Vehicle inspection at ports of entry is a critical component of border security. One part of the vehicle screening process involves customs and border protection (CBP) personnel performing a preliminary inspection of the underside of random vehicles by looking under the vehicle through a mirror mounted on a stick, searching for anomalies or foreign objects present on the undercarriage structure and components of a vehicle. If any deviances are detected, the vehicle is directed to a secondary and more thorough inspection. This paper presents a project that aims at automating this preliminary undercarriage inspection by using an automatic under-vehicle inspection system (AUVIS) and image processing algorithms to assist personnel in identifying vehicles for secondary inspection. The inspection system will image the undercarriage of every car in a lane as they approach the CBP agent and use a novel change detection algorithm to compare the captured image to a corresponding reference image of the vehicle's make and model. The software will detect and highlight any differences between the two images to provide a rapid and objective recommendation for secondary inspection.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.