Feature extraction for stereoscopic vision depth map based on principal component analysis and histogram of oriented depth gradient

doi:10.11772/j.issn.1001-9081.2016.01.0222

Journal of Computer Applications ›› 2016, Vol. 36 ›› Issue (1): 222-226.DOI: 10.11772/j.issn.1001-9081.2016.01.0222

Previous Articles Next Articles

Feature extraction for stereoscopic vision depth map based on principal component analysis and histogram of oriented depth gradient

DUAN Fengfeng^1,2, WANG Yongbin¹, YANG Lifang¹, PAN Shujing¹

1. College of Computer Science, Communication University of China, Beijing 100024, China;
2. Cultural Resources Research and Development Center of Hunan, Hunan Normal University, Changsha Hunan 410081, China

Received:2015-07-27 Revised:2015-08-28 Online:2016-01-10 Published:2016-01-09
Supported by:
This work is partially supported by the National Key Technology Research and Development Program of the Ministry of Science and Technology of China (2012BAH37F02), the Science and Technology Innovation Project of Ministry of Culture of China (2014KJCXXM08).

基于主成分分析方向深度梯度直方图的立体视觉深度图特征提取

段峰峰^1,2, 王永滨¹, 杨丽芳¹, 潘淑静¹

1. 中国传媒大学计算机学院, 北京 100024;
2. 湖南师范大学湖南文化资源开发研究中心, 长沙 410081

通讯作者: 段峰峰(1982-),男,安徽亳州人,讲师,博士研究生,主要研究方向:图像处理和检索、网络新媒体
作者简介:王永滨(1963-),男,北京朝阳人,教授,博士,CCF会员,主要研究方向:网络新媒体、多媒体大数据处理、信息安全;杨丽芳(1984-),女,江西贵溪人,工程师,博士,CCF会员,主要研究方向:图像处理和检索、高维索引;潘淑静(1991-),女,河南新乡人,硕士研究生,主要研究方向:图像处理和检索。
基金资助:
国家科技支撑计划资助项目(2012BAH37F02);文化部科技创新项目(2014KJCXXM08)。

Abstract

Abstract: To solve the low accuracy and high complexity in feature extraction of stereoscopic vision depth map, a feature extraction algorithm based on Principal Component Analysis and Histogram of Oriented Depth Gradient (PCA-HODG) was proposed. Firstly, disparity computation and depth map extraction were executed for binocular stereoscopic vision image to obtain high quality depth map; secondly, edge detection and gradient calculation of depth map within fixed size window were performed, then the features of region shape histograms were acquired and quantified. Meanwhile, dimensionality reduction by Principal Component Analysis (PCA) was implemented; finally, to realize the accuracy and completeness of feature extraction from depth map, a detection method of sliding window was used for the feature extraction of whole depth map and the dimensionality reduction was implemented once again. In the experiment of feature matching and classification, for the frames of test sequence Street, the average classification accuracy rate of the proposed algorithm increased by 1.15% when compared with the Range-Sample Depth Feature (RSDF) algorithm; while for Tanks, Tunnel, Temple, the average classification accuracy rate increased by 0.69%, 1.95%, 0.49% respectively when compared with the Geodesic Invariant Feature (GIF) algorithm. At the same time, the average running time decreased by 71.65%, 78.05%, 80.06% respectively compared with the Histogram of Oriented Depth (HOD), RSDF, GIF algorithm. The experimental results show that the proposed algorithm can not only detect and extract features of depth map more accurately, but also reduce the running time greatly by dimensionality reduction. Moreover, the proposed algorithm also has better robustness.

Key words: feature extraction, stereoscopic vision, depth map, sliding window, dimensionality reduction

摘要： 针对立体视觉深度图特征提取精确度低、复杂度高的问题,提出了一种基于主成分分析方向深度梯度直方图(PCA-HODG)的特征提取算法。首先,对双目立体视觉图像进行视差计算和深度图提取,获取高质量深度图;然后,基于预设大小窗口对所获取的深度图进行边缘检测和梯度计算,获得区域形状直方图特征并量化;同时运用主成分分析(PCA)进行降维;最后,为实现特征获取的精确性和完整性,采用滑动窗口检测方法实现整幅深度图的特征提取,并再次降维。在特征匹配分类实验中,对于Street测试序列帧,该算法比距离样本深度特征(RSDF)算法平均分类准确率提高了1.15%,而对于Tanks、Tunnel、Temple测试序列帧,该算法比测度不变特征(GIF)算法平均分类准确率分别提高了0.69%、1.95%、0.49%;同时与方向深度直方图(HOD)、RSDF、GIF算法相比,平均运行时间分别降低了71.65%、78.05%、80.06%。实验结果表明,该算法不仅能够更精确地检测和提取深度图特征,而且通过降低维数复杂度大大减少了运行时间;同时算法具有较好的鲁棒性。

关键词: 特征提取, 立体视觉, 深度图, 滑动窗口, 降维

CLC Number:

TP391.413

DUAN Fengfeng, WANG Yongbin, YANG Lifang, PAN Shujing. Feature extraction for stereoscopic vision depth map based on principal component analysis and histogram of oriented depth gradient[J]. Journal of Computer Applications, 2016, 36(1): 222-226.

段峰峰, 王永滨, 杨丽芳, 潘淑静. 基于主成分分析方向深度梯度直方图的立体视觉深度图特征提取[J]. 计算机应用, 2016, 36(1): 222-226.

References

[1] 田文君.基于深度图像的三维人脸特征提取[D].北京:北京交通大学,2009.(TIAN W J. 3D face feature extraction based on depth image [D]. Beijing: Beijing Jiaotong University, 2009.)
[2] 范文婕,王命延,杨文姬.基于深度图像的指尖和掌心特征提取方法[J].计算机应用,2015,35(6):1791-1794.(FAN W J, WANG M Y, YANG W J. Feature detection method of fingertip and palm based on depth image [J]. Journal of computer applications, 2015, 35(6): 1791-1794.)
[3] CUI W, WANG W, LIU H. Robust hand tracking with refined CAMshift based on combination of depth and image features [C]// Proceedings of the 2012 IEEE International Conference on Robotics and Biomimetics. Piscataway, NJ: IEEE, 2012: 1355-1361.
[4] ZHAO Y, LIU Z, CHENG H. RGB-depth feature for 3D human activity recognition [J]. China communications, 2013, 10(7): 93-103.
[5] KARPUSHIN M, VALENZISE G, DUFAUX F. Local visual features extraction from texture+depth content based on depth image analysis [C]// Proceedings of the 2014 IEEE International Conference on Image Processing. Piscataway, NJ: IEEE, 2014: 2809-2813.
[6] LU C, JIA J, TANG C. Range-sample depth feature for action recognition [C]// Proceedings of the 2014 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2014: 772-779.
[7] JALAL A, UDDIN M Z, KIM T S. Depth video-based human activity recognition system using translation and scaling invariant features for life logging at smart home [J]. IEEE transactions on consumer electronics, 2012, 58(3): 863-871.
[8] LIU Y, LASANG P, SIEGEL V, et al. Geodesic invariant feature: a local descriptor in depth [J]. IEEE transactions on image processing, 2015, 24(1): 236-248.
[9] DALAL N, TRIGGS B. Histograms of oriented gradients for human detection [C]// Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2005: 886-893.
[10] SPINELLO L, ARRAS K O. People detection in RGB-D data [C]// Proceedings of the 2011 IEEE/RSJ International Conference on Intelligent Robots and Systems. Piscataway, NJ: IEEE, 2011:3838-3843.
[11] LIN Y, WEI S, FU L. Grasping unknown objects using depth gradient feature with eye-in-hand RGB-D sensor [C]// Proceedings of the 2014 IEEE International Conference on Automation Science and Engineering. Piscataway, NJ: IEEE, 2014:1258-1263.
[12] WANG N, GONG X, LIU J. A new depth descriptor for pedestrian detection in RGB-D images [C]// Proceedings of the 21st International Conference on Pattern Recognition. Piscataway, NJ: IEEE, 2012:3688-3691.
[13] BOYKOV Y, VEKSLER O, ZABIH R. Fast approximate energy minimization via graph cuts [J]. IEEE transactions on pattern analysis and machine intelligence, 2001, 23(11): 1222-1239.
[14] DUAN F, WANG Y, YANG L, et al. Spatio-temporal consistency in stereoscopic video depth map sequence estimation [J]. Journal of information and computational science, 2014, 11(18):6497-6508.
[15] LEE S B, HO Y S. Temporally consistent depth map estimation for 3D video generation and coding [J]. China communications, 2013, 10(5): 39-49.
[16] 张永库,李云峰,孙劲光.基于多特征融合的图像检索[J].计算机应用,2015,35(2):495-498.(ZHANG Y K, LI Y F, SUN J G. Image retrieval based on multi-feature fusion [J]. Journal of computer applications, 2015, 35(2):495-498.)
[17] RICHARDT C, ORRD D, DAVIES I, et al. Real-time spatiotemporal stereo matching using the dual-cross-bilateral grid [C]// Proceedings of the 2010 European Conference on Computer Vision. Berlin: Springer, 2010: 510-523.

Feature extraction for stereoscopic vision depth map based on principal component analysis and histogram of oriented depth gradient

基于主成分分析方向深度梯度直方图的立体视觉深度图特征提取

PDF

Knowledge

Abstract

Cite this article

share this article

References

Related Articles 15

Recommended Articles

Metrics

[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]	JING Xinghong, SUN Guodong, HE Shibiao, LIAO Yong. Time-varying channel estimation method based on sliding window filtering and polynomial fitting [J]. Journal of Computer Applications, 2021, 41(9): 2699-2704.
[3]	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.
[4]	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.
[5]	Yang ZHANG, Xiaoning WANG. Text feature selection method based on Word2Vec word embedding and genetic algorithm for biomarker selection in high-dimensional omics [J]. Journal of Computer Applications, 2021, 41(11): 3151-3155.
[6]	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.
[7]	YIN Chunyong, HE Miao. Text classification based on improved capsule network [J]. Journal of Computer Applications, 2020, 40(9): 2525-2530.
[8]	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.
[9]	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.
[10]	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.
[11]	QIU Yuan, Chang Xiangmao, QIU Qian, PENG Cheng, SU Shanting. Stream data anomaly detection method based on long short-term memory network and sliding window [J]. Journal of Computer Applications, 2020, 40(5): 1335-1339.
[12]	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.
[13]	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.
[14]	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.
[15]	CHEN Meijie, XIE Zhenping, CHEN Xiaoqi, XU Peng. Novel bidirectional aggregation degree feature extraction method forpatent new word discovery [J]. Journal of Computer Applications, 2020, 40(3): 631-637.