Automatic monitoring of pest insects traps by Zigbee-based wireless networking of image sensors

• Published in: 2011 IEEE International Instrumentation and Measurement Technology Conference pp. 1 - 5
• Main Authors: Tirelli, P., Borghese, N. A., Pedersini, F., Galassi, G., Oberti, R.
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.05.2011
• Subjects: Base stations; Cameras; crop pest control; Flash memory; image processing; Insects; Monitoring; Peer to peer computing; Wireless sensor networks; zigbee wireless sensor networks
• ISBN: 1424479339; 9781424479337
• ISSN: 1091-5281
• DOI: 10.1109/IMTC.2011.5944204

Monitoring pest insect population is currently a key issue in crop protection. At farm level it is routinely operated by repeated surveys by a human operator of adhesive traps, disseminated through the field, where insects remain stuck when attracted. This is a labor- and time-consuming activity, and it would be of great advantage for farmers to have an affordable system doing this task automatically. This paper illustrates a system based on a distributed imaging device operated through a wireless sensor network that is able to automatically acquire and transmit images of the trapping area to a remote host station. The station evaluates the insect density evolution at different farm sites and produces an alarm when insect density goes over threshold. The network architecture consists of a master node hosted in a PC and a set of client nodes, spread in the fields, that act as monitoring stations. The master node coordinates the network and retrieves from the client nodes the captured images. Zigbee transmission protocol guarantees a low power consumption. Results from real data acquired on a small scale system deployed inside a greenhouse hall hosting a set of Vinca Catharantus roseus plants are shown. During a monitoring period of four weeks the network operated regularly, producing a pest insects population curve fairly correlated to daily counts obtained by visual observations of the trap and therefore demonstrating the feasibility of this approach.