Traffic vehicle cognition in severe weather based on radar and infrared thermal camera fusion
- 5 May 2021
- journal article
- research article
- Published by IOP Publishing in Measurement Science and Technology
- Vol. 32 (9), 095111
- https://doi.org/10.1088/1361-6501/abfe34
Abstract
The accuracy and robustness of vehicle cognition in severe weather has always been the focus and difficulty of intelligent vehicle environment perception. This paper proposed a vehicle cognition method based on radar and infrared thermal camera information fusion in severe weather. The fusion of radar and infrared camera can greatly enrich the completeness of vehicle cognitive information. Firstly, an attention mechanism based on radar guidance information was proposed to extract vehicle ROI. Unlike the traditional ROI extraction method, this method is not disturbed by the environment and does not need complicated calculations, which can quickly and accurately extract ROI for vehicles. Secondly, based on ROI information, the infrared thermal image was reconstructed and enhanced, which is of great significance to improve the accuracy of vehicle detection for deep learning. Finally, we propose a vehicle depth estimation method based on pixel regression and use multi-scale cognitive information to fuse radar and image targets. The fusion method considering depth information can reduce target confusion and improve fusion robustness and accuracy, especially when vehicles are adjacent to each other. The experimental results show that the vehicle detection accuracy of this method is 95.2% and the vehicle detection speed is 37 Fps, which effectively improves the performance of vehicle detection in severe weather.Keywords
Funding Information
- National Natural Science Foundation of China (U1664261)
- National College Students’ innovation and entrepreneurship training program (202010183258)
- Jilin University Postgraduate Innovation Funding Project (101832020CX137)
- Jilin University Postgraduate Innovation Fund Project (101832020CX137)
- Natural Science Foundation of Jilin Province (20170101209JC)
This publication has 23 references indexed in Scilit:
- A survey of transfer learningJournal of Big Data, 2016
- Night-Time Vehicle Sensing in Far Infrared Image with Deep LearningJournal of Sensors, 2016
- Robust Nighttime Vehicle Detection by Tracking and Grouping HeadlightsIEEE Transactions on Intelligent Transportation Systems, 2015
- Optimized contrast enhancement for real-time image and video dehazingJournal of Visual Communication and Image Representation, 2013
- Robust vehicle detection even in poor visibility conditions using infrared thermal images and its application to road traffic flow monitoringMeasurement Science and Technology, 2011
- Single Image Haze Removal Using Dark Channel PriorIEEE Transactions on Pattern Analysis and Machine Intelligence, 2010
- Rear-Lamp Vehicle Detection and Tracking in Low-Exposure Color Video for Night ConditionsIEEE Transactions on Intelligent Transportation Systems, 2010
- Model based vehicle detection and tracking for autonomous urban drivingAutonomous Robots, 2009
- On-road vehicle detection: a reviewIEEE Transactions on Pattern Analysis and Machine Intelligence, 2006
- Fusion of multiple classifiers for intrusion detection in computer networksPattern Recognition Letters, 2003