Convolutional neural networks for parking space detection in downfire urban radar

Abstract

We present a method for detecting parking spaces in radar images based on convolutional neural networks (CNN). A multiple-input multiple-output radar is used to render a slant-range image of the parking scenario and a background estimation technique is applied to reduce the impact of dynamic interference from the surroundings by separating the static background from moving objects in the scene. A CNN architecture, that also incorporates mechanisms to generalize the model to new scenarios, is proposed to determine the occupancy of the parking spaces in the static radar images. The experimental results show very high accuracy even in scenarios where little or no training data is available, proving the viability of the proposed approach for its implementation at large scale with reduced deployment efforts.

EPSDNet: Efficient Campus Parking Space Detection via Convolutional Neural Networks and Vehicle Image Recognition for Intelligent Human–Computer Interactions

“…The random points covered by a vehicle can be detected using the density clustering model [42]. The indirect Monte Carlo method [43] was utilized to construct the probability discriminant model to judge the parking space. The distribution of one vehicle in a parking space was determined as shown in Figure 8, which includes the vehicle and parking space frame.…”