Object detection method and apparatus
By dividing the image sequence into sub-image sequences and performing background modeling, the problem of background modeling algorithms being affected by interference factors is solved, thereby improving the accuracy of object detection and the ability to detect static targets.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- LENOVO (BEIJING) LTD
- Filing Date
- 2023-03-29
- Publication Date
- 2026-05-26
AI Technical Summary
Background modeling algorithms are easily affected by factors such as object movement or people standing still in image sequences, leading to errors in background generation and affecting the accuracy of object detection.
By dividing the image sequence into sub-image sequences, background modeling is performed based on the pixel feature information within the sub-image sequences, reducing the impact of interference factors on background recognition, and the background modeling algorithm is updated using an object detection model.
It improves the accuracy of background recognition and the precision of object detection, reduces background modeling errors, and enhances the ability to detect static target objects.
Smart Images

Figure CN116342890B_ABST