Automated License Plate Recognition on Law Enforcement Vehicles
Overview
The automated license plate recognition (ALPR) system help law enforcement to detect and find stolen or vehicles in question.
The use of technology to aid in fighting crime can be something simple from a dipstick test to something advanced and complicated, such as DNA matching. In the automated license plate recognition application, police with bodycam and vehicle (car or motorcycle) mounted with cameras, coupled with recognition software, allows the system can read multiple license plates in a single view. The data is initially checked against a smaller edge database (stored on police vehicles) for recently reported license plates while the processed edge data can later be uploaded back onto the server to be crosschecked with the backlogged database.
The system brings safety to law enforcement personnel as they can perform the checks undetected and it does not set off alarms for the perpetrator.
Challenges
The camera placements can be placed inside or on top of the vehicles. Though mounting on top is preferred as it gets a better view for license plate scanning. This means the cameras need to operate in outdoor environments, where lighting conditions are a factor, and also the rain can affect its operations, so the cameras need to be waterproof. While the DVR or onboard computer needs to be able to withstand in-vehicle environments, such as elevated operating temperatures, confined space, shock and vibration.
Solution
To have a system that can operate in in-vehicle conditions and have cameras operate in various lighting conditions while in the rain, our customer chose to utilize the Neousys NRU series edge computers. It supports GMSL cameras that have IP67 waterproof characteristics, high dynamic range (>120dB HDR), auto white balance (AWB), and LED flickering mitigation (LFM), and is not affected by lighting conditions, sunny, overcast or in the dark. The NRU series edge computer is powered by NVIDIA Jetson AGX Xavier that offers TFLOPS inference performances, perfect for image recognition applications.
The NRU series systems are also tested to be compliant with MIL-STD-810G to withstand shock and vibration conditions of a moving vehicle; are compact that can fit into confine space installations; come with ignition power control to protect the computer from power surges at startups; and offer true wide temperature operation capabilities.
