Abstract

Computer vision is an important part of the autonomous vehicles to gain the perception of the surrounding environment. In order to satisfy the adaptability of lane detection system under different illumination and different road conditions, an effective lane detection method based on image classification and hybrid isomeric operators is proposed. Camera correction matrix and distortion coefficient are obtained by using checkerboard grid images, and they will be cached to be shared with subsequent image streams to improve the speed of real-time lane detection. In the process of preprocessing, the images under different illumination conditions are classified and processed, and the inverse perspective transformation is used to deal with the 2-D image flow so that the image flow has a certain depth of data. According to the intensity of the whole gray mean, the edge detection is carried out by using heterogeneous operators and combining with a variety of threshold filtering methods to extract the lane pixels. The lane detection module transmits the vehicle steering angle and the deviate distance from the road center line to the decision layer, effectively implementing the interactive simulation. Experiments show that the algorithm has good real-time performance, stability, and robustness under different illumination and road conditions.

Highlights

  • Autonomous Driving Vehicle is an important part for implementing the strategy of Made in China 2025 and ‘‘the Notice of the State Council on the Issue of the New Generation of Artificial Intelligence Development Plan’’, Made in China 2025 proposed to establish an intelligent network vehicle Independent research development system and production supporting system by 2020

  • In the virtual test group competition of the second World Intelligent Driving Challenge in 2018, we found that different illumination conditions and road conditions are the biggest obstacles to lane detection

  • The actual test shows that the system can detect lane in real time and reliably under different illumination conditions and different road conditions

Read more

Summary

INTRODUCTION

Autonomous Driving Vehicle is an important part for implementing the strategy of Made in China 2025 and ‘‘the Notice of the State Council on the Issue of the New Generation of Artificial Intelligence Development Plan’’, Made in China 2025 proposed to establish an intelligent network vehicle Independent research development system and production supporting system by 2020. In order to satisfy the actual requirements, lane detection algorithm must ensure good reliability, real-time and robustness. In the virtual test group competition of the second World Intelligent Driving Challenge in 2018, we found that different illumination conditions and road conditions are the biggest obstacles to lane detection. Designing a system which can detect lane stably all-weather will effectively enhance the robustness of lane detection In this system, the accuracy and realtime identification of lane detection in different illumination conditions and different road conditions are the most important. This method can meet the real-time requirement, but the robustness needs to be improved under the conditions of illumination change and vehicle interference. The actual test shows that the system can detect lane in real time and reliably under different illumination conditions and different road conditions. There has been much work on data classification in recent years [9], it is still a challenging task

CAMERA CALIBRATION
CANNY OPERATOR
ANALYSIS OF TEST RESULTS
CONCLUDING REMARKS
Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call