Research Article
Highway Obstacle Recognition Based on Improved YOLOv7 and Defogging Algorithm
@INPROCEEDINGS{10.1007/978-3-031-70507-6_3, author={Mingliang Fan and Jing Liu and Jiaming Yu}, title={Highway Obstacle Recognition Based on Improved YOLOv7 and Defogging Algorithm}, proceedings={IoT as a Service. 9th EAI International Conference, IoTaaS 2023, Nanjing, China, October 27-29, 2023, Proceedings}, proceedings_a={IOTAAS}, year={2024}, month={10}, keywords={highway obstacle detection YOLOv7 deep learning}, doi={10.1007/978-3-031-70507-6_3} }- Mingliang Fan
Jing Liu
Jiaming Yu
Year: 2024
Highway Obstacle Recognition Based on Improved YOLOv7 and Defogging Algorithm
IOTAAS
Springer
DOI: 10.1007/978-3-031-70507-6_3
Abstract
This study explores a haze removal algorithm based on an enhanced Laplacian operator and guided filtering to enhance image visibility and quality. This algorithm is applicable not only to images taken in hazy weather conditions but also incorporates intelligent transportation systems by employing YOLOv7 object recognition technology. This enables accurate detection and identification of traffic objects within the images. By integrating the improved Laplacian operator into the traditional guided filtering framework, this approach effectively mitigates issues of image blurring and decreased contrast caused by haze, thereby enhancing image transparency. Simultaneously, the Integration of YOLOv7 into the system allows for rapid and precise detection of traffic objects, providing accurate data support for intelligent transportation systems. As a result, this study not only explores novel haze removal techniques in the field of image processing but also brings forth new technological applications for the advancement of intelligent transportation systems.
