Improvement of the Ability to Recognize Sweet Peppers for Picking Robot in Greenhouse Horticulture
Shinsuke Kitamura, Koichi Oka
- 发表年份
- 2006
- 引用次数
- 21
摘要
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
关键词
相关论文
Statistical Learning Theory
Yuhai Wu, Vladimir Vapnik
1999
Artificial intelligence: a modern approach
1995
Fractional Differential Equations
Igor Podlubný
2025
Applied Nonlinear Control
Jean-Jacques Slotine, Weiping Li
1991