The demand for a secure lifestyle and travel is increasing due to the rapid development of technology. Since the turn of the century, the number of road vehicles has risen dramatically. The rapid growth of the vehicular sector makes tracking individual vehicles increasingly difficult. In this work, a novel proposed YOLO-VEHICLE has been introduced to detect the licence plate in the highway using Yolov7 network. Initially, a CCTV camera captures the input highway traffic video. The collected video is converted into frames. The frames are detected the license plate using the YOLOv7 network. The detected Licence plates (LP) are segmented for partitions a digital image into discrete groups of pixels using U-Net. Finally, the segmented LP recognizing the character for clear view. The simulation outcomes show the performance is assessed by using the accuracy reached by the proposed YOLO-VEHICLE method, as well as its accuracy (ACU), precision (PRE), recall (RCL), and F1 score (F1S). According to the results, the proposed network accuracy was 99.59 %. In the comparison, the YOLOv7 network improves the overall accuracy of the YOLOv3, YOLOv4, and YOLOv5 is 95.14%, 96.32%, and 97.36% respectively. The YOLO-VEHICLE approach improves the overall accuracy of 13.37%, 2.13%, 14.03% better than edge intelligence-based enhanced YOLOv4, Faster R-CNN, and recognition system respectively.