For Full-Text PDF, please login, if you are a member of IEICE,|
or go to Pay Per View on menu list, if you are a nonmember of IEICE.
Vision Based Nighttime Vehicle Detection Using Adaptive Threshold and Multi-Class Classification
Yuta SAKAGAWA Kosuke NAKAJIMA Gosuke OHASHI
IEICE TRANSACTIONS on Fundamentals of Electronics, Communications and Computer Sciences
Publication Date: 2019/09/01
Online ISSN: 1745-1337
Type of Manuscript: Special Section PAPER (Special Section on Image Media Quality)
intelligent transportation systems, nighttime driving scenes, vehicle detection, Niblack thresholding, Random Forest, mathematical morphology,
Full Text: PDF(3.1MB)>>
We propose a method that detects vehicles from in-vehicle monocular camera images captured during nighttime driving. Detecting vehicles from their shape is difficult at night; however, many vehicle detection methods focusing on light have been proposed. We detect bright spots by appropriate binarization based on the characteristics of vehicle lights such as brightness and color. Also, as the detected bright spots include lights other than vehicles, we need to distinguish the vehicle lights from other bright spots. Therefore, the bright spots were distinguished using Random Forest, a multiclass classification machine-learning algorithm. The features of bright spots not associated with vehicles were effectively utilized in the vehicle detection in our proposed method. More precisely vehicle detection is performed by giving weights to the results of the Random Forest based on the features of vehicle bright spots and the features of bright spots not related to the vehicle. Our proposed method was applied to nighttime images and confirmed effectiveness.