Title: Fast road scenarios recognition of intelligent vehicles by image processing

Authors: Huawei Wu; Yicheng Li; Jie Zhang; Yong Kuang

Addresses: Hubei Key Laboratory of Power System Design and Test for Electrical Vehicle, Hubei University of Arts and Science, Xiangyang 441053, China; School of Automotive and Traffic Engineering, Hubei University of Arts and Science, Xiangyang 441053, China ' Automotive Engineering Research Institute, Jiangsu University, Zhenjiang 212013, China ' Cangzhou Medical College, Cangzhou, 061001, China ' Dongfeng Xiangyang Touring Car Co., Ltd., China

Abstract: Road scenarios recognition is a key point for intelligent vehicles (IVs) self-localisation. This paper proposes a fast road scenarios recognition method by image processing, which is based on a visual road model. First, a sequence of images is used to set up a visual road model. Second, we use the ORB method to encode both holistic and local features of a query image. Third, we extend the use of H-KNN to fuse ORB-encoded holistic and local features for road scenarios recognition. Real-world driving tests have been carried out in different routes scenarios. The total lengths of these routes are more than 5 km. The experiment results show that the proposed method achieved 80.2% image recognition rate, with about 18 ms in average for localisation from one image. The results demonstrate that the main method is promising in term of recognition accuracy and speed to develop low-cost recognition device for IVs.

Keywords: intelligent vehicle; computer vision; road scenario recognition; holistic feature; local feature; hybrid KNN.

DOI: 10.1504/IJICT.2021.111916

International Journal of Information and Communication Technology, 2021 Vol.18 No.1, pp.1 - 15

Received: 15 Jun 2019
Accepted: 09 Oct 2019
Published online: 21 Dec 2020 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article