The high variability of sign appearance with partial occlusions in uncontrolled environments has made the detection of traffic signs a challenging problem in computer vision. In this study, an occlusion-robust traffic sign detection framework is proposed. To achieve occlusion-robust detection, a colour cubic feature called colour cubic local binary pattern (CC-LBP) is proposed to construct a coarse-to-fine cascaded detector. The CC-LBP utilises colour information and a self-adaptive threshold to express multiclass traffic signs, which can effectively remove non-object subwindows in the cascade-based detection. The verification experiments show that the proposed CC-LBP feature performs better than the previous rectangular features in representing multiclass traffic signs, and that the proposed occlusion-robust detection method can detect multiclass partial occluded traffic signs with high accuracy in real time.
Occlusion-robust traffic sign detection via cascaded colour cubic feature
IET Intelligent Transport Systems ; 10 , 5 ; 354-360
2016-06-01
7 pages
Article (Journal)
Electronic Resource
English
object detection , partial occlusions , nonobject subwindows , sign appearance variability , colour information , computer vision , multiclass traffic signs , self-adaptive threshold , coarse-to-fine cascaded detector , CC-LBP , cascaded colour cubic feature , traffic engineering computing , feature extraction , colour cubic local binary pattern , image colour analysis , occlusion-robust traffic sign detection framework
Metadata by IET is licensed under CC BY 3.0
Occlusion‐robust traffic sign detection via cascaded colour cubic feature
Wiley | 2016
|Traffic Sign Occlusion Detection Using Mobile Laser Scanning Point Clouds
Online Contents | 2017
|Traffic Sign Occlusion Detection Using Mobile Laser Scanning Point Clouds
Online Contents | 2017
|