도로관리청은 고속도로 진·출입 톨게이트 및 본선에 저속 WIM 또는 고속 WIM을 설치하여 과적차량을 단속하고 있으나, 근래 과적 화물차가 가변축을 불법 조작하여 도로관리청의 과적차량 단속시스템을 지능적으로 회피하는 운행이 증가하고 있다. 과적 검문소 진입 시에는 차축을 모두 내려 정상 통과하고 본선 주행 시에는 가변축을 불법으로 들어 축하중 10톤을 초과하여 과적 운행하는 방식이다. 이에 본 연구는 도로변에 차량 옆면 촬영 카메라를 설치하여 도로 주행 중인 화물차의 가변축 상태를 검지하는 기술을 개발하였다. 과적차량 검문소의 계중정보 연계 시 검문소 진출 후 차축을 들어 과적 운행하는 차량을 단속할 수 있는 기반기술이다. 제안기술은 제2서해안고속도로 송산마도IC~마도JC 구간 노변에서 취득된 영상을 학습데이터로 가공하고 Mask RCNN 알고리즘을 활용하여 타이어를 인식하였으며 인식된 타이어들을 배열하고 높이차를 측정하는 방식으로 타이어의 들림 여부를 판단하였다.
도로관리청은 고속도로 진·출입 톨게이트 및 본선에 저속 WIM 또는 고속 WIM을 설치하여 과적차량을 단속하고 있으나, 근래 과적 화물차가 가변축을 불법 조작하여 도로관리청의 과적차량 단속시스템을 지능적으로 회피하는 운행이 증가하고 있다. 과적 검문소 진입 시에는 차축을 모두 내려 정상 통과하고 본선 주행 시에는 가변축을 불법으로 들어 축하중 10톤을 초과하여 과적 운행하는 방식이다. 이에 본 연구는 도로변에 차량 옆면 촬영 카메라를 설치하여 도로 주행 중인 화물차의 가변축 상태를 검지하는 기술을 개발하였다. 과적차량 검문소의 계중정보 연계 시 검문소 진출 후 차축을 들어 과적 운행하는 차량을 단속할 수 있는 기반기술이다. 제안기술은 제2서해안고속도로 송산마도IC~마도JC 구간 노변에서 취득된 영상을 학습데이터로 가공하고 Mask RCNN 알고리즘을 활용하여 타이어를 인식하였으며 인식된 타이어들을 배열하고 높이차를 측정하는 방식으로 타이어의 들림 여부를 판단하였다.
The Road Management Administration is cracking down on overloaded vehicles by installing low-speed or high-speed WIMs at toll gates and main lines on expressways. However, in recent years, the act of intelligently evading the overloaded-vehicle control system of the Road Management Administration by...
The Road Management Administration is cracking down on overloaded vehicles by installing low-speed or high-speed WIMs at toll gates and main lines on expressways. However, in recent years, the act of intelligently evading the overloaded-vehicle control system of the Road Management Administration by illegally manipulating the variable axle of an overloaded truck is increasing. In this manipulation, when entering the overloaded-vehicle checkpoint, all axles of the vehicle are lowered to pass normally, and when driving on the main road, the variable axle of the vehicle is illegally lifted with the axle load exceeding 10 tons alarmingly. Therefore, this study developed a technology to detect the state of the variable axle of a truck driving on the road using roadside camera images. In particular, this technology formed the basis for cracking down on overloaded vehicles by lifting the variable axle after entering the checkpoint and linking the vehicle with the account information of the checkpoint. Fundamentally, in this study, the tires of the vehicle were recognized using the Mask RCNN algorithm, the recognized tires were virtually arranged before and after the checkpoint, and the height difference of the vehicle was measured from the arrangement to determine whether the variable axle was lifted after the vehicle left the checkpoint.
The Road Management Administration is cracking down on overloaded vehicles by installing low-speed or high-speed WIMs at toll gates and main lines on expressways. However, in recent years, the act of intelligently evading the overloaded-vehicle control system of the Road Management Administration by illegally manipulating the variable axle of an overloaded truck is increasing. In this manipulation, when entering the overloaded-vehicle checkpoint, all axles of the vehicle are lowered to pass normally, and when driving on the main road, the variable axle of the vehicle is illegally lifted with the axle load exceeding 10 tons alarmingly. Therefore, this study developed a technology to detect the state of the variable axle of a truck driving on the road using roadside camera images. In particular, this technology formed the basis for cracking down on overloaded vehicles by lifting the variable axle after entering the checkpoint and linking the vehicle with the account information of the checkpoint. Fundamentally, in this study, the tires of the vehicle were recognized using the Mask RCNN algorithm, the recognized tires were virtually arranged before and after the checkpoint, and the height difference of the vehicle was measured from the arrangement to determine whether the variable axle was lifted after the vehicle left the checkpoint.
Enforcement Decree of the Road Act, Enforcement Decree of the Road Act(2022), Article 80, Interference with Measuring Loads, Korean Law Information Center.
Girshick, R., Donahue, J., Darrell, T. and Malik, J.(2014), "Rich feature hierarchies for accurate object detection and semantic segmentation", Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp.580-587.
Han, J. H. and Hong, S. S.(2020), "Semiconductor Process Inspection Using Mask R-CNN", Journal of the Semiconductor & Display Technology, vol. 19, no. 3, pp.12-18.
He, K., Gkioxari, G., Dollar, P. and Girshick, R.(2017), "Mask r-cnn", Proceedings of the IEEE International Conference on Computer Vision, pp.2961-2969.
He, K., Zhang, X., Ren, S. and Sun, J.(2016), "Deep residual learning for image recognition", Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp.770-778.
Oh, M. S., Kwon, S. M. and Oh, C.(2018), "Analyzing the Impact of Weigh-in-Motion (WIM)-based Overloading Enforcement Systems on Freeway Traffic Stream", International Journal of Highway Engineering, vol. 20, no. 5, pp.129-140.
Redmon, J., Divvala, S., Girshick, R. and Farhadi, A.(2016), "You only look once: Unified, real-time object detection", Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp.779-788.
Road Act Enforcement Decree(2022), Article 79 Vehicle Operation Restriction, etc., National Law Information Center.
SBS News, https://news.sbs.co.kr/news/endPage.do?news_idN1005159046&oaidN1005159979&plinkTEXT&cooperSBSNEWSEND, 2022.06.01.
Zhao, X. X., Shi, M., Ren, P., He, R., Wei, X. and Yang, H.(2022), "Crack Detection and Comparison Study Based on Faster R-CNN and Mask R-CNN", Sensors, vol. 22, no. 3, p.1215.
AI-Helper
※ AI-Helper는 부적절한 답변을 할 수 있습니다.