采用人体树图与混合粒子群聚类的行人检测

孟晓燕; 段建民; 刘丹

doi:10.3788/OPE.20182607.1802

您当前的位置：

首页 >

文章列表页 >

采用人体树图与混合粒子群聚类的行人检测

信息科学 | 更新时间：2020-08-13

- 采用人体树图与混合粒子群聚类的行人检测
- Pedestrian detection based on tree-structured graphical model of the human body and hybrid particle swarm clustering
- 光学精密工程 2018年26卷第7期页码：1802-1812
- 作者机构：
  
  北京工业大学信息学部, 北京 100124
- 作者简介：
  
  [ "孟晓燕(1990-), 女, 山西晋中人, 博士研究生, 主要从事图像处理与模式识别, 智能车辆等方面的研究。E-mail:529108419@qq.com" ]
  [ "段建民(1959-)，男，北京人，博士，教授，主要从事车辆环境识别与自动驾驶技术，网络化测控系统与现场总线技术，嵌入式汽车电子控制技术等方面的研究。E-mail：jmduan@bjut.edu.cn" ]
- 基金信息：
  
  北京市属高等学校人才强教计划资助项目(038000543117004);北京市自然科学基金资助项目(JJ002790200802)
- DOI：10.3788/OPE.20182607.1802
  中图分类号： TP391
- 收稿日期：2017-11-20，
  
  录用日期：2018-1-23，
  
  纸质出版日期：2018-07-25
- 稿件说明：
移动端阅览
孟晓燕, 段建民, 刘丹. 采用人体树图与混合粒子群聚类的行人检测[J]. 光学精密工程, 2018,26(7):1802-1812.

Xiao-yan MENG, Jian-min DUAN, Dan LIU. Pedestrian detection based on tree-structured graphical model of the human body and hybrid particle swarm clustering[J]. Optics and precision engineering, 2018, 26(7): 1802-1812.
孟晓燕, 段建民, 刘丹. 采用人体树图与混合粒子群聚类的行人检测[J]. 光学精密工程, 2018,26(7):1802-1812. DOI： 10.3788/OPE.20182607.1802.

Xiao-yan MENG, Jian-min DUAN, Dan LIU. Pedestrian detection based on tree-structured graphical model of the human body and hybrid particle swarm clustering[J]. Optics and precision engineering, 2018, 26(7): 1802-1812. DOI： 10.3788/OPE.20182607.1802.

摘要

为提升辅助驾驶系统的可靠性及安全系数，实现更高精度的行人检测，基于人体树图模型提出了一种改进的离线训练、在线检测的行人检测方法。首先，定义人体部件间的共生关系，得到对应父子部件对，结合K-means算法对其位置关系进行聚类获得部件类型。为兼顾类内紧密性与类间分离性，采用MSE和DBI构建具有两阶段适应度函数的混合粒子群聚类算法，在有效估计各部件最优聚类中心数量的同时，消除随机初始化对聚类准确率造成的影响。其次，将优化聚类得到的部件类型作为隐藏变量，通过求解隐结构SVM获取改进后的人体检测模型。最后，通过动态规划算法求解状态转移方程，在多个尺度上有效估计人体部件位置及检测包围盒，并结合非极大值抑制思想得到最终的行人检测结果。实验结果表明，所提方法在检测性能上明显优于5种行人检测方法，并且相比于原始Pose-original方法，在INRIA和ETH数据集上的丢失率分别下降了8.14%和5.05%。实验证明该方法检测性能良好且具有较高的准确性和鲁棒性。

Abstract

In order to improve the reliability and safety factor of driver assistance systems

and achieve pedestrian detection with a higher precision

an improved pedestrian detection method based on a tree-structured graphical model of the human body is proposed

and it consists of an offline training part and an online detection part. First

the corresponding parent-child parts are obtained by defining the symbiotic relationship between human parts

and then the K-means algorithm is applied to the location relationship between part pairs to acquire part types via clustering. For the purpose of taking both intra-class tightness and inter-class differences into account

a hybrid particle swarm optimization algorithm is built with a two-phase fitness function via introducing MSE and DBI. It is not only effective in estimating the number of optimal cluster centers

but also in eliminating the effect of random initialization on the clustering accuracy. Then

the part type obtained using the optimized clustering method is considered as the latent variable. The pedestrian detection model is obtained through solving the latent structural SVM problem. Finally

we estimate the position of human parts and the detection bounding box on multiple scales based on solving the state equation via a dynamic programming algorithm

and obtain the final pedestrian detection result through incorporating the idea of non-maximum suppression. Experimental results indicate that the performance of the proposed algorithm is superior to those of five other pedestrian detection algorithms. In particular

on the INRIA and ETH databases

the loss rate of the proposed algorithm decreased by 8.14% and 5.05%

respectively

compared with that of the pose-original method. Experimental results show that the proposed algorithm has good performance and high accuracy and robustness.

关键词

Keywords

references

VIOLA P, JONES M J. Robust real-time face detection[J]. International Journal of Computer Vision, 2004, 57(2):137-154.

DALAL N, TRIGGS B. Histograms of oriented gradients for human detection[C]. 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops , San Diego, USA, CVPR, 2005: 886-893.

WANG X, HAN T X, YAN S. An HOG-LBP human detector with partial occlusion handling[C]. 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops , San Francisco, USA, CVPR, 2010: 32-39.

FELZENSZWALB P F, MCALLESTER D, RAMANAN D. A discriminatively trained, multiscale, deformable part model[C]. 2008 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops , Anchorage, USA, CVPR, 2008: 1-8.

FELZENSZWALB P F, GIRSHICK R B, MCALLESTER D, et al.. Object detection with discriminatively trained part-based models[J]. IEEE Transactions on Pattern Analysis & Machine Intelligence, 2010, 32(9):1627.

PEDERSOLI M, VEDALDI A, GONZALEZ J, et al.. A coarse-to-fine approach for fast deformable object detection[J]. Pattern Recognition, 2015, 48(5):1844-1853.

OUYANG W, ZHOU H, LI H, et al. Jointly learning deep features, deformable parts, occlusion and classification for pedestrian detection[J]. IEEE Transactions on Pattern Analysis & Machine Intelligence, 2017, PP(99):1-1.

OUYANG W, ZENG X, WANG X, et al.. DeepID-Net:object detection with deformable part based convolutional neural networks[J]. IEEE Transactions on Pattern Analysis & Machine Intelligence, 2017, 39(7):1320-1334.

YANG Y, RAMANAN D. Articulated human detection with flexible mixtures of parts[J]. IEEE Transactions on Pattern Analysis & Machine Intelligence, 2013, 35(12):2878.

潘楠, 孙亚军, 刘益.线缆盗割痕迹的激光检测特征高效匹配[J].光学精密工程, 2017, 25(10s):183-190.

PAN N, SUN Y J, LIU Y. Efficient matching technique for laser detection features of cable cutting traces[J]. Opt. Precision Eng., 2017, 25(10s):183-190. (in Chinese)

WU J, LIU H, XIONG H, et al.. K-Means based consensus clustering:a unified view[J]. IEEE Transactions on Knowledge & Data Engineering, 2015, 27(1):155-169.

CELEBI M E, KINGRAVI H A. A comparative study of efficient initialization methods for the k-means clustering algorithm[J]. Expert Systems with Applications, 2012, 40(1):200-210.

李庆武, 席淑雅, 王恬, 等.结合位姿约束与轨迹寻优的人体姿态估计[J].光学精密工程, 2017, 25(4):1060-1069.

LI Q W, XI SH Y, WANG T, et al.. Human pose estimation based on configuration constraints and trajectory optimization[J]. Opt. Precision Eng., 2017, 25(4):1060-1069. (in Chinese)

黄建余, 谭继波, 吴文堂, 等. GEO碎片天基观测图像速度估计与动态规划检测[J].光学精密工程, 2017, 25(2):537-546.

HUANG J Y, TAN J B, WU W T, et al.. Velocity estimation of GEO debris space-based observation image and dynamic programming detection[J]. Opt. Precision Eng., 2017, 25(2):537-546. (in Chinese)

ESS A, LEIBE B, SCHINDLER K, et al. . A mobile vision system for robust multi-person tracking[C] . 2008 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops , Anchorage, USA, CVPR, 2008: 1-8.

NIE B X, XIONG C, ZHU S C. Joint action recognition and pose estimation from video[C]. 2015 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops , Boston, USA, CVPR, 2015: 1293-1301.

RAMANAN D. Learning to Parse Images of Articulated Bodies[C]. Proc. Advances in Neural Information Processing System , Vancouver, Canada, NIPS, 2007: 1-8.

PIVIDORI M, STEGMAYER G, MILONE D H. Diversity control for improving the analysis of consensus clustering[J]. Information Sciences, 2016, s361-362(C):120-134.

FONG S, WONG R, VASILAKOS A V. Accelerated PSO swarm search feature selection for data stream mining big data[J]. IEEE Transactions on Services Computing, 2016, 9(1):33-45.

段海滨, 张祥银, 徐春芳.仿生智能计算[M].北京:科学出版社, 2011.

DUAN H B, ZHANG X Y, XU CH F. Bio-inspired Computing[M]. Beijing:Science Press, 2011. (in Chinese)

WANG X, HAN T X, YAN S. An HOG-LBP human detector with partial occlusion handling[C]. 2009 IEEE International Conference on Computer Vision , Kyoto, Japan, ICCV, 2009: 32-39.

LIU Y, ZENG L, HUANG Y. An efficient HOG-ALBP feature for pedestrian detection[J]. Signal Image & Video Processing, 2014, 8(1):125-134.

LIU Y, ZOU L, LI J, et al.. Segmentation by weighted aggregation and perceptual hash for pedestrian detection[J]. Journal of Visual Communication & Image Representation, 2016, 36(C):80-89.

ANGELOVA A, KRIZHEVSKY A, VANHOUCKE V. Pedestrian detection with a Large-Field-Of-View deep network[C]. 2015 IEEE International Conference on Robotics and Automation, Washington , USA, ICRA, 2015: 704-711.

浏览量

571

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

多分支无锚框网络密集行人检测算法

基于粒子群优化的宏观傅里叶叠层成像位置失配校准

自驱动关节臂坐标测量机轨迹优化

面向多元场景的轻量级行人检测

模态自适应权值学习机制下的多光谱行人检测网络