AI-based detection method and equipment for domestic waste and renewable resources delivery
By performing affine transformation and target tracking on the image data of the trash can mouth, combined with non-negative matrix decomposition and watershed segmentation algorithms, the monitoring area is dynamically adjusted, solving the problem of monitoring loss caused by changes in the position of the trash can mouth, and improving the trash can management effect and the cleanliness of the living community.
Patent Information
- Application Number
- CN202310288897.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2023-03-21
- Publication Date
- 2025-09-23
- Estimated Expiration
- 2043-03-21
AI Technical Summary
The position of the existing trash can openings changes frequently, which makes it impossible for image acquisition equipment to continuously monitor, affecting the management of the trash cans and reducing the cleanliness of residential communities.
Affine transformation operations are used to process image data, correct the position of the barrel mouth, and determine the motion state of the barrel mouth through target tracking. The monitoring area is dynamically adjusted to track the position of the barrel mouth. The barrel mouth detection is optimized by combining non-negative matrix decomposition and watershed segmentation algorithm.
It realizes the continuous tracking and accurate monitoring of the bin opening, improves the management effect of the garbage bin, improves the cleanliness of the living quarters, and is conducive to the construction of civilized cities.
Smart Images

Figure CN116395299B_ABST
Abstract
Citation Information
Patent Citations
Garbage can overflow state detection method and device, storage medium and electronic equipment
CN113642509A
Garbage throwing point monitoring method, device and system and storage medium
CN115767021A