Research Article Visual Tracking Using an Insect Vision Embedded Particle Filter Wei Guo, 1 Qingjie Zhao, 1 and Dongbing Gu 2 1 Beijing Key Laboratory of Intelligence Information Technology, School of Computer Science, Beijing Institute of Technology, Beijing 100081, China 2 School of Computer Science and Electronic Engineering, University of Essex, Wivenhoe Park, Colchester CO4 3SQ, UK Correspondence should be addressed to Wei Guo; gwbit0731@gmail.com Received 22 September 2014; Accepted 16 January 2015 Academic Editor: Ebrahim Momoniat Copyright © 2015 Wei Guo et al. his is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited. Particle iltering (PF) based object tracking algorithms have drawn great attention from lots of scholars. he core of PF is to predict the possible location of the target via the state transition model. One commonly adopted approach is resorting to prior motion cues under the smooth motion assumption, which performs well when the target moves with a relatively stable velocity. However, it would possibly fail if the target is undergoing abrupt motion. To address this problem, inspired by insect vision, we propose a simple yet efective visual tracking framework based on PF. Utilizing the neuronal computational model of the insect vision, we estimate the motion of the target in a novel way so as to reine the position state of propagated particles using more accurate transition mode. Furthermore, we design a novel sample optimization framework where local and global search strategies are jointly used. In addition, we propose a new method to monitor long duration severe occlusion and we could recover the target. Experiments on publicly available benchmark video sequences demonstrate that the proposed tracking algorithm outperforms the state-of-the art methods in challenging scenarios, especially for tracking target which is undergoing abrupt motion or fast movement. 1. Introduction Visual tracking is of great signiicance in many vision applications such as video surveillance and human-computer interaction. In recent years, numerous algorithms have been proposed in the development of tracking algorithms and much success has been demonstrated under various scenar- ios. Nevertheless, numerous issues, such as abrupt motion, fast movement, and severe occlusion, remain to be addressed. Generally, the tracking algorithms fall into two main cate- gories: the generative algorithms [1–5] and the discriminative algorithms [6–10]. Generative tracking algorithms typically learn a target model to represent the target object and then try to search for the best image region most similar to the target model. Discriminative algorithms view the tracking problem as a binary classiication task to separate the target object from its local background. he particle iltering- (PF-) based tracking algorithms are very popular generative algorithms since they can efec- tively solve the nonlinear and non-Gaussian problems. In the PF-based tracking process, the state transition model plays a vital role in predicting the possible location of the target. One commonly adopted approach to propagate the sample set is resorting to prior motion cues and amending the prediction according to the Gaussian distribution [5, 11– 16]. his approach performs well when target moves with a relatively stable velocity or with a predictable motion pattern [12, 17]. However, in the real world, abrupt motion or fast movement scenarios are frequently available, thereby causing these algorithms to drit away the target objects gradually and even lose the target. Another predictable and reasonable approach is utilizing the motion direction and moving speed of the target to revise the state transition model so as to reine a more accurate position. To solve those problems, in this paper, we propose a simple yet efective insect vision inspired framework of visual tracking based on PF. In a cluttered moving background, ly- ing insects demonstrate extraordinary capability in locating and detecting visual objects. Insect ommateum can respond to the motion pattern including the motion direction and Hindawi Publishing Corporation Mathematical Problems in Engineering Volume 2015, Article ID 573131, 16 pages http://dx.doi.org/10.1155/2015/573131