1. LV-YOLO: logistic vehicle speed detection and counting using deep learning based YOLO network.
- Author
-
Rani, N. Gopika, Priya, N. Hema, Ahilan, A., and Muthukumaran, N.
- Abstract
In the era of smart cities and advancing transportation technologies, predicting logistic vehicle and vehicle speed is pivotal to enhancing traffic management, safety, and overall transportation efficiency. Properly predicting vehicle and vehicle speed is critical to the interests of both road users and traffic authorities. However, accurately predicting the vehicle speed and logistics vehicle of a single trip is a difficult task. In some cases, unpredicted accidents will happen, so death cases will increase. To overcome these issues, a novel Logistic Vehicle speed detection using the YOLO (LV-YOLO) method has been introduced to detect logistical vehicles and speed using the YOLO network. The proposed framework is divided into three layers such as image acquisition, segmentation layer, and detection layer. In the image acquisition layer, a CCTV camera captures highway traffic video. The collected video is converted into frames. In the segmentation layer, the video frame is segmented using U-Net, which segments the vehicle in the video frames. The detection layer performs truck detection, and speed detection using LV-YOLO on segmented frames based on the Boxy Vehicle dataset. The simulated results show that the LV-YOLO technique maintains excellent mAP levels of 99.42%. The LV-YOLO improves the overall mAP by 1.72, 5.42, and 0.82% better than the Simple Vehicle Counting System, Real-Time Detection, and Advance YOLOv3 Model for vehicle detection, 4.81, and 2.63% better than Deep Learning and CAN protocol, and 1D-CNN speed estimation mode for speed prediction respectively. [ABSTRACT FROM AUTHOR]
- Published
- 2024
- Full Text
- View/download PDF