融合历史轨迹的智能汽车城市复杂环境多目标检测与跟踪算法

隗寒冰 1; 陈尧 1; 贾志杰 1; 赖锋 2

doi:10.7652/xjtuxb201810018

您当前的位置：

首页 >

文章列表页 >

融合历史轨迹的智能汽车城市复杂环境多目标检测与跟踪算法

更新时间：2025-07-09

- 融合历史轨迹的智能汽车城市复杂环境多目标检测与跟踪算法
- A Multi-Target Detection and Tracking Algorithm Incorporating Historical Trajectories for Intelligent Vehicles in Urban Complicated Conditions
- 西安交通大学学报 2018年52卷第10期页码：132-140
- 作者机构：
  
  重庆交通大学车辆与汽车工程学院,重庆,400074
- 作者简介：
- 基金信息：
  
  : 2018-01-17。作者简介: 隗寒冰(1979-),男,副教授。基金项目: 国家自然科学基金资助项目(51305472);重庆市自然科学基金资助项目(cstc2014jcyjA6005)
- DOI：10.7652/xjtuxb201810018
  中图分类号： TP273
- 网络首发：2018-10-10，
  
  纸质出版：2018
- 稿件说明：
移动端阅览
隗寒冰 1, 陈尧 1, 贾志杰 1, 等. 融合历史轨迹的智能汽车城市复杂环境多目标检测与跟踪算法[J]. 西安交通大学学报, 2018,52(10):132-140.

A Multi-Target Detection and Tracking Algorithm Incorporating Historical Trajectories for Intelligent Vehicles in Urban Complicated Conditions[J]. 2018, 52(10): 132-140.
隗寒冰 1, 陈尧 1, 贾志杰 1, 等. 融合历史轨迹的智能汽车城市复杂环境多目标检测与跟踪算法[J]. 西安交通大学学报, 2018,52(10):132-140. DOI： 10.7652/xjtuxb201810018.

A Multi-Target Detection and Tracking Algorithm Incorporating Historical Trajectories for Intelligent Vehicles in Urban Complicated Conditions[J]. 2018, 52(10): 132-140. DOI： 10.7652/xjtuxb201810018.

摘要

针对现有智能汽车环境感知算法多根据特定类型目标设计

在处理目标遮挡、光照突变等城市复杂场景时识别准确率较低的问题

提出一种基于网状分类器与融合历史轨迹的多目标检测与跟踪算法。该算法考虑各目标之间的遮挡关系

利用具有目标融合功能的网状分类器对多尺度滑动窗获取的待检窗口进行多目标检测; 历史检测结果基于目标特征关联通过计算目标长短轨迹和历史轨迹可靠性验证生成历史轨迹库

该轨迹库用于预测或融合新的检测结果; 利用该检测跟踪结果更新网状分类器中的标准差分类器、最近邻分类器和历史轨迹信息

直至完成多目标长时跟踪。实验结果表明

本文算法在目标遮挡、光照变化和阴雨天气的复杂城市环境下均可实现多目标长时间检测跟踪

与KITTI数据集样本相比

平均准确率在77.17%～81.32%之间

单帧图像平均耗时0.05 s

具有较好的实时应用前景。

Abstract

A new type of multi-target detection and tracking algorithm based on net classifiers and historical trajectories is proposed to focus the problem that most existing popular environmental perception algorithms for intelligent vehicles are designed for specific type of targets and they have been proved to be low recognition accuracy in complicated urban conditions where occlusion of different targets and abrupt light change are frequent. Images are scanned from a multi-scale sliding window and then fused by a fusion model according to occlusion relations among pedestrians

vehicles and traffic signs. Historical detection results are obtained based on correlation of target features through short trajectory generation

long trajectory generation and reliability verification of trajectories

and are used to generate a library of historical trajectories

which is used to predict and to fuse detection results in the next step. Then

the standard deviation classifier

the nearest neighbor classifier and historical trajectories are updated by new detection and tracking results. Multi-target long-time tracking in complicated conditions is realized in this way. Field experiment shows that the proposed algorithm exhibits excellent performance of multi-target long-time tracking in complicated urban conditions such as rainy

shade

luminance changes. The average recognition rates for KITTI database samples is up to 77.17%～81.32% and calculation time of single frame picture is only 0.05 s. These results show a promising algorithm for real-time application.

关键词

Keywords

references

GAVRILA D. Pedestrian detection from a moving vehicle [C]∥Proceedings of the European Conference on Computer Vision. Berlin, Germany: Springer, 2000: 37-49.

GAVRILA D M, GIEBEL J. Shape-based pedestrian detection and tracking [C]∥Proceedings of the Intelligent Vehicle Symposium. Piscataway, NJ, USA: IEEE, 2002: 8-14.

SRINIVASA N. Vision-based vehicle detection and tracking method for forward collision warning in automobiles [C]∥Proceedings of the Intelligent Vehicle Symposium. Piscataway, NJ, USA: IEEE, 2002: 626-631.

BERTOZZI M, BROGGI A, FASCIOLI A, et al. Stereo vision-based vehicle detection [C]∥Proceedings of the Intelligent Vehicles Symposium. Piscataway, NJ, USA: IEEE, 2000: 39-44.

BROGGI A, CERRI P, ANTOELLO P C. Multi-resolution vehicle detection using artificial vision [C]∥Proceedings of the Intelligent Vehicles Symposium. Piscataway, NJ, USA: IEEE, 2004: 310-314.

ESTABLE S, SCHICK J, STEIN F, et al. A real-time traffic sign recognition system [C]∥Proceedings of the Intelligent Vehicles Symposium. Piscataway, NJ, USA, IEEE, 1994: 213-218.

BERTOZZI M, BROGGI A, CASTELLUCCIO S. A real-time oriented system for vehicle detection [J]. Journal of Systems Architecture, 1997, 43(1): 317-325.

OUYANG W, WANG X. Joint deep learning for pedestrian detection [C]∥Proceedings of the International Conference on Computer Vision. Piscataway, NJ, USA: IEEE, 2013: 2056-2063.

BETKE M, HARITAOGLU E, DAVIS L S. Multiple vehicle detection and tracking in hard real-time [C]∥Proceedings of the Intelligent Vehicles Symposium. Piscataway, NJ, USA: IEEE, 1996: 351-356.

PAPAGEORGIOU C P, OREN M, POGGIO T. A general framework for object detection [C]∥Proceedings of the International Conference on Computer Vision. Piscataway, NJ, USA: IEEE, 1998: 555-562.

STALLKAMP J, SCHLIPSING M, SALMEN J, et al. Man vs. computer: benchmarking machine learning algorithms for traffic sign recognition [J]. Neural Networks the Official Journal of the International Neural Network Society, 2012, 32(2): 323-332.

GIRSHICK R, DONAHUE J, DARRELL T, et al. Rich feature hierarchies for accurate object detection and semantic segmentation [C]∥Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Piscataway, NJ, USA: IEEE, 2014: 580-587.

GIRSHICK R. Fast R-CNN [C]∥Proceedings of the International Conference on Computer Vision. Piscataway, NJ, USA: IEEE, 2015: 1440-1448.

REN Shaoqing, HE Kaiming, ROSS G, et al. Faster R-CNN: towards real-time object detection with region proposal networks [J]. IEEE Transactions on Pattern Analysis Machine Intelligence, 2015, 39(6): 1137-1149.

REDMON J, DIVVALA S, GIRSHICK R, et al. You only look once: unified, real-time object detection [C]∥Proceedings of the Computer Vision and Pattern Recognition. Berlin, Germany: Springer, 2015: 779-788.

REDMON J, FARHADI A. YOLO9000: better, faster, stronger [C]∥Proceedings of the Computer Vision and Pattern Recognition. Berlin, Germany: Springer, 2017: 21-25.

LIU W, ANGUELOV D, ERHAN D, et al. SSD: single shot multibox detector [C]∥Proceedings of the European Conference on Computer Vision. Berlin, Germany: Springer, 2016: 21-37.

JONATHAN L, EVAN S, TREVOR D. Fully convolutional networks for semantic segmentation [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 4(39): 640-651.

PASZKE A, CHAURASIA A, KIM S, et al. ENet: a deep neural network architecture for real-time semantic segmentation [C]∥Proceedings of the Computer Vision and Pattern Recognition. Berlin, Germany: Springer, 2017: 21-25.

ZHAO Hengshuang, SHI Jianping, QI Xiaojuan, et al. Pyramid scene parsing network [C]∥Proceedings of the Computer Vision and Pattern Recognition. Berlin, Germany: Springer, 2017: 21-25.

ZHAO Hengshuang, QI Xiaojuan, SHEN Xiaoyong, et al. ICNet for real-time semantic segmentation on high-resolution images [C]∥Proceedings of the Computer Vision and Pattern Recognition. Berlin, Germany: Springer, 2017: 21-25.

杨峰, 王永齐, 梁彦, 等. 基于概率假设密度滤波方法的多目标跟踪技术综述 [J]. 自动化学报, 2013, 39(11): 1944-1956.

YANG Feng, WANG Yongqi, LIANG Yan, et al. A survey of PHD filter based multi-target tracking [J]. ACTA Automatic Sinica, 2013, 39(11): 1944-1956.

OKUMA K, TALEGHANI A, FREITAS N D, et al. A boosted particle filter: multitarget detection and tracking [C]∥Proceedings of the European Conference on Computer Vision. Berlin, Germany: Springer, 2004: 28-39.

ANDRIYENKO A, SCHINDLER K. Globally optimal multi-target tracking on a hexagonal lattice [C]∥Proceedings of the European Conference on Computer Vision. Berlin, Germany: Springer, 2010: 466-479.

MALLICK M, KRANT J, SHALON J. Multi-sensor multi-target tracking with out-of-sequence measurements [C]∥Proceedings of the 6th International Conference of Information Fusion. Piscataway, NJ, USA: IEEE, 2003: 672-679.

HOWARD A, PADGETT C, LIEBE C C. A multi-stage neural network for automatic target detection [C]∥Proceedings of the IEEE World Congress on Computational Intelligence. Piscataway, NJ, USA: IEEE, 1998: 4-9.

GRINBERG M, OHR F, BEYERER J. Feature-based probabilistic data association(FBPDA)for visual multi-target detection and tracking under occlusions and split and merge effects [C]∥Proceedings of the International Conference on Intelligent Transportation Systems. Piscataway, NJ, USA: IEEE, 2009: 1-8.

KALAL Z, MIKOLAJCZYK K, MATAS J. Tracking-learning-detection [J]. IEEE Transactions on Pattern Analysis Machine Intelligence, 2011, 34(7): 1409-1422.

HU Weiming, HU We, MAYBANK S. AdaBoost-based algorithm for network intrusion detection [J]. IEEE Transactions on Systems Man and Cybernetics: Part B Cybernetics, 2008, 38(2): 577-583.

刘毅,秦贵和,赵睿,等.车载控制器局域网络安全协议.2018,52(5):94-100.[doi:10.7652/xjtuxb201805014]

邓涛,罗俊林,韩海硕,等.混合动力汽车工况识别自适应能量管理策略.2018,52(1):77-83.[doi:10.7652/xjtuxb201801 012]

张亮修,王宇,吴光强,等.汽车阻尼可调半主动悬架混杂模型预测控制.2017,51(11):56-164[doi:10.7652/xjtuxb2017 11022]

李超超,向建华,王慧敏.汽车保险杠系统吸能盒结构参数对低速碰撞下吸能特性的影响.2017,51(10):77-81.[doi:10. 7652/xjtuxb201710013]

章军辉,李庆,陈大鹏,等.基于BP神经网络的纵向避撞安全辅助算法.2017,51(7):140-147.[doi:10.7652/xjtuxb2017 07020]

严珍,王斌,徐俊,等.双参数组合优化的复合电源模式切换控制策略.2016,50(11):129-135.[doi:10.7652/xjtuxb2016 11020]

卢礼华,陆建辉,刘志峰,等.汽车坐盆安全气囊对假人伤害的仿真及优化.2016,50(9):146-152.[doi:10.7652/xjtuxb 201609023]

许广灿,徐俊,李士盈.电动汽车振动能量回收悬架及其特性优化.2016,50(8):90-95.[doi:10.7652/xjtuxb201608015]

卢礼华,刘志峰,陆建辉.帘式安全气囊有限元建模及侧碰撞系统仿真.2016,50(7):104-109.[doi:10.7652/xjtuxb 201607016]

王斌,徐俊,曹秉刚,等.电动汽车的多模式复合电源能量管理自适应优化.2015,49(12):130-136.[doi:10.7652/xjtuxb 201512021]

邓涛,林椿松,李亚南,等.采用NSGA-II算法的混合动力能量管理控制多目标优化方法[J].西安交通大学学报,2015,49(10):143-150.[doi:10.7652/xjtuxb201510023]

王斌,徐俊,曹秉刚,等.采用模拟退火算法的电动汽车复合电源能量管理系统优化.2009,43(6):10-14.[doi:10.7652/xjtuxb201508015]

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

智能汽车线控转向系统鲁棒保性能容错控制

超临界二氧化碳向心透平轮背间隙内风阻损失及流动特性研究

张角凹坑气膜孔对双层壁气膜冷却特性的影响

混合电解槽阵列协同的风光耦合制氢系统双层多目标优化

水蒸气掺混对氨裂解气旋流燃烧与排放特性的影响研究