A new design on image processing scheme for smart car
Yixu Chen · Journal of Physics Conference Series · 2018
As a product of comprehensive discipline, smart car involve artificial intelligence, computer vision, mechanical design, control science and vehicle engineering, etc. In this study, we take the NXP smart car competition as the background and put forward a new image processing scheme for smart car. The purpose of the image processing is to identify the different types of track from continuously transformed video images, to filter out noise and interference in the images, to identify the obstacles and extract the available left and right edges of the track. The proposed new scheme can effectively extract and classify the image features of different road types and give corresponding image processing algorithms. Experiments show that this scheme can efficiently deal with the probe images and provide accurate image information for smart car. Thus, the proposed scheme has a high practical value in applications, such as smart car contests and self-driving car industry.