Grape stem detection using regression convolutional neural networks

卷积神经网络 人工智能 计算机科学 回归 机器学习 修剪 分割 模式识别(心理学) 特征提取 数学 统计 农学 生物
作者
Τheofanis Kalampokas,Εleni Vrochidou,George A. Papakostas,Theodore P. Pachidis,Vassilis G. Kaburlasos
出处
期刊:Computers and Electronics in Agriculture [Elsevier BV]
卷期号:186: 106220-106220 被引量:50
标识
DOI:10.1016/j.compag.2021.106220
摘要

• A novel vision-based grape stem detection methodology. • A methodology robust to imbalanced data is introduced. • New regression CNN models derived from the combination of known CNN architectures are proposed. • The proposed methodology outperforms the state of the art methods in terms of accuracy. Automation of grapevine agricultural tasks, e.g., harvesting, requires reliable methods for detecting the exact cutting points of the grape bunches. Dynamically changing vineyard environments, differences between plant varieties, illumination, occlusion, color similarities, and varying contrast make the detection of the grapes’ stems in unstructured environments difficult. In this work, a grape stem detection methodology in images is proposed, towards introducing an autonomous grape harvesting robot (ARG), as an affordable and consistent alternative to the time-consuming specialized work of an experienced harvester. For this purpose, a regression convolutional neural network (RegCNN) is applied for executing a stem segmentation task. Twelve Convolutional Neural Network (CNN) model architectures derived by the combination of three different feature learning sub-networks with four meta-architectures, are investigated. For the first time, stem detection is tackled as a regression problem in a way to alleviate the imbalanced data phenomenon that may occur in vineyard images. In order to justify the effectiveness of the RegCNN models, the same CNN architectures are tested in a typical classification (ClaCNN) setup. Comparative results involving two datasets with different characteristics reveal that the regression models outperform the classification ones. Grape bunches stems are detected with an Intersection-over-Union (IU) performance of up to 98.18% with RegCNNs, before post-processing optimization. Moreover, by applying a Genetic Algorithm (GA)-based parameter tuning mechanism, optimized post-processing parameters lead to an improved IU accuracy of up to 98.90% for the UNET_MOBILENETV2 model with acceptable real-time performance. Compared to other similar methodologies, the proposed method provides higher correct stem detection rates in unconstrained and highly changing environments, e.g., vineyards, and thus it is appropriate for robust real-time stem identification towards facilitating the agricultural tasks executed by a robot harvester.

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
liu发布了新的文献求助10
刚刚
天天快乐的应助被senger采纳,获得10
刚刚
小羊发布了新的文献求助10
刚刚
秋风的应助被yyy采纳,获得10
刚刚
刚刚
1秒前
1秒前
1秒前
冀丂完成签到,获得积分10
1秒前
lnix完成签到,获得积分10
1秒前
1秒前
一线科研工作者完成签到,获得积分10
1秒前
1秒前
2秒前
Jun的应助被火星上书琴采纳,获得10
2秒前
2秒前
瘦瘦发布了新的文献求助10
2秒前
飞翔868发布了新的文献求助10
3秒前
wang完成签到,获得积分10
3秒前
猪猪hero发布了新的文献求助10
3秒前
3秒前
linjong完成签到,获得积分20
3秒前
lzy发布了新的文献求助10
4秒前
小恶于发布了新的文献求助10
4秒前
冀丂发布了新的文献求助10
4秒前
隐形曼青的应助被young采纳,获得10
4秒前
5秒前
Lex发布了新的文献求助10
5秒前
科研通AI65的应助被ZLQ采纳,获得10
6秒前
彩色秋蝶完成签到 ,获得积分10
6秒前
yumi发布了新的文献求助10
6秒前
两根元完成签到,获得积分10
7秒前
多美发布了新的文献求助10
7秒前
毛毛发布了新的文献求助10
7秒前
7秒前
zzyyhh完成签到,获得积分10
7秒前
biu完成签到 ,获得积分10
8秒前
8秒前
xide完成签到,获得积分10
8秒前
8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
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
八旗制度の研究 600
plantTFDB 508
高分子基功能界面水蒸发材料与应用研究 500
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 8176481
求助须知:如何正确求助?哪些是违规求助? 9567855
关于积分的说明 21795109
捐赠科研通 7771163
什么是DOI,文献DOI怎么找? 3432027
关于科研通互助平台的介绍 2556365
邀请新用户注册赠送积分活动 2477695