Truck Monitoring Meets Computer Vision and Artificial Intelligence

There has been a great deal of interest in improving over-the-road truck tracking using IoT technology. Some of these systems use the driver’s smartphone and a microcontroller based on GPS/GSM/GPRS technology. The GPS is great at capturing geographic coordinates while the GSM/GPRS updates the vehicle location to a database.1

There are limitations to GPS and related technologies. While good at locating a vehicle’s road location, they lack the granularity to precisely track vehicle within a facility – yard entry/exit, weigh stations, loading/unloading dock. They also lack the ability to watch the action in a yard like a set of human eyes. Computer vision is an ideal means to replace human eyes and complement GPS within yards, depots, and distribution centers.

New computer vision systems use inexpensive mini computers and cameras that are easy to install and provide their own cellar connection to the cloud for real-time reporting and alerting. They watch all the action by reading the license plate and DOT numbers, reading scale weights, and capturing cycle the times from station to station.

Unlike security cameras that require humans to review hours’ worth of images, these new computer vision systems use artificial intelligence to only signal events of interest or concern – foreign materials inside an empty van, debris in the bed of dump truck, a person not wearing a hard hat in a designated area, a vehicle left unattended for an extended period of time.

An example screenshot below captures real-time monitoring of a truck terminal. Each vehicle is logged in automatically by reading its license plate. Its total time in the yard and the number of daily trips are also displayed. Unlike GPS-based systems, computer vision tracks all vehicles in a facility, not just your fleet of vehicles.

The need for a guard to log trucks into and out of a facility is eliminated with a digital guard which never blinks or takes breaks, working 24 hours a day. Such systems are trained to work in all types of lighting and atmospheric conditions and can be easily installed without IT support.

Passive and unobtrusive computer vision combined with real-time monitoring are working at a wide variety of facilities – both inside and outside. It is truly the next generation of vehicle monitoring regardless of the type, size, or ownership of vehicle – from forklifts, to dump trucks, to tractor trailers. Many users report discovering insights and seeing benefits in the first week of operation.

1. “IEEE WF-IoT Session: Design and Implementation of Vehicle Tracking System Using GPS/GSM/GPRS Technology and Smartphone Application,” Girma Tewolde, Kettering University, USA; SeokJu Lee, Kettering University, USA; Jaerock Kwon, Kettering University, USA https://iot.ieee.org/conferences-events/wf-iot-2014-videos/28-ieee-wf-iot-session-design-and-implementation-of-vehicle-tracking-system-using-gps-gsm-gprs-technology-and-smartphone-application.html

Author:

Anthony Tarantino, PhD
Adjunct Professor, Santa Clara University – Operations and Finance
Six Sigma Master Black Belt, Certified Scrum Master, CPIM (APICS), CPM (ISM)
Senior Advisor to Atollogy for Alliances and University Relations
Tony@atollogy.com