Abstract
Numerous vehicle detection methods have been proposed to obtain trustworthy traffic data for the development of intelligent traffic systems. Most of these methods perform sufficiently well under common scenarios, such as sunny or cloudy days; however, the detection accuracy drastically decreases under various bad weather conditions, such as rainy days or days with glare, which normally happens during sunset. This study proposes a vehicle detection system with a visibility complementation module that improves detection accuracy under various bad weather conditions. Furthermore, the proposed system can be implemented without retraining the deep learning models for object detection under different weather conditions. The complementation of the visibility was obtained through the use of a dark channel prior and a convolutional encoder–decoder deep learning network with dual residual blocks to resolve different effects from different bad weather conditions. We validated our system on multiple surveillance videos by detecting vehicles with the You Only Look Once (YOLOv3) deep learning model and demonstrated that the computational time of our system could reach 30 fps on average; moreover, the accuracy increased not only by nearly 5% under low-contrast scene conditions but also 50% under rainy scene conditions. The results of our demonstrations indicate that our approach is able to detect vehicles under various bad weather conditions without the need to retrain a new model.
Highlights
Numerous vehicle detection methods have been proposed to obtain trustworthy traffic data for the development of intelligent traffic systems. We can split these methods into two categories: the first category adopts the classical machine learning models trained from manually defined features [1,2,3,4,5,6], such as Haar-like features and histogram of gradients (HoG) features with AdaBoost classifiers and support vector machines (SVM) classifiers; the other category comprises deep learning model-based approaches constructed from large amounts of labeling data [7,8,9,10,11]
To resolve the above-mentioned issues of vehicle detection under various bad weather conditions without the cost of completely retraining the deep learning models for different weather conditions, this paper proposes a new vehicle detection system with a visibility complementation module that is integrated with multiple deep learning techniques
Through our proposed visibility complementation module, the visibility problem in various bad weather conditions was compensated; as Table 4 shows, under glare scene conditions, the recall rate increased from 85.22% to 89.82%, and the false classification ratio decreased from 14.71% to 9.97%
Summary
Numerous vehicle detection methods have been proposed to obtain trustworthy traffic data for the development of intelligent traffic systems. For a real-time system, only past frames can be taken as the reference frames; as a result, the restoration methods are not suitable for our application Another approach for this issue is to collect specific data to retrain the deep learning model. Training a deep learning model for all possible bad weather conditions suffers from huge computational times to converge the corresponding model weights and parameters; a visibility complementation module that can be combined with the exist vehicle detection method and can improve the detection accuracy for different weather conditions without retraining the classification model or deep learning model is needed. To resolve the above-mentioned issues of vehicle detection under various bad weather conditions without the cost of completely retraining the deep learning models for different weather conditions, this paper proposes a new vehicle detection system with a visibility complementation module that is integrated with multiple deep learning techniques.
Sign-in/Register to view highlights & summary 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 callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
