温室作物三维重建与生长信息获取方法研究
项目来源
国（略）科（略）(（略）C（略）
项目主持人
蒋（略）
项目受资助机构
浙（略）
立项年度
2（略）
立项时间
未（略）
项目编号
3（略）0（略）
项目级别
国（略）
研究期限
未（略） （略）
受资助金额
6（略）0（略）
学科
生（略）-（略）-（略）研（略）技（略）方（略）
学科代码
C（略）2（略）2（略）
基金类别
面（略）
关键词
活（略） （略）度（略）;（略）三（略）技（略） （略）测
参与者
俞（略）容（略）乐（略）囡（略）萍（略）；（略）
参与机构
未（略）
项目标书摘要：我国（略）施农业生产大国，设（略）界第一。及时掌握作（略）业生产具有重要意义（略）ct作为温室作物信（略）比和光环境等农艺优（略）信息高精度获取方法（略）时、动态作物生长信（略）移动监测平台，研究（略）重建方法；针对作物（略）模方法，使之对同类（略）普适性；结合深度学（略）、准确、高分辨率的（略）分割方法，并在分割（略）的自动获取；在大量（略）取形态参数的模型进（略）含水率、生物量等非（略）可提取参数的相关性（略），实现作物参数的自（略），为温室内水肥管理（略）准确的作物信息
Applicati（略）: China i（略）ry of fac（略）ulture wi（略）e cultiva（略） mainstay（略）f agricul（略）ities and（略）egetables（略）the first（略）toring pl（略）ation can（略） plants g（略） efficien（略）s importa（略）to scient（略）lture pro（略）s,design （略）latform f（略）es with t（略）l require（略）icultural（略） via Kine（略）ry necess（略）roject ai（略）ng high-p（略）ant infor（略）ugh Kinec（略）lative re（略）ke agricu（略）ement and（略）ilizer pr（略） optimiza（略）dering th（略）oduction （略）s project（略）n a movab（略）ng platfo（略）n get rea（略）rmation,a（略） a new an（略） 3D-recon（略）ethod for（略）ts in gre（略）bined the（略）ants’shap（略）his proje（略）imize thi（略）truction （略）ake it su（略）same clas（略）s.Combine（略）-learning（略）,we desig（略）ent,preci（略）olution a（略）ation alg（略）et part l（略）ants.Then（略）informati（略）lants aut（略）Last at a（略）f experim（略）e done to（略）ction and（略）on of the（略） features（略）lly.The r（略）tween mor（略）tures and（略）logy feat（略）nts such （略）water con（略）omass,wil（略）ed as wel（略）ect aims （略）automatic（略）ring syst（略）t informa（略）vide accu（略）able plan（略）rameters （略）ertilizer（略） and agri（略）eration i（略）e.
项目受资助省
浙（略）
项目结题报告(全文)
基于三维视觉系统的（略），实时监测作物全生（略），借助自动化和智能（略）与生长信息管理系统（略）的农业生产具有重要（略）度相机作为主要的信（略）验室场景、玻璃温室（略）对单株作物和群体作（略）使用场景的差异优化（略）重建平台。将平台搭（略）实现设施温室、植物（略）模型的自动化获取。（略）觉系统、三维几何学（略）模型分割问题上的表（略）于二维图像的作物分（略）定性以及时效性上均（略）方法。基于作物的形（略）导致的三维模型缺陷（略）型上提取的生长参数（略）度相关，并且总叶面（略）重、干重的测量值相（略）物量的估计。搭建作（略）了数据采集、处理、（略）系统包含了作物三维（略）生长信息管理，可以（略）作物信息，为温室内（略）产等提供准确的作物（略）
1. Type: Other Status: Published Year Published: 2022 Citation: Zalapa J, Russo J, Atucha A. 2022. VaCTrait: Color in cranberries. April 5, 2022 Status: Online (https://www.vacciniumcap.org/sites/default/files/inline-files/Vactrait%20Color %20in%20Cranberries.pdf ). Handout
2.Review on Convolutional Neural Network (CNN) Applied to Plant Leaf Disease Classification
Crop production can be greatly reduced due to various diseases, which seriously endangers food security. Thus, detecting plant diseases accurately is necessary and urgent. Traditional classification methods, such as naked-eye observation and laboratory tests, have many limitations, such as being time consuming and subjective. Currently, deep learning (DL) methods, especially those based on convolutional neural network (CNN), have gained widespread application in plant disease classification. They have solved or partially solved the problems of traditional classification methods and represent state-of-the-art technology in this field. In this work, we reviewed the latest CNN networks pertinent to plant leaf disease classification. We summarized DL principles involved in plant disease classification. Additionally, we summarized the main problems and corresponding solutions of CNN used for plant disease classification. Furthermore, we discussed the future development direction in plant disease classification.
...3.A Convolutional Neural Network-Based Method for Corn Stand Counting in the Field.
- 关键词：
- ;
Accurate corn stand count in the field at early season is of great interest to corn breeders and plant geneticists. However, the commonly used manual counting method is time consuming, laborious, and prone to error. Nowadays, unmanned aerial vehicles (UAV) tend to be a popular base for plant-image-collecting platforms. However, detecting corn stands in the field is a challenging task, primarily because of camera motion, leaf fluttering caused by wind, shadows of plants caused by direct sunlight, and the complex soil background. As for the UAV system, there are mainly two limitations for early seedling detection and counting. First, flying height cannot ensure a high resolution for small objects. It is especially difficult to detect early corn seedlings at around one week after planting, because the plants are small and difficult to differentiate from the background. Second, the battery life and payload of UAV systems cannot support long-duration online counting work. In this research project, we developed an automated, robust, and high-throughput method for corn stand counting based on color images extracted from video clips. A pipeline developed based on the YoloV3 network and Kalman filter was used to count corn seedlings online. The results demonstrate that our method is accurate and reliable for stand counting, achieving an accuracy of over 98% at growth stages V2 and V3 (vegetative stages with two and three visible collars) with an average frame rate of 47 frames per second (FPS). This pipeline can also be mounted easily on manned cart, tractor, or field robotic systems for online corn counting.
...