-This paper describes recognition and cutting system of sweet peppers for picking robots in greenhouse horticulture. This picking robot has an image processing system with a parallel stereovision, a camera positioning system to follow the sweet pepper by visual feedback control, and a cutting device. A prototype robot system has been made and is introduced. Experiments of the prototype prove that performance of the cutting system depends on recognition of fruits of sweet peppers. Consequently, the robot has ability for picking sweet peppers.

This paper describes a distinction method for fruit of sweet peppers, which are grown in greenhouse, using reflection of LED light. Distinction for fruit of sweet pepper is necessary for development of picking robot in greenhouse horticulture. We have been manufactured a prototype of picking robot for sweet peppers. This picking robot has an image processing system using a parallel stereovision, a positioning system to the recognized sweet pepper using visual feedback control, and a cutting device. However, the distinction ability is lacking. We proposed a distinction method for fruits of sweet pepper using reflection of LED light. Experiments were carried out in greenhouse. In consequence, it was possible to improve the distinction ability.

This paper describes improvement of the ability to recognize sweet peppers for picking robot in greenhouse horticulture. A prototype of the picking robot for sweet peppers has been manufactured. This robot has an image processing system, a camera positioning system, and a cutting device. However the ability to recognize sweet peppers was low, the picking ability was also low. The color of fruits of sweet peppers is almost same color of leaves of it. For identifying a fruit from leaves, this system needs the lighting system. At first we used the fluorescent lamp on the lighting system. In this system, it was possible to identify only fruits in the condition of mixed fruits and leaves. However, if the fruits overlapping with several other fruits, the shapes of these fruits did not exactly recognize, and it is possible to be different the two fruits that are recognized by right and left camera. In this case, because it cannot to exactly measure by stereovision system, the picking ability became low. So we use the new lighting system with LED. In the result of experiments, this CDD lighting system improves the ability to recognize the sweet peppers.

This paper describes a method for sweet pepper picking robots working in greenhouses to distinguish the pepper fruits from the leaves. The fruits of the sweet pepper plant are recognized by image processing techniques, using a parallel stereovision system installed in the robot. However, as fruits and leaves of the sweet pepper have almost the same color, it is very difficult to recognize fruits using only color information. In this paper, we propose a new method using reflections of LED lights. The fruits of the sweet pepper are more reflective than the leaves; therefore, we can identify fruits by assuming that the more reflective parts are the fruits. We perform experiments using the improved image processing algorithm in a greenhouse, and the algorithm indeed improves the recognition ability of the robots.

No abstract