A machine vision system using a charge coupled device camera for the weed detection in a radish farm was developed. Shape features were analysed with the binary images obtained from colour images of radish and weeds. Aspect, elongation and perimeter to broadness were selected as significant variable
AE—Automation and Emerging Technologies: Robotic Weed Control using Machine Vision
✍ Scribed by J. Blasco; N. Aleixos; J.M. Roger; G. Rabatel; E. Moltó
- Publisher
- Elsevier Science
- Year
- 2002
- Tongue
- English
- Weight
- 633 KB
- Volume
- 83
- Category
- Article
- ISSN
- 1537-5110
No coin nor oath required. For personal study only.
✦ Synopsis
The purpose of this work is to present a non-chemical weed controller for vegetable crops derived from a cooperative French-Spanish project. One of the major efforts of this project is related with working in a natural, complex environment and the similarity between the weeds and the vegetable crop, which makes locating the weeds difficult.
The robotic arm presents a parallel structure with six degrees of freedom, and due to its light structure, it is capable of reaching high accelerations. The end-effector has an electrode powered by a set of batteries and kills the weeds by producing an electrical discharge of 15 000 V. All the subsystems of the machine communicate through a controller area network (CAN) bus.
There are two vision systems mounted on the machine. The first one is placed at the front of the robot to acquire and analyse field images, in order to detect weeds and send their coordinates to the robotic arm control. The second camera is placed close to the electrode, and its mission is to correct inertial perturbations by relocating every individual weed detected by the first vision system.
The successful performance of this new concept of precise non-chemical weeding has been demonstrated in a lettuce crop in Valencia, Spain.
📜 SIMILAR VOLUMES
This paper presents apple grading into four classes according to European standards. Two varieties were tested: Golden Delicious and Jonagold. The image database included more than a 1000 images of fruits (528 Golden Delicious, 642 Jonagold) belonging to the three acceptable categories}Extra, I and
In order to improve weeding strategies in terms of pesticide reduction, spatial distribution and characterization of in-"eld weed populations are important. With recent improvements in image processing, many studies have focused on weed detection by vision techniques. However, weed identi"cation sti
In Korea, research projects on year-round leaf vegetable production systems are in progress, most of them focused on environmental control. Therefore, automation technologies for harvesting, transporting and grading are in great demand. A robot system was developed for harvesting lettuce plants, com
This study was carried out to develop a robotic transplanter for bedding plants. The transplanter consisted of a manipulator, an end-e!ector, plug tray conveyors and a vision system. The manipulator consisted of two electrical linear motors. It was used to move the end-e!ector to the desired working
A prototype slurry spreading system, based on a commercially available pump discharge tanker, was designed, built and tested. The system featured a positive displacement slurry pump, an electrically operated #ow control valve and a novel spreading boom "tted with #uidic diodes. The prototype slurry