一种基于DEIM-FC的马铃薯捡拾机用产量估测方法
By using a yield estimation method for potato pickers based on the DEIM-FC algorithm, the three-dimensional information and quality of potatoes can be identified and calculated in real time. This solves the problems of high estimation cost and low accuracy in existing technologies, and achieves efficient and accurate potato yield estimation.
CN121121735BActive Publication Date: 2026-07-17QINGDAO AGRI UNIV
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- QINGDAO AGRI UNIV
- Filing Date
- 2025-11-12
- Publication Date
- 2026-07-17
AI Technical Summary
Technical Problem
Existing potato yield estimation methods suffer from high estimation costs and low accuracy due to numerous estimation variables.
Method used
A yield estimation method for potato pickers based on the DEIM-FC algorithm is adopted. The method involves real-time image acquisition, preprocessing, and then using the DEIM-FC algorithm to identify potatoes. A depth camera is used to obtain three-dimensional information, and the potato quality is calculated by combining the bytetracker target tracking algorithm to achieve simultaneous yield estimation.
Benefits of technology
This technology enables rapid and accurate estimation of potato yield on potato pickers, reducing estimation costs and improving the accuracy and efficiency of yield forecasting.
✦ Generated by Eureka AI based on patent content.
Smart Images
Figure CN121121735B_ABST
Abstract
本发明提供了一种基于DEIM‑FC的马铃薯捡拾机用产量估测方法，该方法基于DEIM‑FC算法提出一种适应于马铃薯产量估测场景的DEIM‑FC模型，该模型轻量化、检测速度快，能够快速的进行马铃薯的识别；通过深度相机获取完成识别的马铃薯的三维信息，预测马铃薯的体积，并计算每个马铃薯的质量，最终获得预测的马铃薯的产量；该方法能够实现在马铃薯捡拾机上的部署，随着马铃薯捡拾工作的进行，同步估测马铃薯产量，有效降低产量估算成本，同时预测变量少，可以高精度地快速预测马铃薯的产量。
Need to check novelty before this filing date? Find Prior Art