Abstract-Pedestrian recognition in aerial video is a challenge problem for the problem of low resolution, camera movement and target's blurred detail in aerial video. This paper proposes weighted region matching algorithm with Kalman filter, Multi-features fusion model and saliency segmentation (KMFS-WRM) to detect and recognize pedestrian. The KMFS-WRM algorithm first uses Kalman filter algorithm to mark candidate's region, which can avoid the problem of selecting candidates under supervision. Then we proposed the fusion algorithm of multi-feature, including HOG, LBP and SIFT features, namely HLS model to detect the pedestrian in aerial video. Our proposed detection method is robust for whether the camera is moving. And instructing human percept and concept, we segment the pedestrians in marked region using Context-Aware saliency detection algorithm that proposed by Goferman et al. and revised the segmentation results by HST model (Head Shoulder and Torso) and AAM model (Active Appearance Model) to obtain the candidates set. Last the matching of voter and candidates set using weighted region matching algorithm. Experimental results in complex aerial video demonstrated that our KMFS-WRM algorithm not only cuts down calculated complexity, but also improves adaptive and real-time ability. Moreover proposed method outperforms recent state-of-the-art methods.Index Terms-Pedestrian detection, saliency detection, Kalman filter algorithm, weight region matching.
I. INTRODUCTIONPedestrian detection and recognition is an essential and significant task in any intelligent video surveillance system, since it provides the fundamental semantic information of video understanding. Along with the urgent demand for video surveillance systems in many security-sensitive occasions, e.g., some large squares, stadiums, super-markets et al., the research on non-contact pedestrian detection and recognition draws more attention. Most existing methods of pedestrian detection and recognition mainly depend on the extraction of features based on image details [1]- [4]. As one of main information source for non-contact pedestrian detection and recognition, aerial video has seen widely used in both military and commercial world application where its advantages over traditional video outweigh its disadvantages, such as poorer Manuscript received December 19, 2013; revised May 5, 2014. This work was supported in part National Science Foundation of China (NSFC Grant No. 61272258, 61170124, 61170020, 61301299).Chunping Liu, Xu Fang, and Shengrong Gong are with School of Computer Science and Technology, Soochow University, Suzhou 215006, China (e-mail: cpliu@suda.edu.cn, fangxu_8040595@126.com, shrgong@suda.edu.cn).Xingbao Wang was with School of Computer science and technology, Soochow University, Suzhou 215006, China. He is now with Anhui USTCiflytek Co., LTD (e-mail: wangxingbao@163.com).spatial resolution, moving video camera, targets with much smaller and more obscure details, complex background and high density pedestrian flow. Therefore, in...