Computational Model Based on Neural Network of Visual Cortex for Human Action Recognition

doi:10.1109/TNNLS.2017.2669522

CASIA OpenIR > 多模态人工智能系统全国重点实验室 > 人工智能与机器学习（杨雪冰）-技术团队

	Computational Model Based on Neural Network of Visual Cortex for Human Action Recognition
	Liu, Haihua 1,2,3; Shu, Na 1; Tang, Qiling 1; Zhang, Wensheng4
发表期刊	IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
	2018-05-01
卷号	29 期号:5 页码:1427-1440
文章类型	Article
摘要	In this paper, we propose a bioinspired model for human action recognition through modeling neural mechanisms of information processing in two visual cortical areas: the primary visual cortex (V1) and the middle temporal cortex (MT) dedicated to motion. This model, named V1-MT, is composed of V1 and MT models (layers) corresponding to their cortical areas, which are built with layered spiking neural networks (SNNs). Some neuron properties in V1 and MT, such as direction and speed selectivity, spatiotemporal inseparability, and center surround suppression, are integrated into SNNs. Based on speed and direction selectivity, V1 and MT models contain multiple SNN channels, each of which processes motion information in sequences with spatiotemporal tunings of neurons at a certain speed and different directions. Therefore, we propose two operations, input signal perceiving with 3-D Gabor filters and surround inhibition processing with 3-D differences of Gaussian functions, to perform this task according to the spatiotemporal inseparability and center surround suppression of neurons. Then, neurons are modeled with our simplified integrate-and-fire model and motion information is transformed into spike trains. Afterward, we define a new feature vector: a mean motion map computed from spike trains in all channels to represent human actions. Finally, a support vector machine is trained to classify actions represented by the feature vectors. We conducted extensive experiments on public action databases, and the results show that our model outperforms other bioinspired models and rivals the state-of-the-art approaches.
关键词	Action Recognition Classical Receptive Field (Rf) Spiking Neural Networks (Snns) Surround Suppression Visual Cortex
WOS标题词	Science & Technology ; Technology
DOI	10.1109/TNNLS.2017.2669522
关键词[WOS]	CELL RECEPTIVE-FIELDS ; BIOLOGICAL MOTION ; SPATIOTEMPORAL ORGANIZATION ; GABOR FILTERS ; VISION SENSOR ; FEATURES ; ARCHITECTURE ; ENHANCEMENT ; SUPPRESSION ; SELECTIVITY
收录类别	SCI
语种	英语
项目资助者	National Natural Science Foundation of China(91320102 ; 60972158 ; 61432008 ; 61532006)
WOS研究方向	Computer Science ; Engineering
WOS类目	Computer Science, Artificial Intelligence ; Computer Science, Hardware & Architecture ; Computer Science, Theory & Methods ; Engineering, Electrical & Electronic
WOS记录号	WOS:000430729100003
引用统计	被引频次：25[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/22032
专题	多模态人工智能系统全国重点实验室_人工智能与机器学习（杨雪冰）-技术团队
作者单位	1.South Cent Univ Nationalities, Sch Biomed Engn, Wuhan 430074, Hubei, Peoples R China 2.Key Lab Cognit Sci State Ethn Affairs Commiss, Wuhan 430074, Hubei, Peoples R China 3.Hubei Key Lab Med Informat Anal & Tumor Diag & Tr, Wuhan 430074, Hubei, Peoples R China 4.Chinese Acad Sci, Inst Automat, Beijing 100190, Peoples R China
推荐引用方式 GB/T 7714	Liu, Haihua,Shu, Na,Tang, Qiling,et al. Computational Model Based on Neural Network of Visual Cortex for Human Action Recognition[J]. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS,2018,29(5):1427-1440.
APA	Liu, Haihua,Shu, Na,Tang, Qiling,&Zhang, Wensheng.(2018).Computational Model Based on Neural Network of Visual Cortex for Human Action Recognition.IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS,29(5),1427-1440.
MLA	Liu, Haihua,et al."Computational Model Based on Neural Network of Visual Cortex for Human Action Recognition".IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 29.5(2018):1427-1440.