A monocular three-dimensional object detection method, device, equipment and product
By acquiring two-dimensional center point and depth information through the CenterNet network model, three-dimensional center point and orientation angle are generated, which solves the problem of difficult detection of truncated objects in monocular 3D detection and realizes accurate detection of truncated objects and stable perception of close-range targets of vehicles.
Patent Information
- Application Number
- CN202111013230.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2021-08-31
- Publication Date
- 2025-11-07
- Estimated Expiration
- 2041-08-31
AI Technical Summary
Existing monocular 3D detection technology exhibits significant differences in visibility when detecting truncated objects, making it difficult to accurately obtain their 3D center point, resulting in poor detection performance.
By employing the CenterNet network model, the three-dimensional center point and orientation angle of the object to be detected are generated by acquiring the two-dimensional center point and depth information of the object, thereby achieving accurate detection of truncated objects.
It significantly optimizes the prediction performance of truncated objects in monocular 3D detection, improves the accuracy of vehicle near-range target perception, and can perform stable 3D detection of both normal and truncated objects.
Smart Images

Figure CN113887289B_ABST
Abstract
Citation Information
Patent Citations
Three-dimensional target detection system and method based on binocular vision
CN111563415A
Monocular three-dimensional object detection method and device based on decoupling truncation object
CN112712062A