In this project, we developed a computer vision algorithm that can detect the traffic signs and road markings on the road. Machine learned based feature extraction and classification are employed to recognize the detected sign. The algorithm is highly efficient and does not require the CNN architecture that often requires large computational resource. For real-time processing, we implemented the efficient algorithm on an FPGA, which can process 1080p high-resolution images at 60 fps. The FPGA implementation is ready to be integrated into an existing ADAS or autonomous vehicle platform.

Click to view the result in Youtube