面向协作式自动泊车的场端单目视觉测距系统

摘要/Abstract

摘要： 在协作式自动泊车的实现过程中，较为关键的一点是停车场全局范围内相关车辆的识别与定位，因此本文提出一种应用于场端基于单目视觉的车辆识别与定位方法。首先，考虑基础设施停车场的特点，设计灵活性更好的以分布式架构为核心的感知系统架构，改进SSD网络以使检测模型更适于在边缘处理设备中部署运行；之后分析并构建用于场端的单目视觉测距数学模型；最终综合利用目标检测与视觉测距算法，完成目标车辆的识别与定位。为验证单目视觉测距算法在场端中应用的有效性，在真实的停车场环境中设计模拟实验，进行相应的测试，实验结果表明，视觉测距精度满足系统要求。

关键词: 协作式自动泊车, SSD算法, 目标检测, 单目测距, 车辆定位

Abstract: In the process of realizing collaborative automatic parking, the key point is to identify and locate the target vehicle in the global scope of the parking lot. Therefore, this paper proposes a vehicle identification and location method based on monocular vision that is suitable for the parking lot. Firstly, considering the characteristics of the parking lot, a distributed architecture is designed to ensure the flexibility of the perception system. An improved SSD network is proposed to make it run better in embedded devices, and then a monocular measurement model is established. Finally, the detection and ranging algorithm is used to realize the identification and location of vehicles. In order to verify the effectiveness of the monocular measurement algorithm, an experiment is designed and tested in a real parking lot. The experimental results show that the accuracy of the visual ranging meets the requirements of the system.

Key words: collaborative automatic parking, SSD algorithm, object detection, monocular ranging, vehicle positioning

张成龙, 张毅. 面向协作式自动泊车的场端单目视觉测距系统[J]. 计算机与现代化, 2021, 0(11): 112-117.

ZHANG Cheng-long, ZHANG Yi. Monocular Visual Distance Measurement System Used at Park for Collaborative Automatic Parking#br#[J]. Computer and Modernization, 2021, 0(11): 112-117.

参考文献

［1］ JANG C, KIM C, LEE S, et al. Re-plannable automated parking system with a standalone around view monitor for narrow parking lots［J］. IEEE Transactions on Intelligent Transportation Systems, 2020,21(2):777-790.
［2］ HE D F, HE W T, SONG X L. Efficient predictive cruise control of autonomous vehicles with improving ride comfort and safety［J］. Measurement & Control, 2020,53(2):18-28.
［3］《中国公路学报》编辑部. 中国汽车工程学术研究综述·2017［J］. 中国公路学报, 2017,30(6):1-197.
［4］ LEE B, WEI Y, GUO I Y. Automatic parking of self-driving car based on LiDAR［J］. The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 2017, XLII-2(W7):241-246.
［5］ ZHAO J X, XU H, LIU H C. Detection and tracking of pedestrians and vehicles using roadside LiDAR sensors［J］. Transportation Research Part C-Emerging Technologies, 2019,100:68-87.
［6］张微，华一丁，臧晨，等. 面向室内停车场的自主代客泊车关键技术研究［J］. 汽车电器, 2019(8):6-8.
［7］ HEIMBERGER M, HORGAN J, HUGHES C, et al. Computer vision in automated parking systems: Design, implementation and challenges［J］. Image and Vision Computing, 2017,68: 88-101.
［8］ SHIN H, CHAE J. A performance review of collision-free path planning algorithms［J］. Electronics, 2020,9(2). DOI: 10.3390/electronics9020316.
［9］ HE K M, GKIOXARI G, DOLLAR P, et al. Mask R-CNN［C］∥Proceedings of the 2017 IEEE International Conference on Computer Vision. 2017:2980-2988.〖HJ0.95mm〗
［10］REDMON J, FARHADI A. YOLO9000: Better, faster, stronger［C］∥Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition. 2017:6517-6525.
［11］LIU W, ANGUELOV D, ERHAN D, et al. SSD: Single shot multiBox detector［C］// 2016 European Conference on Computer Vision. 2016:21-37.
［12］周哲，徐晓滨，文成林，等. 冲突证据融合的优化方法［J］. 自动化学报, 2012,38(6):976-985.
［13］魏永超. 基于K-L距离的改进D-S证据合成方法［J］. 电讯技术, 2011,51(1):27-30.
［14］王志刚，赵海良，王星. 基于图像识别的模糊测距方法［J］. 重庆理工大学学报(自然科学), 2020,34(1):58-63.
［15］魏旭，陶冰洁. 基于2DPCA的特征融合方法及其应用［J］. 计算机工程与应用, 2008,44(5):70-72.
［16］HUANG L Q, CHEN Y N, FAN Z J, et al. Measuring the absolute distance of a front vehicle from an in-car camera based on monocular vision and instance segmentation［J］. Journal of Electronic Imaging, 2018,27(4). DOI: 10.1117/1.JEI.27.4.043019.
［17］余厚云，张为公. 基于单目视觉传感器的车距测量与误差分析［J］. 传感器与微系统， 2012,31(9):10-13.
［18］RAZA M, CHEN Z H, REHMAN S U, et al. Framework for estimating distance and dimension attributes of pedestrians in real-time environments using monocular camera［J］. Neurocomputing, 2018,275:533-545.
［19］刘昌辉，帅考，杨维荣. 嵌入式视觉的测距系统设计［J］. 武汉工程大学学报, 2015, 37(4):65-68.
［20］ZHOU H B, XU W C, CHEN J C, et al. Evolutionary V2X technologies toward the Internet of vehicles: Challenges and opportunities［J］. Proceedings of the IEEE, 2020,108(2):308-323.
［21］朱涛, 黎恒明, 唐新科，等. 面向栅格模型的室内环境地图构建方法［J］. 现代计算机(专业版), 2017(29):74-77.
［22］BREITENSTEIN M D, REICHLIN F, LEIBE B, et al. Robust tracking-by-detection using a detector confidence particle filter［C］// 2009 IEEE International Conference on Computer Vision. 2009:1515-1522.
［23］CHOLLET F. Xception: Deep learning with depthwise separable convolutions［C］// Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition. 2017:1800-1807.
［24］HOWARD A G, ZHU M L, CHEN B, et al. MobileNets：Efficient convolutional neural networks for mobile vision applications［J］. arXiv preprint arXiv: 1704.04861, 2017.
［25］STEIN G P, MANO O, SHASHUA A. Vision-based ACC with a single camera: Bounds on range and range rate accuracy［C］// 2003 IEEE Intelligent Vehicles Symposium. 2003:120-125.
［26］ADAMSHUK R, CARVALHO D, NEME J H Z, et al. On the applicability of inverse perspective mapping for the forward distance estimation based on the HSV colormap ［C］// 2017 IEEE International Conference on Industrial Technology. 2017:1036-1041.
［27］曹毓，冯莹，赵立双，等. 相机姿态安装误差对单目视觉定位精度的影响［J］. 传感器与微系统, 2012, 31(12):23-26.
［28］ZHANG Z Y. A flexible new technique for camera calibration［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2000,22(11):1330-1334.

[1]	刘云海1, 冯广1, 吴晓婷2, 杨群2. 复杂施工场景下的安全帽佩戴检测算法[J]. 计算机与现代化, 2024, 0(12): 66-71.
[2]	陈亮, 李诚, 易伟, 熊伟, 汪晓帆, 唐海东. 基于毫米波雷达与视觉融合的电力现场安全帽佩戴检测[J]. 计算机与现代化, 2024, 0(12): 100-107.
[3]	张宇1, 2, 黎靖1, 2, 马铭1, 2, 王众祥1, 2, 孙妍1, 2. YOLOLW:一个新的轻量级目标检测模型[J]. 计算机与现代化, 2024, 0(11): 91-98.
[4]	董玉玟. 基于改进YOLOv7-tiny的多尺度运动目标检测算法[J]. 计算机与现代化, 2024, 0(11): 99-105.
[5]	陈凯1, 李宜汀1, 2, 全华凤1 . 基于改进YOLOv8的河道废弃瓶检测方法[J]. 计算机与现代化, 2024, 0(11): 113-120.
[6]	魏学诚1, 江凌云1, 李研2, 何非2. 改进YOLOv5的路侧单目视角小目标检测算法[J]. 计算机与现代化, 2024, 0(10): 27-34.
[7]	史星宇1, 李强2, 庄莉3, 梁懿3, 王秋琳3, 陈锴3, 伍臣周3, 常胜1. 一种面向工业部署的目标检测模型蒸馏技术[J]. 计算机与现代化, 2024, 0(10): 93-99.
[8]	程萌, 李浩. 改进YOLOv5s的落叶树鸟巢检测方法[J]. 计算机与现代化, 2024, 0(08): 24-29.
[9]	庞梅, 汪珙, 詹泳, 黄哲法. 基于YOLOv5改进算法的海洋水下垃圾检测方法[J]. 计算机与现代化, 2024, 0(07): 120-126.
[10]	孙睿琦1, 窦修超2, 李志华1, 蒋雪梅2, 孙宇豪1. 基于改进YOLOv5的复杂路况密集行人检测方法[J]. 计算机与现代化, 2024, 0(05): 85-91.
[11]	刘耀鑫1, 陈仁喜2, 杨伟宏1. 一种针对抖动无人机视频的运动目标检测算法[J]. 计算机与现代化, 2024, 0(05): 99-103.
[12]	薛杨义1, 周立凡2, 龚声蓉1, 2. 用于遥感图像目标检测的少样本算法[J]. 计算机与现代化, 2024, 0(02): 43-49.
[13]	杨轲, 董兵, 吴悦, 郝宽公, 彭自琛. 基于轻量化YOLOv4机场场面遥感图像目标检测方法#br#[J]. 计算机与现代化, 2024, 0(02): 93-99.
[14]	王秋忆, 周浩, 郑婷婷. 改进RetinaNet的电力设备目标检测方法[J]. 计算机与现代化, 2024, 0(01): 47-52.
[15]	欧嘉城, 曾安, 金亮. 基于CP-YOLOX的冷冻电镜图像蛋白质目标检测算法[J]. 计算机与现代化, 2023, 0(11): 113-119.