一种轻量化的动态体积测量方法及系统
By combining RGB and depth cameras with clustering algorithms in an end-to-end deep learning approach, the real-time performance, accuracy, and cost control issues of dynamic volume measurement in existing technologies have been solved. This approach enables efficient and accurate volume measurement of high-speed moving packages and is suitable for logistics and warehousing automation.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- GUANGZHOU GENYE INFORMATION TECH
- Filing Date
- 2025-07-24
- Publication Date
- 2026-07-17
AI Technical Summary
Existing dynamic volume measurement technologies have shortcomings in terms of real-time performance, accuracy, and cost control. In particular, the measurement accuracy and stability in complex environments such as high speed, reflective light, and low light cannot meet industrial needs, and the ability to segment instances in cases of multiple targets sticking together or stacking is insufficient.
The system uses RGB and depth cameras to acquire package images, combines clustering algorithms for package segmentation, and directly outputs package images and calculates volume using an end-to-end deep learning method, reducing the number of sensors and optimizing the algorithm structure.
It enables real-time, high-precision volume measurement of high-speed moving packages, reduces system cost and deployment difficulty, and improves segmentation robustness in low light noise and multi-target adhesion and stacking scenarios.
Smart Images
Figure CN120580447B_ABST