ABSTRACT
Aiming at the problem of large error in detecting lane lines on curved, long distance and complex roads by autonomous vehicles, a lane line detection algorithm based on dynamic ROI (Region Of Interest) and adaptive thresholding segmentation is proposed. According to the principle of inverse perspective transform, the original image is converted into an aerial view, and then the aerial view is preprocessed to calculate the gray column mean and full mean to dynamically determine the ROI. The image array is expanded for differentiation calculation. The adaptive threshold segmentation is carried out according to the characteristics of partition. The area and transverse and longitudinal span of each connected area in the binary diagram are calculated, and the interference factors are filtered out as required. Using the curve fitting algorithm of RANSAC (RANdom SAmple Consensus), the quadratic polynomial is defined as the target curve model to fit the characteristic points of lane line. The results show that the algorithm can accurately detect the lane lines under various road conditions.
- KORTLI Y, MARZOUGUI M, BOUALLEGUE B, A novel illumination-invariant lane detection system [C]// 2017 2nd International Conference on Anti-Cyber Crimes (ICACC), Abha, Saudi Arabia, 2017: 166-171.Google Scholar
- LI H L, MA L M, ZHONG L W. Lane Detection Based on improved Hough Transform [J]. Automotive Practical Technology, 2021, 46(07): 16-18.Google Scholar
- GAMAL I, BADAWY A, AL-HABAL A M W, A robust, real-time and calibration-free lane departure warning system [C]// 2019 IEEE International Symposium on Circuits and Systems (ISCAS), Sapporo, Japan, 2019: 1-4.Google Scholar
- DENG G, WU Y. Double Lane Line Edge Detection Method Based on Constraint Conditions Hough Transform [C]// 2018 17th International Symposium on Distributed Computing and Applications for Business Engineering and Science (DCABES), Wuxi, China, 2018: 107-110.Google Scholar
- OZGUNALP U, DAHNOUN N. Lane detection based on improved feature map and efficient region of interest extraction [C]// 2015 IEEE Global Conference on Signal and Information Processing (GlobalSIP), Orlando, FL, USA, 2015: 923-927.Google Scholar
- GUO J, WEI Z, MIAO D. Lane Detection Method Based on Improved RANSAC Algorithm [C]// 2015 IEEE Twelfth International Symposium on Autonomous Decentralized Systems, Taichung, Taiwan, 2015: 285-288.Google Scholar
- XU S, HE J H, WANG D. Research on Lane Detection Algorithm Based on Improved Double Threshold Segmentation [J]. Industrial Control Computer, 2021, 34(08): 110-112.Google Scholar
- LI W L, LIANG Z f, FANG W. A Multi-threshold Hough Transform Lane Line Detection Algorithm [J]. Journal of Xiamen University of Technology, 2021, 29(05): 1-7.Google Scholar
- XU X W, XIONG H, CHEN Q K, Lane Line Detection Method for Fusion Segmentation and Vanishing Point Extraction [J]. Journal of Henan University of Science and Technology (Natural Science Edition), 2022, 43(01): 32-37.Google Scholar
- YANG Q G, HOU Zh W. Research on a Vehicle Distance Measurement Method based on Vanishing Point Detection of Lane Line [J]. Automotive Engineer, 2021, (06): 35-38.Google Scholar
- WANG T T, HUO C B, BAI B, Intelligent Detection Method of Lane Line Based on OpenCV [J]. Information Technology and Informatization, 2021, (09): 224-227.Google Scholar
- Hua C J, Pan R, Chen Y. A Fast Lane Line Detection Algorithm Based on the Continuity of Edge Direction [J]. Journal of Sensor Technology, 2021, 34 (08): 1082-1088.Google Scholar
- ZHANG Luyao, LIANG Yuming, ZHANG Tianlu. mproved Lane Line Detection Algorithm Based on OpenCV [J]. Information Technology and Informatization, 2019, (12): 108-111.Google Scholar
- XIN Xiaomeng, YIN Xue, ZHAO Yuhang, Accurate Detection of Damaged Lane Lines on Pavement [J]. Journal of Changzhou Institute of Technology, 2020, 33 (06): 37-40.Google Scholar
- XIE Changgang, LI Xiangfeng, LI Kun, Lane Line Detection Algorithm Based on Dynamic Partition of Interested Region [J]. Machinery Manufacturing and Automation, 2019, 48(06): 150-154.Google Scholar
- LI Haihua, WAN Rehua, CHEN Xiaoling, A lane line detection method based on inverse perspective transformation [J]. Industrial Instrumentation & Automation Devices, 2021, (02): 97-100.Google Scholar
- SHEN Mei, YANG Hongtao, JIANG Kuosheng, Research on lane line detection and recognition algorithm based on Raspberry Pi platform[J]. Modern Electronics Technology, 2021, 44 (17): 141-145.Google Scholar
- JIANG L, LI J, AI W. Lane Line Detection Optimization Algorithm based on Improved Hough Transform and R-least Squares with Dual Removal [C]// 2019 IEEE 4th Advanced Information Technology, Electronic and Automation Control Conference (IAEAC), Chengdu, China, 2019: 186-190.Google Scholar
Recommendations
A lane line detection method based on adaptive ROI selection for smart networked vehicles
ICIT '21: Proceedings of the 2021 9th International Conference on Information Technology: IoT and Smart CityThe assisted driving and autonomous driving of intelligent networked vehicles have become an inevitable trend in the development of the automotive industry, and the detection of lane lines provides the basic core function for intelligent driving ...
Real time lane detection model based on Lightweight
ICVIP '20: Proceedings of the 2020 4th International Conference on Video and Image ProcessingMany cars now have functions to assist the driver in driving, such as keeping the lane. This function can keep the vehicle in a proper position between lanes. This function can ensure the safety of the vehicle. The traditional lane detection method ...
End-to-End Lane Detection: a Key Point Approach
ICRSA '21: Proceedings of the 2021 4th International Conference on Robot Systems and ApplicationsNowadays, autonomous driving is becoming more and more popular. Lane line detection is very important for trajectory planning and decision making in autonomous driving. Traditional lane detection methods rely on highly defined, manual feature extraction ...
Comments