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.

CN116395299BActive Publication Date: 2025-09-23ZHEJIANG LIANYUN ZHIHUI TECH CO LTD
View PDF 2 Cites 0 Cited by

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

Technical Problem

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.

Method used

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.

Benefits of technology

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.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN116395299B_ABST
    Figure CN116395299B_ABST
Patent Text Reader

Abstract

The present application relates to the technical field of trash cans, and in particular to an AI-based method and device for detecting the placement of domestic waste and renewable resources. Current image data is acquired, and the current image data is processed using an affine transformation operation to obtain corrected image data. The mouth of the bucket is tracked according to the corrected image data, and whether the mouth of the bucket moves is determined based on the result of the target tracking. If it moves, the motion state of the mouth of the bucket at the current moment is determined based on the corrected image data. When the motion state of the mouth of the bucket is stationary, the current position of the mouth of the bucket is acquired, and the area corresponding to the current position of the mouth of the bucket is determined as the target monitoring area, and the target monitoring area is centered on the current position of the mouth of the bucket. Tracking and detection of mobile trash cans can be achieved, the management effect of trash cans can be optimized, the cleanliness of residential communities can be improved, and it is more conducive to the construction of civilized cities.
Need to check novelty before this filing date? Find Prior Art

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