16AGRITECHCAT5: GrassVision: Automated application of herbicides to broad-leaf weeds in grass crops

本项目的目的是研制一种新型的除草剂精确喷洒装置，用于对禾本科作物中的阔叶杂草进行精确喷洒。这种系统使用覆盖10x.5米地面面积的喷洒杆，可以以1米/秒以上的速度运行，允许以1至2公顷/小时的速度精确喷洒杂草。（1）机器视觉中心（CMV），3D机器视觉领域的领先研究中心，过去在农业技术领域取得了成功，（2）Aralia Systems Ltd（AS），一家国际安全公司，在数据挖掘和视频复杂特征分析方面拥有广泛的研发组合，（3）Soil Essentials Ltd（SE），一家领先的精准农业公司，专门从事GPS机械导航，机具控制，基于云的决策支持系统和新兴的草地农学技术。主要重点将是使用新型3D机器视觉检测草中的杂草，如船坞和豚草技术.最初，该项目将使用现成的机械设备在每棵杂草周围喷洒大约50 x50厘米的区域，激活围栏上的相关喷嘴，估计目标是减少除草剂使用量约75%。然后，该项目将通过改进围栏本身来确定精度的极限，允许喷嘴像喷墨打印机一样在围栏上线性移动，或者使用伺服电机旋转。使用这种方法，我们的目标是提供超过90%的除草剂使用量的潜在减少。CMV团队的作用将是实现新型的3D成像硬件和软件，用于在拖拉机上移动时检测草中的杂草。我们也要识别杂草的种类。这些数据将用于实时指导自动除草系统（由SE开发），并创建整个田地的详细杂草数据地图（由AS开发）。

The aim of the project is to develop a novel spray apparatus for precision application of herbicides to broad-leaf weeds ingrass crops. Such a system, using a spray boom covering a 10x.5m area of ground, could feasibly run at upwards of 1m/s,allowing precision spraying of weeds at between 1 and 2 hectares/hr.The consortium is comprised of three partners; (1) Centre for Machine Vision (CMV), a leading research centre in 3Dmachine vision, with past success in the agri-tech field, (2) Aralia Systems Ltd (AS), an international security company witha wide R&D portfolio in data-mining and complex feature analysis on videos, (3) Soil Essentials Ltd (SE), a leadingprecision agriculture company specialising in GPS machinery guidance, implement control, cloud based decision supportsystems and emerging grassland agronomy technologies.The primary focus will be to detect weeds in grass such as dock and ragwort using novel 3D machine vision techniques. Initially theproject will use off-the-shelf machinery to spray an area of roughly 50x50cm around each weed, activating the relevantnozzles on the boom with an estimated aimed decrease in herbicide use of around 75%.The project will then look todetermine the limits of precision by refining the boom itself, allowing nozzles to move linearly across the boom as on aninkjet printer, or in rotation using servo motors. Using this approach, we aim to provide potential reductions in herbicide usein excess of 90%.The role of the CMV team will be to realise novel 3D imaging hardware and software for detecting the weeds in the grasswhile moving on a tractor. We also aim to recognise the weed species. This data will be used to both direct the automatedweeding system in real-time (developed by SE) and to create a detailed weed data map (developed by AS) of the entirefield.