全部 标题 作者
关键词 摘要

OALib Journal期刊
ISSN: 2333-9721
费用:99美元

查看量下载量

相关文章

更多...
电子学报  2015 

一种改进型机器人仿生认知神经网络

DOI: 10.3969/j.issn.0372-2112.2015.06.007, PP. 1084-1089

Keywords: 注意力选择,仿生认知神经网络,机器人,视觉

Full-Text   Cite this paper   Add to My Lib

Abstract:

为了更好地模拟人类视觉系统中的注意力选择,本文提出一种改进型机器人仿生认知神经网络.首先模拟人类视觉皮层结构,在已有模型基础上建立改进型仿生认知神经网络模型;增加位置层(PositionMotor,PM)到感受野(ReceptiveField,RF)的自上而下(top-down)的视觉注意,同时下颞叶(InferiorTemporal,IT)不再接收全局视觉信息,而改为接收带有自下而上(bottom-up)视觉注意的局部信息,不仅降低数据处理的复杂度,也更加符合人类格式塔心理;最后利用该模型实现机器人复杂背景下目标识别与跟踪.实验结果证明该方法在有效减少数据冗余、缩短处理时间的同时,还可有效提高机器人视觉系统对目标的识别准确率.

References

[1]  Deco G, Rolls E T.A neurodynamical cortical model of visual attention and invariant object recognition[J].Vision Research, 2004, 44(6):621-642.
[2]  Itti L, Koch C.Computational modelling of visual attention[J].Nature Reviews Neuroscience, 2001, 2(3):194-203.
[3]  Itti L, Koch C.A saliency-based search mechanism for overt and covert shifts of visual attention[J].Vision Research, 2000, 40(10):1489-1506.
[4]  Weng J, Luwang T, Lu H, et al.A multilayer in-place learning network for development of general invariances[J].International Journal of Humanoid Robotics, 2007, 4(02):281-320.
[5]  Ji Z, Weng J, Prokhorov D.Where-what network 1:"Where" and "What" assist each other through top-down connections[A].7th IEEE International Conference on Development and Learning[C].Monterey:IEEE, 2008.61-66.
[6]  Ji Z, Weng J.WWN-2:A biologically inspired neural network for concurrent visual attention and recognition[A].The IEEE 2010 International Joint Conference on Neural Networks[C].Barcelona:IEEE, 2010.1-8.
[7]  Luciw M, Weng J.Where What Network 3:Developmental top-down attention with multiple meaningful foregrounds[A].International Joint Conference on Neural Networks[C].Barcelona:IEEE, 2010.4233-4240.
[8]  Chou J R.A Gestalt-Minimalism-based decision-making model for evaluating product form design[J].International Journal of Industrial Ergonomics, 2011, 41(6):607-616.
[9]  Weng J, Luciw M.Dually optimal neuronal layers:Lobe component analysis[J].IEEE Transactions on Autonomous Mental Development, 2009, 1(1):68-85.
[10]  Qian K, Song A G, Bao J T, et al.Small teleoperated robot for nuclear radiation and chemical leak detection[J/OL].International Journal of Advanced Robotic Systems, 2012, 9.http://www.intechopen.com/journals/international-journal-of-advanced-robotic-systems, 2012-09-19.
[11]  Song X, Zhang W, Weng J.Where-what network 5:Dealing with scales for objects in complex backgrounds[A].International Joint Conference on Neural Networks[C].San Jose:IEEE, 2011.2795-2802.
[12]  王守觉.仿生模式识别(拓扑模式识别)—一种模式识别新模型的理论与应用[J].电子学报, 2002, 30(10):1417-1420. WANG Shou-jue.Bionic(topological)pattern recognition—a new model of pattern recognition theory and its applications[J].Acta Electronica Sinica, 2002, 30(10):1417-1420.(in Chinese)
[13]  刘炳尧, 秦世引.基于概念空间学习认知的机器人目标识别方法[J].北京航空航天大学学报, 2012, 38(11):1502-1506, 1511. Liu Bing-yao, Qin Shi-yin.Robot object recognition based on learning and cognition with conceptual space[J]. Journal of Beijing University of Aeronautics and Astronautics, 2012, 38(11):1502-1506, 1511.(in Chinese)
[14]  Rabinovich Z L.Natural thinking mechanisms and computer intelligence[J].Cybernetics and Systems Analysis, 2003, 39(5):695-700.

Full-Text

Contact Us

service@oalib.com

QQ:3279437679

WhatsApp +8615387084133