Abstract
The present invention discloses an object recognition and anomaly detection system, comprising: at least one image capturing device configured to capture at least one raw image; at least one database configured to store a vehicle’s information; a signal trigger device connected to at least one processor, wherein the at least one processor is configured to execute instructions stored on a memory to: detect location and size of a license plate (104) in the at least one raw image using an artificial intelligence (AI) object detection model (102); determine an optimal location and target area for tracking the license plate (104) when the location and size of the license plate (104) are unchanged for a predetermined period; recognize the license plate number (106); repeat the detection and recognition steps for subsequent vehicles; analyze distribution of vehicle locations (150) to obtain a reference value (146); and compare changes in the reference value (146) with a predetermined threshold (148).
| Original language | English |
|---|---|
| Patent number | HK30115167 |
| Filing date | 10/01/25 |
| Publication status | Published - 2025 |