Efficient Detection and Tracking of Road Signs Based on Vehicle Motion and Stereo Vision

Choi, Chang-Won; Choi, Suhyoung; Park, Soon-Yong

doi:10.1007/978-3-319-02895-8_55

Cited by 1 publication

(1 citation statement)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The category of kernel-based approach is based on traffic signs appearance representation, namely templates and density-appearance models. In fact, Template matching is a brute force method which goes over the whole frame, looking for a similar region to the object template defined in the previous frame (Choi, Choi & Park, 2013). Instead of templates, other traffic signs representations can be used like color histograms (Zhang, Yu & Liu, 2013) which can be computed by using the appearance of pixels inside the traffic signs region.…”

Section: Traffic Sign Trackingmentioning

confidence: 99%

Automatic Recognition of Traffic Signs with 3D Distance Estimation for Intelligent Vehicles

Romdhane

Mliki

Hammami

2017

International Journal of Software Innovation

View full text Add to dashboard Cite

Traffic sign recognition (TSR) systems within the Advanced Driving Assistance Systems (ADAS) has attract many researchers as it plays a vital role to ensure road and transportation safety. In this paper, the authors introduce a new method for the automatic recognition and distance estimation of traffic signs using hybrid 2D-3D approach. The proposed method performs on two steps: Traffic signs recognition and distance estimation. The traffic signs recognition step aims to detect, classify and track traffic signs. Regarding the distance estimation step, it seeks to compute the depth distance of the traffic sign so as to estimate the distance between the recognized traffic sign and the vehicle carrying the camera. Many series of experiments were carried out on GTSBD and KITTI Stereo 2015 databases to evaluate the performance of the authors' method. The obtained results have shown that the proposed method achieves good performance in challenging scenarios.

show abstract

Section: Traffic Sign Trackingmentioning

confidence: 99%