Lentinula edodes stick pollution identification system based on improved YoLoV5s
By introducing the CA attention mechanism and GSConv and GhostConv modules into the YoLoV5s model, the contamination identification system for shiitake mushroom spawn is optimized, solving the problems of low identification efficiency and low accuracy in the existing technology, and achieving efficient and accurate contamination identification.
CN116342930BActive Publication Date: 2026-03-24SHANDONG AGRICULTURAL UNIVERSITY
View PDF 0 Cites 0 Cited by
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2023-02-23
- Publication Date
- 2026-03-24
AI Technical Summary
Technical Problem
Existing technologies for identifying contamination in shiitake mushroom spawn have limitations such as low identification efficiency and low accuracy, especially in identifying some contaminated spawn. Furthermore, the high network complexity makes them unsuitable for real-time detection.
Method used
Based on YoLoV5s, the CA attention mechanism and GSConv and GhostConv modules are introduced to optimize the feature extraction and feature fusion networks, and the YoLoV5s-CGG model is constructed to improve recognition accuracy and efficiency.
Benefits of technology
It significantly improves the accuracy and efficiency of identifying contamination in shiitake mushroom spawn, reduces network complexity, and is suitable for real-time detection.
✦ Generated by Eureka AI based on patent content.
Smart Images
Figure CN116342930B_ABST
Abstract
The present application belongs to the field of shiitake mushroom stick pollution identification, and specifically relates to a shiitake mushroom stick pollution identification system based on an improved YoLoV5s. The present application aims to provide a shiitake mushroom stick pollution identification system based on an improved YoLoV5s. The present application is improved and optimized on the basis of YoLoV5s, and proposes a YoLoV5s-CGG shiitake mushroom stick pollution identification model. The model introduces a CA attention mechanism in the feature extraction network, highlights the features of the identified objects, and improves the accuracy of the stick pollution identification. In combination with the GSConv and GhostConv modules, the feature fusion network is optimized to ensure that the stick pollution identification accuracy is improved while the identification efficiency is improved. The method proposed in this paper is suitable for shiitake mushroom stick pollution identification during the shiitake mushroom stick cultivation process. It includes adding a CA (Coordinate Attention) attention mechanism to the feature extraction network of YoLoV5s to improve the recognizability of the stick pollution and the accuracy of the target positioning.
Need to check novelty before this filing date? Find Prior Art