Abstract：Inspired by the way in which humans perceive the environment,a memory-based cognitive model for visual information processing is proposed to imitate some cognitive functions of human brain. The proposed model includes five components: information granule,memory spaces cognitive behaviors,rules for manipulating information among memory spaces,and decision-making processes. According to the three-stage memory model of human brain,three memory spaces are defined to store the current,temporal and permanent visual information respectively,i.e. ultra short-term memory space (USTMS),short-term memory space (STMS) and long-term memory space (LTMS). The past scenes can be remembered or forgotten by the proposed model,and thus the model can adapt to the variation of the scene. The proposed model is applied to two hot issues in computer vision: background modeling and object tracking. Experimental results show that the proposed model can deal with scenes with sudden background,object appearance changing and heavy object occlusions under complex background.
[1\]Wang Yingxu,Chiew V. On the Cognitive Process of Human Problem Solving. Cognitive Systems Research,2010,11(1): 81-92 [2]Wang Yingxu. Formal Description of the Cognitive Process of Memorization. IEEE Trans on Computational Intelligence,2009,11(3): 1-15 [3]James W. The Principles of Psychology. New York,USA: Henry Holt,1890 [4]Atkinson R C,Shiffrin R M. Human Memory: A Proposed System and Its Control Processes // Spence K W,Spence J T,eds. Psychology of Learning and Motivation. New York,USA: Academic Press,1968,Ⅱ: 89-195 [5]Baddeley A D,Hitch G. Working Memory //Bower G A,ed. Psychology of Learning and Motivation.New York,USA: Academic Press,1974,Ⅷ: 47-89 [6]Wang Yingxu,Wang Ying. Cognitive Informatics Models of the Brain. IEEE Trans on Systems,Man and Cybernetics,2006,36(2): 203-207 [7]Lin J H,Vitter J S,Hellerstein L. A Theory for Memory Based Learning. Machine Learning,1994,17(2/3): 143-167 [8]Putze F,Schultz T. Cognitive Memory Modeling for Interactive Systems in Dynamic Environments // \[EB/OL\]. \[2012-11-01\]. csl. ira. uka. de/ fileadmin/ media/ publication_files/ PutzeSehultz_ZWSDS09.pdf [9]Yang Zhixiao,Fan Yanfeng,Zhang Bin,et al. A Computation Memory Model with Human Memory Features for Autonomous Virtual Humans // Proc of the International Conference on Computer Application and System Modeling. Taiyuan,China,2010,III: 246-250 [10]Dinerstein J,Egbert P K,Garis H,et al. Fast and Learnable Behavioral and Cognitive Modeling for Virtual Character Animation. Computer Animation and Virtual Worlds,2004,15(2): 95-108 [11]Ai Dongmei,Ban Xiaojuan,Zhang Shujun,et al. Cognitive Modeling of Artificial Fish Learning and Memory // Proc of the 12th International Symposium on Artificial Life and Robotics.Beppu,Japan,2007: 280-283 [12]Ho W C,Dautenhahn K,Lim M Y,et al. Modeling Human Memory in Robotic Companions for Personalization and Long Term Adaptation in HRI // Proc of the 1st Annual Meeting of the Biologically Inspired Cognitive Architecture Society. Washington,USA,2010: 64-71 [13]Huang Shan,Sadek A W. A Novel Forecasting Approach Inspired by Human Memory: The Example of Short Term Traffic Volume Forecasting. Transportation Research Part C: Emerging Technologies,2009,17(5): 510-525 [14]Luo Siwei. The Perception Computing of Visual Information. Beijing,China: Science Press,2010(in Chinese) (罗四维.视觉信息认知计算理论.北京:科学出版社,2010) [15]Eysenck M W,Keane M T. Cognitive Psychology: A Student's Handbook. 6th Edition. New York,USA: Psychology Press,2010 [16]Qi Yujuan,Wang Yanjiang,Li Yongping. Memory Based Gaussian Mixture Background Modeling. Acta Automatica Sinica,2010,36(11): 1520-1526(in Chinese) (齐玉娟,王延江,李永平.基于记忆的混合高斯背景建模.自动化学报,2010,36(11): 1520-1526) [17]Qi Yujuan,Wang Yanjiang. Robust Object Tracking by Particle Filter Based on Human Memory Model. Pattern Recognition and Artificial Intelligence,2012,25(5): 810-816 (in Chinese) (齐玉娟,王延江.基于人类记忆模型的粒子滤波鲁棒目标跟踪算法.模式识别与人工智能,2012,25(5): 810-816) [18]Skowron A,Stepaniuk J. Information Granules: Towards Foundations of Granular Computing. International Journal of Intelligent Systems,2001,16(1): 57-85 [19]Lee D S. Effective Gaussian Mixture Learning for Video Background Subtraction. IEEE Trans on Pattern Analysis and Machine Intelligence,2005,27(5): 827-832 [20]Shen Zhixi,Yang Xin,Huang Xiyue. Study on Target Model Update Method in Mean Shift Algorithm. Acta Automatica Sinica,2009,35(5): 478-483 (in Chinese). (沈志熙,杨 欣,黄席樾.均值漂移算法中的目标模型更新方法研究.自动化学报,2009,35(5): 478-483)
2013, Vol. 26 
