LIU Mingwen,JIANG Tao,YUAN Jianying*,et al.Detection of Moving Objects in Smart Cars based on Binocular Sparse Scene Flow[J].Journal of Chengdu University of Information Technology,2023,38(04):381-386.[doi:10.16836/j.cnki.jcuit.2023.04.001]
基于双目稀疏场景流的智能车运动目标检测
- Title:
- Detection of Moving Objects in Smart Cars based on Binocular Sparse Scene Flow
- 文章编号:
- 2096-1618(2023)04-0381-06
- 分类号:
- TP391.4
- 文献标志码:
- A
- 摘要:
- 为提高无人驾驶汽车视觉运动目标检测精度, 提出一种基于深度学习与稀疏场景流结合的运动目标检测方法。首先使用深度学习网络SOLO V2分割交通场景, 提取行人、车辆等潜在运动目标, 缩小场景内运动目标搜索范围。其次, 利用背景中特征匹配点估计相机自运动参数, 在此基础上将潜在运动区域前后两帧特征点坐标映射到同一坐标系下, 进而计算出仅由运动目标产生的稀疏场景流。最后, 根据每个目标场景流估计误差的不同, 计算每个目标场景流估计的不确定度, 然后使用独立自适应阈值用于运动状态判断。使用KITTI数据集进行测试, 实验结果表明:所提算法能明显提升运动目标检测精度, 算法精度和召回率在两组数据集分别为92.3%、94.4%和87.4%、95.1%。
- Abstract:
- In order to improve the accuracy of visual moving object detection of unmanned vehicles, this paper proposes a moving object detection method based on deep learning combined with sparse scene flow.First, the deep learning network SOLO V2 is used to segment the traffic scene, extract potential moving targets such as pedestrians and vehicles, and narrow the search range of moving targets in the scene. Secondly, the camera self-motion parameters are calculated by using the feature matching points in the background. On this basis, the feature points of the potential motion area are mapped to a unified coordinate system.This feature point is at two moments before and after, and then the sparse scene flow generated only by its own motion is calculated. Finally, according to the difference of the estimation error of each target scene flow, the uncertainty of each target scene flow estimation is calculated and an independent adaptive threshold is set for each target for motion state judgment. The KITTI data set is used to test. The experimental results show that the proposed algorithm can significantly improve the accuracy of moving target detection.The accuracy and recall of the algorithm are 92.3%, 94.4% and 87.4%, 95.1% respectively in the two sets of data.
参考文献/References:
[1] Radke R J, Andra S, Al-Kofahi O, et al.Image change detection algorithms:a systematic survey[J].IEEE transactions on image processing, 2005, 14(3):294-307.
[2] 何楠楠, 杜军平.智能视频监控中高效运动目标检测方法研究[J].北京工商大学学报(自然科学版), 2009, 27(4):34-37.
[3] 巨志勇, 彭彦妮.基于自动背景提取及Lab色彩空间的运动目标检测[J].软件导刊, 2018, 17(5):183-186.
[4] 马波, 张田文.基于AOS的运动目标检测算法[J].计算机辅助设计与图形学学报, 2003, 15(10):1213-1217.
[5] 王春兰.智能视频监控系统中运动目标检测方法综述[J].自动化与仪器仪表, 2017(3):1-3.
[6] 王恩旺, 王恩达.改进的帧差法在空间运动目标检测中的应用[J].天文研究与技术, 2016, 13(3):333-339.
[7] 金玥佟, 杨耀权, 杜永昂.电力监控场景下基于光流特征点的目标跟踪算法[J].电力科学与工程, 2020, 36(5):40-47.
[8] Esparza D, Flores G.The STDyn-SLAM:A Stereo Vision and Semantic Segmentation Approach for VSLAM in Dynamic Outdoor Environments[J].IEEE Access, 2022, 10:18201-18209.
[9] Liu G, Zeng W, Feng B, et al.DMS-SLAM:A general visual SLAM system for dynamic scenes with multiple sensors[J].Sensors, 2019, 19(17):3714.
[10] Zhou D, Frémont V, Quost B, et al.Moving object detection and segmentation in urban environments from a moving platform[J].Image and Vision Computing, 2017, 68:76-87.
[11] Lin S F, Huang S H.Moving object detection from a moving stereo camera via depth information and visual odometry[C].2018 IEEE International Conference on Applied System Invention(ICASI).IEEE, 2018:437-440.
[12] Chen L, Fan L, Xie G, et al.Moving-object detection from consecutive stereo pairs using slanted plane smoothing[J].IEEE Transactions on Intelligent Transportation Systems, 2017, 18(11):3093-3102.
[13] Cui L, Ma C.SOF-SLAM:A semantic visual SLAM for dynamic environments[J].IEEE access, 2019, 7:166528-166539.
[14] Ballester I, Fontán A, Civera J, et al.DOT:Dynamic object tracking for visual SLAM[C].2021 IEEE International Conference on Robotics and Automation(ICRA).IEEE, 2021:11705-11711.
[15] Kaneko M, Iwami K, Ogawa T, et al.Mask-slam:Robust feature-based monocular slam by masking using semantic segmentation[C].Proceedings of the IEEE conference on computer vision and pattern recognition workshops.2018:258-266.
[16] Huang J, Yang S, Mu T J, et al.Clustervo:Clustering moving instances and estimating visual odometry for self and surroundings[C].Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2020:2168-2177.
[17] Wang X, Zhang R, Kong T, et al.Solov2:Dynamic and fast instance segmentation[J].Advances in Neural information processing systems, 2020, 33:17721-17732.
备注/Memo
收稿日期:2022-09-09
基金项目:国家自然科学基金资助项目(62103064); 四川省自然科学基金资助项目(22NSFSC2317); 四川省科技计划资助资助(2021YFG0133、2021YFG0295、2021YFH0069、2021YFQ0057、2022YFS0565、2022YFN0020、2021YFG0308)
通信作者:袁建英.E-mail:yuanjy@cuit.edu.cn