. This paper uses a fast face detection based on skin color, and recognition technology using spectrum feature matching, decompose the coupling video, and classify frames related to the object into different sets, generate a different video abstraction of each object. Experimental results show that the algorithm under different light conditions has better practicability.

Initial rainwater pollution is an important non-point source pollution of urban drainage systems. The application of storage tanks and other reduction facilities has play a key role in reducing first flush pollution. Because of the lack of scientific evaluation system, the evaluation is disorderly and there are many operational problems. This case is based on the reduction facilities research of Suzhou Creek in Shanghai, through which a standard evaluation system and implementation procedure are built to perfect the incomprehensive and unscientific system, so that the efficiency can be improved.

No abstract

To the background establishment in background difference method, a method is proposed to detect moving targets based on the improved Burendra algorithm. This method can accurately detect moving targets in the video images, meanwhile it can respond to the changes of background and light intensity in the scene in time, being with good real-time performance and robustness.