While real-time parking slot detection plays a critical role in valet parking systems, existing methods have limited success in real-world application. We argue two reasons accounting for the unsatisfactory performance: i, The available datasets have limited diversity, which causes the low generalization ability. ii, Expert knowledge for parking slot detection is under-estimated. Thus, we annotate a large-scale benchmark for training the network and release it for the benefit of community. Driven by the observation of various parking lots in our benchmark, we propose the circular descriptor to regress the coordinates of parking slot vertexes and accordingly localize slots accurately. To further boost the performance, we develop a two-stage deep architecture to localize vertexes in the coarse-to-fine manner. In our benchmark and other datasets, it achieves the state-of-the-art accuracy while being real-time in practice. Benchmark is available at: https://github.com/wuzzh/Parking-slot-dataset
PSDet: Efficient and Universal Parking Slot Detection
2020-10-19
1844861 byte
Conference paper
Electronic Resource
English
PSDET: EFFICIENT AND UNIVERSAL PARKING SLOT DETECTION
British Library Conference Proceedings | 2020
|METHODOLOGY TO ESTIMATE SLOT LINE DIRECTION FOR PARKING SLOT DETECTION
European Patent Office | 2023
|Parking assistance system with universal parking space detection
European Patent Office | 2020
|Parking Assistance System with Universal Parking Space Detection
European Patent Office | 2017
|Line Filter-Based Parking Slot Detection for Intelligent Parking Assistance System
British Library Conference Proceedings | 2015
|