AUTHOR=Li Wei , Cao Hu , Liao Jiacai , Xia Jiahao , Cao Libo , Knoll Alois 

TITLE=Parking Slot Detection on Around-View Images Using DCNN

JOURNAL=Frontiers in Neurorobotics

VOLUME=Volume 14 - 2020

YEAR=2020

URL=https://www.frontiersin.org/journals/neurorobotics/articles/10.3389/fnbot.2020.00046

DOI=10.3389/fnbot.2020.00046

ISSN=1662-5218

ABSTRACT=Due to the complex visual environment and incomplete display of parking slot on around view images, the vision-based parking slot detection is a big challenge. Previous studies in this field mostly use the existing models to solve it, whose steps are cumbersome. In this paper, we propose a parking slot detection method using directional entrance line regression and classification based on deep convolutional neural network (DCNN) to make it robust and simple. For parking slots with different shapes and being observed from different angles, we represent the parking slot as a directional entrance line. Subsequently, we design a DCNN detector to simultaneously obtain the type, position, length, direction of the entrance line. After that, the complete parking slot can be easily inferred using detection results and prior geometric information. To verify our method, we conduct experiments on the public ps2.0 dataset and self-annotated parking slot dataset with 2135 images. The results show that our method not only outperforms state-of-the-art competitors with a precision rate of 99.68% and a recall rate of 99.41%$on the ps2.0 dataset but also has a satisfying generalization on the self-annotated dataset. Moreover, it achieves a real-time detection speed of 13ms per frame on Titan Xp. By converting the parking slot into a directional entrance line, a specially designed DCNN detector can quickly and effectively detect various types of parking slots.