A Cognitive Vision Approach to Early Pest Detection in Greenhouse Crops

Paul Boissard (1) , Vincent Martin (2) , Sabine Moisan (2)

1 URIH - Unité Recherches Intégrées en Horticulture
2 PULSAR - Perception Understanding Learning Systems for Activity Recognition

Early disease detection is a major challenge in horticulture. Integrated Pest Management (IPM) combines prophylactic, biological and physical methods to fight bioagressors of crops while minimizing the use of pesticides. This approach is particularly promising in the context of ornamental crops in greenhouses because of the high level of control needed in such agrosystems. However, IPM requires frequent and precise observations of plants (mainly leaves), which are not compatible with production constraints. Our goal is early detection of bioagressors. In this paper, we present a strategy based on advances in automatic interpretation of images applied to leaves of roses scanned in situ. We propose a cognitive vision system that combines image processing, learning and knowledge-based techniques. This system is illustrated with automatic detection and counting of a whitefly (Trialeurodes vaporariorum Westwood) at a mature stage. We have compared our approach with manual methods and our results showed that automatic processing is reliable. Special attention was paid to low infestation cases, which are crucial to agronomic decisions.

Mots clés: IPM; Greenhouse crops; Pest early detection; Cognitive vision; Knowledge-based system; Machine learning

Domaines: Vision par ordinateur et reconnaissance de formes [cs.CV]

Paul Boissard, Vincent Martin, Sabine Moisan. A Cognitive Vision Approach to Early Pest Detection in Greenhouse Crops. Computers and Electronics in Agriculture, 2008, 62 (2), pp.81-93. ⟨10.1016/j.compag.2007.11.009⟩. ⟨inria-00499603⟩