Parking information perception based on automotive millimeter wave SAR

Autonomous vehicle (Auto-v) has received wide attention for its possible advantages that can provide much safer driving than human drivers. Autonomous parking becomes a tricky issue because the parking environment is often too complex to be fully perceived. The information acquired with the millimeter wave synthetic aperture radar (SAR) could be helpful to solve this problem. In this paper, an information perception method for parking is presented. It adopts the visual saliency detection method based on spectral residual to obtain the locations of the vehicles and empty parking sites, and use the morphology filter to judge the postures of the vehicles. Then, the vehicle types are classified based on principal component analysis (PCA) and support vector machine (SVM). Finally, the suitable parking sites are obtained according to the parking information perception. This study can be used to search the available parking sites, and confirm whether the obstacles of the empty parking site exist, which can assist the safe parking of autonomous vehicle. Experimental results based on measured automotive millimeter wave SAR images show the effectiveness and accuracy of the proposed parking information perception method.