United States Department of Transportation
i
Development of a Virtual Weigh-In-Motion System for Enhanced Pavement System Management
-
2022-10-24
[PDF-915.44 KB]
Details:
-
Creators:
-
Corporate Creators:
-
Corporate Contributors:
-
Subject/TRT Terms:
-
Publication/ Report Number:
-
Resource Type:
-
Geographical Coverage:
-
Edition:Draft Final Report 1/2/2020 - 8/14/2022
-
Corporate Publisher:
-
Abstract:Weigh-in-Motion (WIM) is a promising solution to regulate weight-related violations but has high installation and recurring maintenance costs. Also, the requirement of installing induction loops for vehicle presence detection may cause damage to pavement structure and lead to early deterioration of the pavement surface. Recently, virtual weigh-in-motion (V-WIM) techniques consisting of WIM scales, traffic surveillance videos, and other sensors have become a new technological trend that has attracted interest from state DOTs to deal with size and weight enforcement that reaches beyond the WIM’s conventional role in data collection. Accurate detection of the specific vehicle-type information to activate the WIM sensors is a major step for the V-WIM from roadside-captured images/videos containing vehicles. This project evaluated the machine learning–based You Only Look Once (YOLO) algorithm trained on a custom dataset as a potential automatic vehicle detection process to work on existing traffic surveillance videos/images as the vehicle sensor data source. The results showed that the trained model could detect vehicles close to the camera with high confidence. The findings and outcomes may support the development of viable and functional V-WIM as well as increase the applications of traffic surveillance videos in transportation infrastructure management.
-
Format:
-
Funding:
-
Collection(s):
-
Main Document Checksum:
-
Download URL:
-
File Type:
