COMMAX 2020 UiTM Kampus Kuala Terengganu

Traffic sign detection is the pivotal technology of the traffic sign recognition system. In
this report, a traffic sign detection method comes up based on Faster R-CNN deep learning
framework. In this method, a convolution neural network is devoted to extract traffic sign
image features automatically, and the extracted convolution feature map is sent into a
Region Proposal Network (RPN) for foreground objects filtration and regression of
bounding boxes. Then the proposed regions are mapped to the feature map, and the fixed-
size proposal boxes via Region of Interest pooling layer (RoI). After that, i use the
classification network to perform specific classification tasks and further compute the
bounding box regression. The experimental results show that the method has effectiveness
and robustness to different light, block, and motion. Throughout this project, the
identification of CNN requirements, prototype development and model evaluation are the
three objectives that already has been achieved successfully. However, there is some
limitations and recommendation that have been analysed and need to discuss further for
future improvement.There are many suggested recommendations for the future system.
First of all, this project can be improved by improving the system so that all of the traffic
sign image can detect. With this solution, the user can achieve the real traffic sign image
detection. Secondly, one of the most important way that must take it as a serious
recommendation is the used of hardware to develop this project. To develop this kind of
complex project, it needs powerful device so that it can maintain the performance of the
system. If the device used is powerful, it able to train thousands of data.