For vehicles equipped with the automatic parking system, the accuracy and speed of the parking slot detection are crucial. But the high accuracy is obtained at the price of low speed or expensive computation equipment, which are sensitive for many car manufacturers. In this paper, we proposed a detector using CNN (convolutional neural networks) for faster speed and smaller model size while keeps accuracy. To achieve the optimal balance, we developed a strategy to select the best receptive fields and prune the redundant channels automatically after each training epoch. The proposed model is capable of jointly detecting corners and line features of parking slots while running efficiently in real time on average processors. The model has a frame rate of about 30 FPS on a 2.3 GHz CPU core, yielding parking slot corner localization error of $1.51\pm 2.14$ cm (std. err.) and slot detection accuracy of 98%, generally satisfying the requirements in both speed and accuracy on onboard mobile terminals.
SPFCN: Select and Prune the Fully Convolutional Networks for Real-time Parking Slot Detection
19.10.2020
2299458 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
SPFCN: SELECT AND PRUNE THE FULLY CONVOLUTIONAL NETWORKS FOR REAL-TIME PARKING SLOT DETECTION
British Library Conference Proceedings | 2020
|METHODOLOGY TO ESTIMATE SLOT LINE DIRECTION FOR PARKING SLOT DETECTION
Europäisches Patentamt | 2023
|PSDET: EFFICIENT AND UNIVERSAL PARKING SLOT DETECTION
British Library Conference Proceedings | 2020
|Line Filter-Based Parking Slot Detection for Intelligent Parking Assistance System
British Library Conference Proceedings | 2015
|