Behavior classification algorithm based on enhanced gait energy image and two-dimensional locality preserving projection

doi:10.3724/SP.J.1087.2011.00721

Journal of Computer Applications ›› 2011, Vol. 31 ›› Issue (03): 721-723.DOI: 10.3724/SP.J.1087.2011.00721

• Graphics and image technology • Previous Articles Next Articles

Behavior classification algorithm based on enhanced gait energy image and two-dimensional locality preserving projection

LIN Chun-li¹,WANG Ke-jun²,LI Yue²

1. College of Automation, Harbin Engineering University, Harbin Heilongjiang 150001, China; School of the Higher Vocational Education, University of Science and Technology Liaoning, Anshan Liaoning 114051, China
2. ollege of Automation, Harbin Engineering University, Harbin Heilongjiang 150001, China

Received:2010-09-25 Revised:2010-11-23 Online:2011-03-03 Published:2011-03-01
Contact: LIN Chun-li

基于增强能量图和二维保局映射的行为分类算法

林春丽¹,王科俊²,李玥³

1. 哈尔滨工程大学自动化学院，哈尔滨150001; 辽宁科技大学高等职业技术学院，辽宁鞍山114051
2. 哈尔滨工程大学自动化学院，哈尔滨150001
3. 辽宁科技大学高等职业技术学院，辽宁鞍山114051

通讯作者: 林春丽
作者简介:林春丽（1972-），女（满族），辽宁开原人，副教授，博士研究生，主要研究方向：图像处理、模式识别；王科俊(1962-)，男，吉林吉林人，教授，博士，主要研究方向：图像处理、模式识别、人工智能；李玥（1981-），女，辽宁鞍山人，硕士研究生，主要研究方向：图像处理、模式识别。
基金资助:
国家863计划项目（2008AA01Z148）;黑龙江省杰出青年科学基金资助项目（JC200703）

Abstract

Abstract: In action classification, methods of feature extraction were either simple with low accuracy, or complicated with poor real-time quality. To resolve this problem, firstly, Enhanced Gait Energy Image (EGEI) was derived from Gait Energy Image (GEI); secondly, high dimensional feature space of the action was reduced to lower dimensional space by Two-Dimensional Locality Preserving Projection (2DLPP); then Nearest-Neighbor (NN) classifier was adopted to distinguish different actions. EGEI could extract more obvious feature information than GEI; 2DLPP outperformed principal component analysis and locality preserving projections in dimensional reduction. It was tested on the Weizmann human action dataset. The experimental results show that the proposed algorithm is simple, achieves higher classification accuracy, and the average recognition ratio reaches 91.22%.

Key words: action recognition, intelligent surveillance, feature extraction, Enhanced Gait Energy Image (EGEI), Two-Dimensional Locality Preserving Projection (2DLPP)

摘要： 行为分类中，现有的特征提取要么方法简单、识别率低，要么特征提取复杂、实时性差。对此，提出一种算法：将步态能量图（GEI）改进，得到增强步态能量图（EGEI）；然后将二维保局映射（2DLPP）应用于特征空间降维；最后采用最近邻(NN)法分类。EGEI比GEI更能反映目标特征；2DLPP降维效果好于主成分分析(PCA)及一维保局映射。在Weizmann行为数据库上测试，实验结果表明：该算法简单、准确率高，平均识别率达到了91.22%。

关键词: 行为识别, 智能监控, 特征提取, 增强的步态能量图, 二维保局映射

CLC Number:

TP391.41

LIN Chun-li WANG Ke-jun LI Yue. Behavior classification algorithm based on enhanced gait energy image and two-dimensional locality preserving projection[J]. Journal of Computer Applications, 2011, 31(03): 721-723.

林春丽王科俊李玥. 基于增强能量图和二维保局映射的行为分类算法[J]. 计算机应用, 2011, 31(03): 721-723.

[1]	ZHENG Zhiqiang, HU Xin, WENG Zhi, WANG Yuhe, CHENG Xi. Cattle eye image feature extraction method based on improved DenseNet [J]. Journal of Computer Applications, 2021, 41(9): 2780-2784.
[2]	LI Yangzhi, YUAN Jiazheng, LIU Hongzhe. Human skeleton-based action recognition algorithm based on spatiotemporal attention graph convolutional network model [J]. Journal of Computer Applications, 2021, 41(7): 1915-1921.
[3]	GUO Tianxiao, HU Qingrui, LI Jianwei, SHEN Yanfei. Fitness action recognition method based on human skeleton feature encoding [J]. Journal of Computer Applications, 2021, 41(5): 1458-1464.
[4]	JIANG Li, HUANG Shijian, YAN Wenjuan. Human action recognition method based on low-rank action information and multi-scale convolutional neural network [J]. Journal of Computer Applications, 2021, 41(3): 721-726.
[5]	SHE Yulong, ZHANG Xiaolong, CHENG Ruoqin, DENG Chunhua. Semantic segmentation method based on edge attention model [J]. Journal of Computer Applications, 2021, 41(2): 343-349.
[6]	Jin ZHAO, Wen’ai SONG, Jun TAI, Jijiang YANG, Qing WANG, Xiaodan LI, Yi LEI, Yue QIU. Review of computer-aided face diagnosis for obstructive sleep apnea in children [J]. Journal of Computer Applications, 2021, 41(11): 3394-3401.
[7]	ZHU Xincheng, HE Kunjin, NI Na, HAO Bo. Rapid calculation method of orthopedic plate fit based on improved iterative closest point algorithm [J]. Journal of Computer Applications, 2021, 41(10): 3033-3039.
[8]	YIN Chunyong, HE Miao. Text classification based on improved capsule network [J]. Journal of Computer Applications, 2020, 40(9): 2525-2530.
[9]	ZHOU Yun, CHEN Shurong. Behavior recognition method based on two-stream non-local residual network [J]. Journal of Computer Applications, 2020, 40(8): 2236-2240.
[10]	ZHANG Jiagang, LI Daping, YANG Xiaodong, ZOU Maoyang, WU Xi, HU Jinrong. Deformable medical image registration algorithm based on deep convolution feature optical flow [J]. Journal of Computer Applications, 2020, 40(6): 1799-1805.
[11]	XU Dai, YUE Zhang, YANG Wenxia, REN Xiao. Tampered image recognition based on improved three-stream Faster R-CNN [J]. Journal of Computer Applications, 2020, 40(5): 1315-1321.
[12]	GUO Zhiqing, HU Yongwu, LIU Peng, YANG Jie. Outdoor weather image classification based on feature fusion [J]. Journal of Computer Applications, 2020, 40(4): 1023-1029.
[13]	ZHANG Junsheng, XU Jingjing, YU Wei. No-reference image quality assessment method for facial beautification image [J]. Journal of Computer Applications, 2020, 40(4): 1184-1190.
[14]	LIU Shangwang, LIU Chengwei, ZHANG Aili. Real-time facial expression and gender recognition based on depthwise separable convolutional neural network [J]. Journal of Computer Applications, 2020, 40(4): 990-995.
[15]	ZHU Zhe, XU Shaohua. Denoising autoencoder deep convolution process neural network and its application in time-varying signal classification [J]. Journal of Computer Applications, 2020, 40(3): 698-703.

Behavior classification algorithm based on enhanced gait energy image and two-dimensional locality preserving projection

基于增强能量图和二维保局映射的行为分类算法

PDF

Knowledge

Abstract

Cite this article

share this article

References

Related Articles 15

Recommended Articles

Metrics