结合场景运动模式的有向加权AdaBoost目标检测

doi:10.3969/j.issn.1001-2400.2015.03.012

Abstract

Abstract:

The regular behavior reflected by the interaction of spatial layout and interior elements of the scene with the moving object is named the scene motion pattern. In this paper, a novel approach of the object detection combining scene motion pattern with the directed AdaBoost weighting method is proposed to remedy the limitation of the existing detection algorithms that give little consideration of the object motion regularity and the priori information about the scene. For this reason, a model of the scene motion pattern described by a matrix of speed-weighting directed histogram is created, and the information about the scene motion pattern is acquired by the voting of the sparse optical flows on that basis. Meanwhile, a directed AdaBoost weighting detection algorithm is developed correspondingly. A set of directed AdaBoost classifiers which are then weighted according to the motion pattern of the region are established in the algorithm. According to the specially designed cross-validation classification experiments and video tests, the precision rates of the algorithm are about 10％ higher than that of standard AdaBoost detector under the same condition of the false positive rate, which proves the effectiveness and the advancements of the proposed approach.

Key words: object detection, scene motion pattern, directed AdaBoost, weighted classification, optical flows

CLC Number:

P315.69

QU Jianming;LIU Zhijing;HE Wenhua. Directed AdaBoost weighting classifier based on the scene motion pattern for object detection[J].J4, 2015, 42(3): 67-72.

References

［1］ Dollar P, Wojek C, Schiele B, et al. Pedestrian Detection: an Evaluation of the State of the Art ［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2012, 34(4): 743-761.
［2］ Shantaiya S, Verma K, Mehta K. A Survey on Approaches of Object Detection ［J］. International Journal of Computer Applications, 2013, 65(18): 14-20.
［3］ Dalal N, Triggs B. Histograms of Oriented Gradients for Human Detection ［C］//IEEE Computer Society Conference on Computer Vision and Pattern Recognition: 1. Piscataway: IEEE, 2005: 886-893.
［4］鲁珂, 丁正明, 赵继东, 等. 一种基于相关反馈的视频人脸算法［J］. 西安电子科技大学学报, 2012, 39(4): 154-160.
Lu Ke, Ding Zhengming, Zhao Jidong, et al. Novel Face Recognition Relevance Feedback Algorithm for Video ［J］. Journal of Xidian University, 2012, 39(4): 154-160.
［5］杨曦, 李洁, 韩冰, 等. 一种分层小波模型下的极光图像分类算法［J］. 西安电子科技大学学报, 2013, 40(2): 18-24.
Yang Xi, Li Jie, Han Bing, et al. Wavelet Hierarchical Model for Aurora Images Classification ［J］. Journal of Xidian University, 2013, 40(2): 18-24.
［6］李远征, 卢朝阳, 李静. 一种基于多特征融合的视频目标跟踪方法［J］. 西安电子科技大学学报, 2012, 39(4): 1-6.
Li Yuanzheng, Lu Zhaoyang, Li Jing. Rubust Video Object Tracking Algorithm Based on Multi-feature Fusion ［J］. Journal of Xidian University, 2012, 39(4): 1-6.
［7］ Walk S, Majer N, Schindler K, et al. New Features and Insights for Pedestrian Detection ［C］//2010 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2010: 1030-1037.
［8］ Park K Y, Hwang S Y. An Improved Haar-like Feature for Efficient Object Detection ［J］. Pattern Recognition Letters, 2014, 42: 148-153.
［9］ Wang X, Yang M, Zhu S, et al. Regionlets for Generic Object Detection ［C］//IEEE International Conference on Computer Vision. Piscataway: IEEE, 2013: 17-24.
［10］ Paisitkriangkrai S, Shen C. Efficient Pedestrian Detection by Directly Optimize the Partial Area under the ROC Curve ［C］//IEEE International Conference on Computer Vision. Piscataway: IEEE, 2013: 1057-1064.
［11］杜喆, 刘三阳. 最小二乘支持向量机变型算法研究［J］. 西安电子科技大学学报, 2009, 36(2): 331-337.
Du Zhe, Liu Sanyang. Research on Variations of Least Square Support Vector Machine ［J］. Journal of Xidian University, 2009, 36(2): 331-337.
［12］ Jones M, Snow D. Pedestrian Detection Using Boosted Features over Many Frames ［C］//19th International Conference on Pattern Recognition. Piscataway: IEEE, 2008: 1-4.
［13］ Park D, Zitnick C L, Ramanan D, et al. Exploring Weak Stabilization for Motion Feature Extraction ［C］//IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2013: 2882-2889.
［14］ Enzweiler M, Eigenstetter A. Multi-cue Pedestrian Classification with Partial Occlusion Handling ［C］//IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2010: 990-997.
［15］ Dollar P, Wojek C, Schiele B, et al. Pedestrian Detection: a Benchmark ［C］//IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2009: 304-311.
［16］ CBCL at MIT. MIT CBCL Car Database ＃1 ［DB/OL］. ［2014-02-11］. http://cbcl.mit.edu/software-datasets/CarData.html.
［17］ Carbonetto P, Dorko G. INRIA Car Data Set ［DB/OL］. ［2014-02-11］. http://lear.inrialpes.fr/data.
［18］ Caltech. Caltech Car Database ［DB/OL］. ［2014-02-11］. http://www.vision.caltech.edu/html-files/archive.html.
［19］ Ali S, Shah M. A Lagrangian Particle Dynamics Approach for Crowd Flow Segmentation and Stability Analysis ［C］//IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2007: 1-6.
［20］ CAVIAR Project. CAVIAR Test Case Scenarios ［DB/OL］. ［2014-02-11］ http://homepages.inf.ed.ac.uk/rbf/CAVIAR/.

[1]	HAN Yongsai,MA Shiping,HE Linyuan,LI Chenghao,ZHU Mingming,ZHANG Fei. Detection of the object in the fast remote sensing airport area on the improved YOLOv3 [J]. Journal of Xidian University, 2021, 48(5): 156-166.
[2]	DONG Ruchan,JIAO Licheng,ZHAO Jin,SHEN Weiyan. Application of the deep fusion mechanism in object detection of remote sensing images [J]. Journal of Xidian University, 2021, 48(5): 128-138.
[3]	MAO Zhaoyong,WANG Yichen,WANG Xin,SHEN Junge. Vehicle video surveillance and analysis system for the expressway [J]. Journal of Xidian University, 2021, 48(5): 178-189.
[4]	WANG Yudong,GUO Jichang,WANG Tianbao. Algorithm for foggy-image pedestrian and vehicle detection [J]. Journal of Xidian University, 2020, 47(4): 70-77.
[5]	YU Zhichao,ZHANG Ruihong. Improved Siamese network based object tracking combined with the deep contour feature [J]. Journal of Xidian University, 2020, 47(3): 40-49.
[6]	WANG Haijun,ZHANG Shengyan. Robust object tracking via adaptive weight convolutional features [J]. Journal of Xidian University, 2019, 46(1): 117-123.
[7]	HE Xiaochuan;XU Luping;FENG Dongzhu;YU Hang. HLBP model method with color and location information about moving objects detection [J]. J4, 2015, 42(4): 27-32+158.

Directed AdaBoost weighting classifier based on the scene motion pattern for object detection

PDF (PC)

Like

Knowledge

Cited

Abstract

Cite this article

share this article

References

Related Articles 7

Metrics

Comments

Recommended 0