Robust detection of landmarks in color image based on fuzzy set theory

There are some tasks required to make vehicles fully automated for road detection, obstacle avoidance, and sign recognition. Detecting landmarks is one of key steps to vision-based vehicle guidance. This paper focuses on detecting traffic-sign-type landmarks from real scenes. A new landmark extracting algorithm based on fuzzy set theory is proposed. Experimental results show that the algorithm is robust to noise and performs well on real landmark detection.