Method of mapping bulk material in bunker using machine learning

By using depth map capture sensors and deep convolutional neural networks, the problem of difficulty in distinguishing between the storage silo wall and the surface of bulk materials in existing technologies is solved, and accurate monitoring and mapping of bulk materials is achieved.

CN120712460APending Publication Date: 2025-09-26BINSENTRY INC
1 Cites 0 Cited by

Patent Information

Application Number
CN202480013071.7
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Priority Date
2023-02-17
Filing Date
2024-01-23
Publication Date
2025-09-26

AI Technical Summary

Technical Problem

It is difficult to accurately distinguish between the wall of the storage silo and the surface of the bulk material in the existing technology, which limits the accuracy of bulk material monitoring in the silo.

Method used

A depth map capture sensor such as a time-of-flight camera is used to capture the topological structure image of the bulk material, and an AI model that can distinguish between the wall and the surface of the bulk material is developed by training an artificial neural network. The image data is then processed using a deep convolutional neural network to achieve accurate distinction.

Benefits of technology

It achieves accurate distinction between bulk materials and walls in the silo, improving the accuracy and precision of bulk material monitoring in the silo.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

A method for mapping bulk material in a storage silo having a wall for containing bulk material is disclosed. The method includes capturing a plurality of training images of various topologies of bulk material in a storage bin using a depth map capture sensor, such as a time-of-flight camera, each of the plurality of training images defined by an array of pixels. An artificial neural network is trained on the plurality of training images to develop an artificial intelligence model capable of distinguishing the wall from the surface of the bulk material. The method further includes capturing one or more images of the bulk material to be mapped in the bunker or another similarly shaped bunker using a depth map capture sensor, such as a time-of-flight camera, and then mapping the bulk material in the bunker or another similarly shaped bunker using an artificial intelligence model, in this way, the bulk material and the wall in the silo or another similarly shaped silo can be distinguished.
Need to check novelty before this filing date? Find Prior Art