Detection and Recognition of Traffic Signs from Road Scene Images

Abstract

Automatic detection and recognition of road signs is an important component of automated driver assistance systems contributing to the safety of the drivers, pedestrians and vehicles. Despite significant research, the problem of detecting and recognizing road signs still remains challenging due to varying lighting conditions, complex backgrounds and different viewing angles. We present an effective and efficient method for detection and recognition of traffic signs from images. Detection is carried out by performing color based segmentation followed by application of Hough transform to find circles, triangles or rectangles. Recognition is carried out using three state-of-the-art feature matching techniques, SIFT, SURF and BRISK. The proposed system evaluated on a custom developed dataset reported promising detection and recognition results. A comparative analysis of the three descriptors reveal that while SIFT achieves the best recognition rates, BRISK is the most efficient of the three descriptors in terms of computation time.

A Comparative Study of Vision-Based Traffic Signs Recognition Methods

“…In the detection step, the image is segmented relying on the visual key of traffic signs features such as color [2,3] and shape [4]. Once the candidate traffic sign regions have been detected, a classifying step is performed to make the decision to keep or reject a candidate region of traffic sign.…”

Real Time Traffic Sign Detection Recognition using Adaptive Neuro Fuzzy Inference System

“…The creators [1] laid out a thorough viewpoint and study on vision based TSR for ITS featuring diverse calculations of sign location, feature extraction and sign recognition. The greater part of the recognition calculation proposed in the written works utilized shading data for division of the street picture [2,4,5,6,8,9,12]. For recognition feature vectors of sectioned locale of intrigue (ROI) is separated.…”

“…For recognition feature vectors of sectioned locale of intrigue (ROI) is separated. The creators [2] utilized Scale Invariant Feature Transform (SIFT), SURF and Binary Robust Invariant Scalable Key focuses (BRISK) feature descriptor to characterize the street sign and furthermore showed execution examination among these feature vectors. In [9] Histogram Oriented Gradient (HOG) feature vector was utilized to order the street sign.…”

“…In supervised learning worldview the feature vector is prepared by the classifier demonstrate and these models figure out how to separate the distinctive street signs. Classifiers utilized for recognition of street sign incorporate ANN [8], Adaboost [13,14], SVM [6,10,11,12] and KNN [2]. The creators [16,17] created TSR framework in light of content data of the traffic sign.…”

Recognition and Classification of Traffic Signs using Machine Learning Techniques

“…Different countries use different colors and various pictograms. [14] The machine should be adaptive, which means it should allow continuous learning otherwise the training should be repeated for each and every country.…”