The Potato Operation: Computer vision for agricultural robotics
نویسندگان
چکیده
Each year at harvest time millions of seed potatoes are checked for the presence of viruses, by means of an Elisa test. The Potato Operation aims at automatizing the potato manipulation and pulp sampling procedure, starting from bunches of harvested potatoes and ending with the deposit of potato pulp into Elisa containers. Automatizing these manipulations addresses several issues, linking robotic and computer vision. The paper reports on the current status of this project. It first summarizes the robotic aspects, which consist of locating a potato in a bunch, grasping it, positioning it into the camera field of view, pumping the pulp sample and depositing it into a container. The computer vision aspects are then detailed. They concern locating particular potatoes in a bunch, and finding the position of the best germ where the drill has to sample the pulp. The emphasis is put on the germ location problem. A general overview of the approach is given, which combines the processing of both frontal and silhouette views of the potato, together with movements of the robot arm (active vision). Frontal and silhouette analysis algorithms are then presented. Results are shown, that confirm the feasibility of the approach. 1. OVERVIEW AND CONSTRAINTS 1.1. Overview This article presents a general overview of the Potato Operation1,2,3,4,5,6,7 in its current status. The whole project belongs to the domain of agricultural robotics8,9,10,11,12, or agrotics. It aims at automatizing pulp sampling of potatoes used as seeds. With respect to industrial applications, the Potato Operation project will lead to the realization of a prototype. At harvest time (autumn), randomly selected potatoes are tested for the detection of possible viral diseases. The detection is performed using an Elisa test13. Such statistical detection is essential in order to prevent propagation of these viral diseases, which can decrease productivity by up to an order of magnitude. The whole process is currently being performed by hand for hundred of thousand of potatoes each year. At the Swiss Federal Agricultural Station in Changins, approximately 10’000 potatoes are handled per day during the two months testing period. The present project aims at automatizing the manipulation and sampling procedure, Proc. SPIE Conf. on Advances in Intelligent Robotic Systems, Boston, USA, Nov. 10-15, 1991.
منابع مشابه
Computer Vision and Agricultural Robotics for Disease Control: The Potato Operation
camera light 1 light 2 potato sprout shadows due to light source 1 shadows due to light source 2 25 Fig 9; Lefebvre et al.
متن کاملEvaluation of Aqua Crop Computer Model in the Potato Under Irrigation Management of Continuity Plan of Jiroft Region, Kerman, Iran
The agricultural regions are running into difficulties, which are restrictive availability of water, successive appearing draughts, and overuse of ground water resources for supplemental water requirements. As a sample which is got from the farm is sent to the laboratory for testing and the laboratory works need devices. Hence, conducting farm experiments are expensive and time consuming to opt...
متن کاملEvaluation of Aqua Crop Computer Model in the Potato Under Irrigation Management of Continuity Plan of Jiroft Region, Kerman, Iran
The agricultural regions are running into difficulties, which are restrictive availability of water, successive appearing draughts, and overuse of ground water resources for supplemental water requirements. As a sample which is got from the farm is sent to the laboratory for testing and the laboratory works need devices. Hence, conducting farm experiments are expensive and time consuming to opt...
متن کاملCurrent work at the Robotics group of the Universidad de Guanajuato
At Universidad de Guanajuato at Salamanca, robotic techniques are developed in LaViRIA (Laboratory of Vision, Robotics and Artificial Intelligence). Our work is directed towards developing methods that integrate computer vision techniques and artificial intelligence techniques (mainly based in soft computing) in robotics applications and its implementations in the real robots. Main applications...
متن کاملTwo New Methods of Boundary Correction for Classifying Textural Images
With the growth of technology, supervising systems are increasingly replacing humans in military, transportation, medical, spatial, and other industries. Among these systems are machine vision systems which are based on image processing and analysis. One of the important tasks of image processing is classification of images into desirable categories for the identification of objects or their sp...
متن کامل