基于 BING-casDPM 的快速行人检测算法

doi:10.12066/j.issn.1007-2861.1988

上海大学学报(自然科学版) ›› 2019, Vol. 25 ›› Issue (5): 712-721.doi: 10.12066/j.issn.1007-2861.1988

基于 BING-casDPM 的快速行人检测算法

胡燕伟, 徐美华(), 郭爱英

上海大学机电工程与自动化学院, 上海 200444

收稿日期:2017-08-17 出版日期:2019-10-30 发布日期:2019-10-31
通讯作者: 徐美华 E-mail:mhxu@shu.edu.cn
基金资助:
国家自然科学基金资助项目(61376028);国家自然科学基金资助项目(61674100)

Fast pedestrian detection algorithm based on BING-casDPM

Yanwei HU, Meihua XU(), Aiying GUO

School of Mechatronic Engineering and Automation,Shanghai University, Shanghai 200444, China

Received:2017-08-17 Online:2019-10-30 Published:2019-10-31
Contact: Meihua XU E-mail:mhxu@shu.edu.cn

摘要/Abstract

摘要：

行人检测是计算机视觉技术中一个热门的研究热点, 在汽车辅助驾驶和视频监控等方面具有重要作用. 由于传统的可变形部件模型(deformable part model, DPM)采用滑动窗口检测方式, 在背景区域花费大量检测时间会导致检测速度降低, 因此提出了一种基于 BING-casDPM 的快速行人检测算法. 首先基于二进制化梯度范数特征(binarized normed gradient, BING)训练一个二级支持向量机(support vector machine, SVM)分类器, 通过该分类器快速标定出所测图像中包含各类物体的候选区域; 然后根据候选区域窗口的特点进一步提取待检测框; 最后将待检测框作为输入, 使用级联 DPM(cascade DPM, casDPM)模型进行精确检测, 并将结果返回至原图. 实验结果表明, 该算法在基本不降低检测率的情况下, 其检测速度比经典 DPM 模型检测速度提高了约 16 倍, 比 casDPM 模型提高了约40%.

关键词: 行人检测, 二进制化梯度范数, 待检测框, 星型级联可变形部件模型

Abstract:

Pedestrian detection is a hot research field in computer vision technology, and it has important applications in automobile assisted driving and video surveillance. In view of the fact that traditional deformable part model (DPM) uses a sliding window for pedestrian detection and is time-consuming in the background area, a fast pedestrian detection algorithm based on BING-casDPM is proposed. Firstly, a cascaded support vector machine (SVM) classifier is trained based on the binarized normed gradients (BING) feature. The candidate areas containing all kinds of objects as seen on the test image are quickly calibrated through the classifier. Then, the detected box is extracted according to the characteristics of candidate windows, and finally pedestrians are accurately detected from the detected box using casDPM model with the result being returned to the original image. The experiment results show that the algorithm proposed in this paper is about 16 times faster than the classical DPM model, and about 40% faster than the casDPM model in terms of the speed of detection when detection rate remains stable.

Key words: pedestrian detection, binarized normed gradient(BING), detected box, star-cascade deformable part model (casDPM)

中图分类号:

TP312

胡燕伟, 徐美华, 郭爱英. 基于 BING-casDPM 的快速行人检测算法[J]. 上海大学学报(自然科学版), 2019, 25(5): 712-721.

Yanwei HU, Meihua XU, Aiying GUO. Fast pedestrian detection algorithm based on BING-casDPM[J]. Journal of Shanghai University（Natural Science Edition）, 2019, 25(5): 712-721.

图/表 9

图1

图2

图3

图4

图5

图6

表1

图7

图8

参考文献 19

[1]	许言午, 曹先彬, 乔红 . 行人检测系统研究新进展及关键技术展望[J]. 电子学报, 2008,36(5):368-376.
[2]	Geronimo D, Lopez A, Sappa A , et al. Survey of pedestrian detection for advanced driver assistance systems[J]. IEEE Trans on Pattern Analysis and Machine Intelligence, 2010,32(7):1239-1258.
[3]	Aggarwal J, Ryoo M . Human activity analysis: a review[J]. ACM Computing Surveys, 2011,43(3):1-47.
[4]	杨恒, 王超, 姜文涛 , 等. 基于随机背景建模的目标检测算法[J]. 应用光学, 2015,36(6):880-887.
[5]	胡强 . 行人检测技术研究与实现[D]. 辽宁锦州: 辽宁工业大学, 2016: 9-10.
[6]	Viola P, Jones M . Rapid object detection using a boosted cascade of simple features[C]// Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. 2001.
[7]	Viola P, Jones M J . Robust real-time face detection[J]. International Journal of Computer Vision, 2004,57(2):137-154.
[8]	Dalal N, Triggs B . Histograms of oriented gradients for human detection[C]// 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05). 2005: 886-893.
[9]	Zhu Q, Yeh M C, Cheng K T , et al. Fast human detection using a cascade of histograms of oriented gradients[C]// Proc IEEE CVPR. 2006: 1491-1498.
[10]	Wojek C, Schiele B . A performance evaluation of single and multi-feature peopledetection[C]// Proc DAGM. 2008.
[11]	Felzenszwalb P, McAllester D, Ramanan D . A discriminatively trained, multiscale, deformable part model[C]// IEEE Conference on Computer Vision and Pattern Recognition. 2008: 1-8.
[12]	Felzenszwalb P, Girshick R, McAllester D , et al. Cascade object detection with deformable part models[C]// Computer Vision and Pattern Recognition. 2010: 2241-2248.
[13]	Dubout C, Fleuret F . Exact acceleration of linear object detectors[M]. Berlin: Springer Heidelberg, 2012: 301-311.
[14]	Cheng M M, Zhang Z M, Lin W Y , et al. BING: binarized normed gradients for objectness estimation at 300 fps [C]// IEEE Conference on Computer Vision and Pattern Recognition. 2014: 3286-3293.
[15]	Alexe B, Deselaers T, Ferrari V . Measuring the objectness of image windows[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2012,34(11):2189-2202.
[16]	Hare S, Saffari A, Torr P H S . Efficient online structured output learning for keypoint-based object tracking[C]// IEEE Conference on Computer Vision and Pattern Recognition. 2012: 1894-1901.
[17]	Zheng S, Sturgess P, Torr P H S . Approximate structured output learning for constrained local models with application to real-time facial feature detection and tracking on low-power devices[C]// IEEE International Conference and Workshops on Automatic Face and Gesture Recognition. 2013: 1-8.
[18]	Yan J J, Lei Z, Wen L Y , et al. The fastest deformable part model for object detec-tion[C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2014: 2497-2504.
[19]	韦皓瀚, 曹国, 金挺 , 等. 改进星型级联可形变部件模型的行人检测[J]. 中国图象图形学报, 2017,22(2):170-178.

基于 BING-casDPM 的快速行人检测算法

Fast pedestrian detection algorithm based on BING-casDPM

RichHTML

PDF

可视化

摘要/Abstract

引用本文

使用本文

图/表 9

参考文献 19

相关文章 1

编辑推荐

Metrics

本文评价