Traffic Sign Recognition Using Visual Attributes and Bayesian Network.

Recognizing traffic signs is a crucial task in Advanced Driver Assistant Systems. Current methods for solving this problem are mainly divided into traditional classification approach based on hand-crafted features such as HOG and end-to-end learning approaches based on Convolutional Neural Networks (ConvNets). Despite a high accuracy achieved by ConvNets, they suffer from high computational complexity which restricts their application only on GPU enabled devices. In contrast, traditional classification approaches can be executed on CPU based devices in real-time. However, the main issue with traditional classification approaches is that hand-crafted features have a limited representation power. For this reason, they are not able to discriminate a large number of traffic signs. Consequently, they are less accurate than ConvNets. Regardless, both approaches do not scale well. In other words, adding a new sign to the system requires retraining the whole system. In addition, they are not able to deal with novel inputs such as the false-positive results produced by the detection module. In other words, if the input of these methods is a non-traffic sign image, they will classify it into one of the traffic sign classes. In this paper, we propose a coarse-to-fine method using visual attributes that is easily scalable and, importantly, it is able to detect the novel inputs and transfer its knowledge to a newly observed sample. To correct the misclassified attributes, we build a Bayesian network considering the dependency between the attributes and find their most probable explanation using the observations. Experimental results on a benchmark dataset indicates that our method is able to outperform the state-of-art methods and it also possesses three important properties of novelty detection, scalability and providing semantic information.