A saliency-based cascade method for fast traffic sign detection

Wang, Dongdong and Yue, Shigang and Xu, Jiawei and Hou, Xinwen and Liu, Cheng-Lin (2015) A saliency-based cascade method for fast traffic sign detection. In: Intelligent Vehicles Symposium, IV 2015, June 28-July 1 2015, Seoul, South Korea.

Documents
__network.uni_staff_S2_jpartridge_07225683.pdf

Request a copy
[img] PDF
__network.uni_staff_S2_jpartridge_07225683.pdf - Whole Document
Restricted to Repository staff only

754kB
Item Type:Conference or Workshop contribution (Paper)
Item Status:Live Archive

Abstract

We propose a cascade method for fast and accurate traffic sign detection. The main feature of the method is that mid-level saliency test is used to efficiently and reliably eliminate background windows. Fast feature extraction is adopted in the subsequent stages for rejecting more negatives. Combining with neighbor scales awareness in window search, the proposed method runs at 3~5 fps for high resolution (1360x800) images, 2~7 times as fast as most state-of-the-art methods. Compared with them, the proposed method yields competitive performance on prohibitory signs while sacrifices performance moderately on danger and mandatory signs. © 2015 IEEE.

Additional Information:Conference Code:117127
Keywords:Feature extraction, Intelligent vehicle highway systems, Competitive performance, High resolution, State-of-the-art methods, Traffic sign detection, Window searches, Traffic signs
Subjects:G Mathematical and Computer Sciences > G400 Computer Science
J Technologies > J900 Others in Technology
Divisions:College of Science > School of Computer Science
Related URLs:
ID Code:20151
Deposited On:02 Mar 2016 14:47

Repository Staff Only: item control page