A robotic monitoring system for diseases of pepper in greenhouse
Noa Schor, Sigal Berman, Aviv Dombrovsky, Yigal Elad, Tímea Ignát, Avital Bechar
- Year
- 2015
- Citations
- 7
Abstract
Powdery mildew and tomato spotted wilt virus (TSWV) are the two main threats to pepper plants (Capsicum annuum) grown in greenhouses causing severe damage and yield loss. The paper reports the development of a robotic disease monitoring system for early detection of both threats. The research faced several challenges as, currently, algorithms for powdery mildew detection have only been implemented on other crops and there are no known algorithms for TSWV detection. Moreover, monitoring several diseases of pepper plants using a single monitoring system has not been reported. The system development was based on a holistic approach, integrating the design of both motion and perception systems. Preliminary results for TSWV detection are promising. Analysis of powdery mildew database is currently being conducted. The physical hardware system has been constructed and once the image processing algorithms are finalized, the system will be ready for extensive testing.
Keywords
Related papers
Statistical Learning Theory
Yuhai Wu, Vladimir Vapnik
1999
Artificial intelligence: a modern approach
1995
Applied Nonlinear Control
Jean-Jacques Slotine, Weiping Li
1991
A new optimizer using particle swarm theory
R.C. Eberhart, James Kennedy
2002