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

Abstract

Automatic detection and recognition of traffic signs is a topic of research for various applications like driver assistance, inventory management and autonomous driving. Poorly maintained traffic signs degrade by losing their colors or some part is weird due to aging and hence making the task more challenging. The problem is mainly related to the developing world and has gained less attention in the literature on automatic traffic sign detection and recognition. To handle the degradation issue, we present a novel flexible Gaussian mixture model based technique with automatic split and merge strategy. This adaptive scheme works as a preprocessing step which facilitates locating traffic signs under a certain degree of degradation in a real world scenario. A multiscale convolutional neural network augmented with dimensionality reduction layer is proposed to recognize contents of the sign. Since, there is no available benchmark dataset for this purpose, we collected a number of images containing partially degraded signs from the famous German Traffic Sign Detection Benchmark (GTSDB) and augmented it with manually and naturally degraded traffic sign images taken from the longest highway in the country of authors' residence. Experimental results show that our proposed technique outperforms many state of the art and recent methods for detection and recognition of degraded traffic signs. INDEX TERMS Degraded traffic sign, Gaussian mixture model, Transfer learning, Convolutional neural networks, dimensionality reduction.

Intelligent Recognition Technology for the Segmentation of Traffic Indication Images Concerning Different Pavement Materials

“…The image registration of processing point groups was proposed to highlight a group of traffic signs on the two-dimensional image plane [ 13 ]. The third dimension, according to the extracted traffic sign point, creates a relationship between the geospatial traffic signs and the road environment, thus recommending a process to check the location of the traffic signs and layout [ 14 , 15 ].…”

Composition and Application of Current Advanced Driving Assistance System: A Review

“…These kinds of problems may influence the accuracy of traffic sign detection. For this reason, [57] has proposed a novel methodology to solve degraded traffic sign recognition. They use a novel flexible linear mapping technique to first fix outer rim color fade problem and then send the output into a flexible Gaussian mixture dynamically updating split and merge scheme to capture the feature of the original signal.…”