Moving toward smart breeding: A robust amodal segmentation method for occluded Oudemansiella raphanipes cap size estimation

变数知觉 估计 分割 人工智能 计算机视觉 计算机科学 模式识别(心理学) 统计 数学 工程类 生物 认知 神经科学 系统工程
作者
Hua Yin,Wei Quan,Yang Gao,Haijing Hu,Yinglong Wang
出处
期刊:Computers and Electronics in Agriculture [Elsevier BV]
卷期号:220: 108895-108895 被引量:10
标识
DOI:10.1016/j.compag.2024.108895
摘要

High-throughput acquisition of phenotypic parameters based on machine vision is important for intelligent breeding, digital cultivation and automated harvesting of Oudemansiella raphanipes. However, due to the occlusion among Oudemansiella raphanipes in the growing bed, it is challenging to accurately and rapidly capture their full shape with conventional methods, resulting in a low measurement success rate. The overall goal of this study is to propose a deep learning-based method (Oudemansiella raphanipes Occlusion Region-based Convolutional Neural Networks, OR-ORCNN) to obtain the morphology of occluded Oudemansiella raphanipes precisely in the mushroom growing bed with high efficiency. To accomplish this, a state-of-the-art attention architecture (OR-SE), which consists of CCA (Criss-Cross Attention) and MSF (Multiscale Fusion) modules, was applied to the deocclusion assignment. Then, the predicted amodal mask combined pinhole camera model was used to compute the size of Oudemansiella raphanipes caps in millimeters (mm). The experimental results showed an improvement in the AP50 of 2.78 % and mAR of 5.60 % compared with the baseline model, demonstrating the effectiveness of the OR-SE module in improving the feature information capability of backbone networks. Meanwhile, the Oudemansiella raphanipes cap size estimation results reported an MAE of 0.93 mm and a MAPE of 4.96 %. Furthermore, to confirm the robustness and generalizability of the OR-ORCNN model, we also conducted experiments on Agrocybe cylindraceas and obtained satisfactory results. In summary, the proposed algorithm provides an effective way to recover the shape of the occluded region of Oudemansiella raphanipes with high efficiency and precision, which can be used to help researchers breed intelligently and growers optimize management.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
星辰大海的应助被上官小怡采纳,获得10
刚刚
酷波er的应助被朴素毛豆采纳,获得10
刚刚
刚刚
ZM关闭了ZM的文献求助
刚刚
元吉的应助被迪迪张采纳,获得10
刚刚
Orange的应助被包子采纳,获得10
刚刚
秋风的应助被shufei采纳,获得10
1秒前
1秒前
1秒前
tianzhen完成签到,获得积分10
1秒前
DDD完成签到,获得积分10
1秒前
YMing发布了新的文献求助10
1秒前
陈HT完成签到,获得积分10
1秒前
回忆lhy完成签到,获得积分10
2秒前
星月夜完成签到,获得积分10
2秒前
Lucas发布了新的文献求助10
2秒前
3秒前
3秒前
floraya完成签到,获得积分10
3秒前
4秒前
4秒前
Patman发布了新的文献求助10
4秒前
余香的应助被yjh采纳,获得10
4秒前
文静凝旋完成签到,获得积分10
4秒前
Owen的应助被认真连虎采纳,获得10
5秒前
5秒前
楚司遥完成签到,获得积分10
5秒前
5秒前
pinst7完成签到,获得积分10
6秒前
易瑾完成签到 ,获得积分10
6秒前
DW的应助被悦耳的尔冬采纳,获得10
6秒前
luoll发布了新的文献求助10
6秒前
6秒前
科研通AI2S的应助被111采纳,获得10
6秒前
7秒前
7秒前
张天虹完成签到,获得积分10
7秒前
zcydbttj2011完成签到 ,获得积分10
7秒前
7秒前
piglet完成签到,获得积分10
7秒前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
拉伸高分子熔体中缠结行为的模拟和小角中子散射研究 1700
The World Atlas of Wine 9th edition 1000
奈特基础组织学:配套组织病理学(第4版)(Netter's Essential Histology With Correlated Histopathology) 800
John McDowells Bildungstheorie 800
Social Psychology in the Real World 600
八旗制度の研究 600
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 计算机科学 工程类 有机化学 化学工程 生物化学 物理 复合材料 内科学 催化作用 光电子学 人工智能 细胞生物学 无机化学 物理化学 数学
热门帖子
关注 科研通微信公众号,转发送积分 8180807
求助须知:如何正确求助?哪些是违规求助? 9570895
关于积分的说明 21815089
捐赠科研通 7777155
什么是DOI,文献DOI怎么找? 3433347
关于科研通互助平台的介绍 2557613
邀请新用户注册赠送积分活动 2479317