End-to-end Parking Slot Detection Method Based on Panoramic Surround View

被引：0
|
作者：
Qin X. [1 ,2 ]
Yin Z. [1 ]
Zhang S. [3 ]
Huang S. [1 ]
Zhang R. [1 ]
Lu T. [1 ]
Liu S. [1 ]
Hu M. [1 ,2 ]
机构：
[1] College of Mechanical and Vehicle Engineering, Hunan University, Changsha
[2] Wuxi Intelligent Control of Research Institute（WICRI）, Hunan University, Wuxi
[3] Center of Research and Department, WEICHAI Power Co. ，Ltd., Weifang
来源：
Hunan Daxue Xuebao/Journal of Hunan University Natural Sciences | 2024年 / 51卷 / 02期
基金：
中国国家自然科学基金;
关键词：
autonomous parking; object detection; parking slot detection; surround-view image;
D O I：
10.16339/j.cnki.hdxbzkb.2024156
中图分类号：
TP3 [计算技术、计算机技术];
学科分类号：
0812 ;
摘要：
Most of the existing parking spot detection solutions simply combine the target detection scheme and with manually designed post-processing modules，and there is a large amount of redundant information in the features extracted at each stage. Moreover，the manually designed post-processing modules are usually narrowly adapted and computationally intensive，which ultimately makes the parking space detection effect difficult to be practical. To address these problems，this paper introduces panoramic vision and combines the advantages of existing algorithms with the characteristics of surround-view images to design an end-to-end anchorless frame parking spot detection algorithm. The algorithm models the entry line orientation of parking spaces instead of considering two entry points separately，eliminating the process of parking space entry point matching and orientation judgment，and finally realizing realizes fully integrated parking space location，orientation，and occupancy detection. Considering the practicality，the network structure design is optimized in many aspects，such as the balance of speed and accuracy，positive and negative sample balance，and no post-processing. Finally，on the ps2.0 dataset，the AFPSD model proposed in this paper achieves 68.7% AP with a FPS（Frames Per Secend）of 88.7，which is 1.2% and 2.1% higher accuracy compared to the VPS-Net and DMPR-PS schemes，respectively. It can be seen that the one-stage end-to-end scheme designed in this paper can replace the three-stage scheme to achieve stable detection of parking slots on the surround-view image. © 2024 Hunan University. All rights reserved.
引用
收藏
页码：177 / 186
页数：9
相关论文
共 21 条
  • [1] LI L，, ZHANG L，, LI X，, Et al., Vision-based parking-slot detection：a benchmark and a learning-based approach, 2017 IEEE International Conference on Multimedia and Expo（ICME）, pp. 649-654, (2017)
  • [2] ZHANG L, Et al., Vision-based parking-slot detection：A DCNN-based approach and a large-scale benchmark dataset［J］, IEEE Transactions on Image Processing, 27, 11, pp. 5350-5364, (2018)
  • [3] Proceedings of the IEEE Conference on computer Vision and Pattern Recognition, pp. 7263-7271, (2017)
  • [4] HINTON G E., Imagenet classification with deep convolutional neural networks ［J］, Communications of the ACM, 60, 6, pp. 84-90, (2017)
  • [5] YAN L，, Et al., Vacant parking slot detection in the around view image based on deep learning［J］, Sensors, 20, 7, (2020)
  • [6] FARHADI A., Yolov3：an incremental improvement ［J］, (2018)
  • [7] HUANG J, ZHANG L，, SHEN Y，, Et al., DMPR-PS：a novel approach for parking-slot detection using directional marking-point regression, 2019 IEEE International Conference on Multimedia and Expo（ICME）, pp. 212-217, (2019)
  • [8] WANG M，, Et al., Psdet：efficient and universal parking slot detection, 2020 IEEE Intelligent Vehicles Symposium（IV）, pp. 290-297, (2020)
  • [9] LU X J., Automatic parking system based on surround view vision ［D］, (2020)
  • [10] GOYAL P, Et al., Focal loss for dense object detection［J］, IEEE Transaction on Pattern Analysis and Machine Intelligence, 42, 2, pp. 319-327, (2020)
123