Author(s)

Bongkyo Moon^1*, Jiwon Choi², Juehyun Lee³, Minyoung Lee³

¹Department of Computer Science and Engineering, Dongguk University, Seoul, South Korea.
²Graduate School of Information Security, KAIST, Daejeon, South Korea.
³Electronics and Telecommunications Research Institute (ERTI), Daejeon, South Korea.

This paper proposes an efficient object localization method based on a vanishing line. The proposed method can be much improved in time efficiency since it requires scanning only vanishing line area. It requires the time complexity of O(n) while the existing sliding window method requires the time complexity O(n²) for detecting all objects in the entire image. In addition, the range of detection area can be also remarkably reduced when compared with the sliding window method. As a result, the total range and times for searching in the proposed method can be significantly reduced by considering together the distance and position of the object. The experiment on the proposed method is performed with the virtual road data set known as SYNTHIA, and the competitive results are obtained.

Object Localization, Image Preprocessing, Sliding Window, Vanishing Line, Autonomous Vehicle

Moon, B. , Choi, J. , Lee, J. and Lee, M. (2021) Efficient Object Localization Scheme Based on Vanishing Line in Road Image for Autonomous Vehicles. Journal of Computer and Communications, 9, 85-97. doi: 10.4236/jcc.2021.99006.