Vehicle Type and Color Classification and Detection for Amber and Silver Alert Emergencies Using Machine Learning

Abstract

The National Center for Missing & Exploited Children estimated that 161 AMBER Alerts were issued in the U.S. involving 203 children in 2018, where 85% had involved vehicles and in Florida, 136 Silver Alerts were issued in 2008-2009. The details of broadcasting in Amber and Silver alerts are color, type of the vehicle, vehicle license plate numbers, and car brands. This paper is focused on classifying and detecting vehicle types, colors, and license plates. Currently, a child and older adult were rescued when someone recognized the vehicle in the alert. This paper proposes to design a Machine Learning model to classify the vehicle’s colors, types and recognize each vehicle’s license plate from camera feeds under different weather conditions and to find possible matches involved in these emergency alerts for the safe return of a child and older adult. Vehicle types include seven classes such as SUV, Sedan, Truck, Bus, Microbus, Minivan, and Motorcycle. Vehicle colors include eight classes: green, blue, black, white, gray, yellow, white, and red. When an Amber or Silver signal is broadcast, the proposed design checks with the vehicle’s specifications and extracts the color and type of the vehicle. The model then recognizes the vehicle’s license plate of specific vehicle’s color and type using image processing techniques and give notification of detected vehicle. Implementing CNN, real-time object detector YOLO, and character recognition model will improve detection and classify vehicle’s type, color, and recognize license plate numbers and letters accurately under different environmental conditions for Amber and Silver alert emergencies.