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.
本文采用上述试验配置,验证停车位检测算法的性能.首先对主干网络进行试验,使用一些常用的主干网络构建停车位检测网络,进行训练之后在ps2.0数据集上测试其性能.试验结果见表2,其中ResNet50由He等[18]于2016年提出,在网络结构设计中引入残差结构应对退化问题,此后被许多不同领域的算法作为主干网络使用.hourglass[19]由多个包含了上采样、下采样、跳层连接的沙漏模块组成,反复的上采样再下采样,使其能够捕获特征之间的关联性,因而常被用于关键点检测任务中,而本文设计的停车位检测方案也包含两个入口点之间关联信息的提取,所以该主干网络也被选为对比网络之一.表2中,P(Precision)表示精确率,R(Recall)表示召回率,FPS(Frames Per Second)表示每秒帧数.
LIL, ZHANGL, LIX, et al. Vision-based parking-slot detection: a benchmark and a learning-based approach[C]//2017 IEEE International Conference on Multimedia and Expo (ICME). Hong Kong, China, IEEE, 2017: 649-654.
[2]
ZHANGL, HUANGJ, LIX, et al. Vision-based parking-slot detection: A DCNN-based approach and a large-scale benchmark dataset[J]. IEEE Transactions on Image Processing, 2018, 27(11): 5350-5364.
[3]
REDMONJ, FARHADIA. YOLO9000: better, faster, stronger[C]//Proceedings of the IEEE Conference on computer Vision and Pattern Recognition. Honolulu, HI, USA: IEEE, 2017: 7263-7271.
[4]
KRIZHEVSKYA, SUTSKEVERI, HINTONG E. Imagenet classification with deep convolutional neural networks[J]. Communications of the ACM, 2017, 60(6): 84-90.
[5]
LIW, CAOL, YANL, et al. Vacant parking slot detection in the around view image based on deep learning[J]. Sensors, 2020, 20(7): 2138.
[6]
REDMONJ, FARHADIA. Yolov3: an incremental improvement[J]. arXiv preprint arXiv:2018.
[7]
HUANGJ, ZHANGL, SHENY, et al. DMPR-PS: a novel approach for parking-slot detection using directional marking-point regression[C]//2019 IEEE International Conference on Multimedia and Expo (ICME). Shanghai, China: IEEE, 2019: 212-217.
[8]
WUZ, SUNW, WANGM, et al. Psdet: efficient and universal parking slot detection[C]//2020 IEEE Intelligent Vehicles Symposium (IV). Las Vegas, NV, USA: IEEE, 2020: 290-297.
[9]
吕雪杰. 基于环视视觉的自动泊车系统[D]. 北京: 北京交通大学, 2020.
[10]
LÜX J. Automatic parking system based on surround view vision[D]. Beijing: Beijing Jiaotong University,2020.(in Chinese)
[11]
LINT Y, GOYALP, GIRSHICKR, et al. Focal loss for dense object detection[J]. IEEE Transaction on Pattern Analysis and Machine Intelligence, 2020,42(2): 319-327.(in Chinese)
[12]
LIW, CAOL, YANL, et al. Vacant parking slot detection and tracking during driving and parking with a standalone around view monitor[J]. Proceedings of the Institution of Mechanical Engineers, Part D: Journal of Automobile Engineering, 2021, 235(6): 1539-1551.
[13]
WANGC Y, LIAOH Y M, WUY H, et al. CSPNet: a new backbone that can enhance learning capability of CNN[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops. Seattle, WA, USA: IEEE,2020: 390-391.
[14]
CAOY, XUJ, LINS, et al. Gcnet: non-local networks meet squeeze-excitation networks and beyond[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision Workshops. Seoul, Kovea: ICCV, 2019.
[15]
VASWANIA, SHAZEERN, PARMARN, et al. Attention is all you need[C]//ICASSP 2021-2021 IEEE International Conference on Acoustics,Speach and signal processing (ICASSP), Toronto,ON,Canada, 2021.
[16]
HUJ, SHENL, SUNG. Squeeze-and-excitation networks[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Salt Lake City, UT,USA:IEEE, 2018: 7132-7141.
[17]
SONGG, LIUY, WANGX. Revisiting the sibling head in object detector[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.Seattle, WA,USA:IEEE, 2020: 11563-11572.
[18]
JIANGB, LUOR, MAOJ, et al. Acquisition of localization confidence for accurate object detection[C]//Proceedings of the European Conference on Computer Vision (ECCV). Munich Germany: ECCV, 2018: 784-799.
[19]
HEK, ZHANGX, RENS, et al. Deep residual learning for image recognition[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas,NV, USA:IEEE, 2016: 770-778.
[20]
NEWELLA, YANGK, DENGJ. Stacked hourglass networks for human pose estimation[C]//Computer Vision-ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11-14, 2016, Proceedings, Part VIII 14. Springer International Publishing, 2016: 483-499.
[21]
LINT Y, DOLLÁRP, GIRSHICKR, et al. Feature pyramid networks for object detection[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Honolulu, HI,USA: 2017: 2117-2125.
[22]
LIUS, QIL, QINH, et al. Path aggregation network for instance segmentation[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Salt Lake City, UT, USA: IEEE, 2018: 8759-8768.
基金资助
长沙市自然科学基金资助项目(kq2202162)
Changsha Natural ScienceFoundation of China(kq2202162)
国家自然科学基金资助项目(52172384)
National Natural Science Foundation of China(52172384)
湖南省湖湘青年科技创新人才(2021RC3048)
S&T Innovation Program of Hunan Province(2021RC3048)
汽车车身先进设计制造国家重点实验室自主研究课题(61775006)
Independent Research Program of State Key Laboratory of Advanced Design and Manufacturing for Vehicle Body(61775006)