An Optimization Approach for Localization Refinement of Candidate Traffic Signs

Abstract

We propose a localization refinement approach for candidate traffic signs. Previous traffic sign localization approaches, which place a bounding rectangle around the sign, do not always give a compact bounding box, making the subsequent classification task more difficult. We formulate localization as a segmentation problem, and incorporate prior knowledge concerning color and shape of traffic signs. To evaluate the effectiveness of our approach, we use it as an intermediate step between a standard traffic sign localizer and a classifier. Our experiments use the well-known German Traffic Sign Detection Benchmark (GTSDB) as well as our new Chinese Traffic Sign Detection Benchmark. This newly created benchmark is publicly available, 1 and goes beyond previous benchmark data sets: it has over 5000 high-resolution images containing more than 14 000 traffic signs taken in realistic driving conditions. Experimental results show that our localization approach significantly improves bounding boxes when compared with a standard localizer, thereby allowing a standard traffic sign classifier to generate more accurate classification results.

Vision-Based Traffic Sign Detection and Recognition Systems: Current Trends and Challenges

“…Subsequently, shape detection is implemented and is applied only to the segmented regions [58]. Color and shape features were combined into traffic sign detection algorithms in studies [71,72,73,74,75,76]. In these studies, different signs with various colors and shapes were detected using different datasets.…”

Classification of Degraded Traffic Signs Using Flexible Mixture Model and Transfer Learning

“…This makes them unsuitable for signs with large variation in colors due to aging etc. Optimization based method proposed in [13] uses color edge data to localize traffic sign in a real world scene and use Markov random field to obtain a tight box around a detected sign. Color probability maps (CPM) [6] based method uses statistical parameter estimation using Ohta transform [32].…”

“…The associate editor coordinating the review of this manuscript and approving it for publication was Wei Liu. of methods used for segmenting a traffic sign in a complex outdoor scene i.e., (1) thresholding in various color spaces like RGB, HSI, etc. [1]- [5] (2) using statistical parameter estimation for colors of interest [6]- [8] (3) using saliency and/or dictionary learning to segment windows containing a traffic sign with a certain confidence level [9], [10] and (4) using convolutional neural networks (CNN) to indicate that a real world image contains a traffic sign [11]- [13]. CNN based methods are very famous but most of the times post processing is required to exactly crop the portion containing pictogram of the traffic sign [11].…”

Deep learning–based traffic sign recognition for unmanned autonomous vehicles

“…Till now, CNNs have been successfully used in a great number of applications, such as handwritten recognition, 22 traffic sign detection, 23,24 visual object recognition, 25 human action identification, 26 brain-computer interaction 27 and audio classification. 28 The CNN-based methods [29][30][31][32] outperform the other three classes; however, they process the inputs as either gray images or three color channels separately. Therefore, it is necessary to explore the ways of learning color features efficiently.…”

“…The CNN-based methods 29–32 outperform the other three classes; however, they process the inputs as either gray images or three color channels separately. Therefore, it is necessary to explore the ways of learning color features efficiently.…”