A real-time remote surveillance system for fruit flies of economic importance: sensitivity and image analysis

• Published in: Journal of pest science Vol. 96; no. 2; pp. 611 - 622
• Main Authors: Diller, Yoshua, Shamsian, Aviv, Shaked, Ben, Altman, Yam, Danziger, Bat-Chen, Manrakhan, Aruna, Serfontein, Leani, Bali, Elma, Wernicke, Matthias, Egartner, Alois, Colacci, Marco, Sciarretta, Andrea, Chechik, Gal, Alchanatis, Victor, Papadopoulos, Nikos T., Nestel, David
• Format: Journal Article
• Language: English
• Published: Berlin/Heidelberg Springer Berlin Heidelberg 01.03.2023; Springer Nature B.V
• Subjects: Agricultural research; Agriculture; Algorithms; Automation; Biomedical and Life Sciences; Classification; Decision making; Deep learning; Ecology; Economic analysis; Economic importance; Entomology; Field tests; Forestry; Fruit flies; Fruits; Image analysis; Image processing; Invasive species; Laboratories; Life Sciences; Machine learning; Model accuracy; Original Paper; Pest outbreaks; Plant Pathology; Plant Sciences; Sensors; Surveillance; Surveillance systems; Zoology; Deep-learning; Detection; Smart-trap
• ISSN: 1612-4758; 1612-4766
• DOI: 10.1007/s10340-022-01528-x

Timely detection of an invasion event, or a pest outbreak, is an extremely challenging operation of major importance for implementing management action toward eradication and/or containment. Fruit flies—FF—(Diptera: Tephritidae) comprise important invasive and quarantine species that threaten the world fruit and vegetables production. The current manuscript introduces a recently developed McPhail-type electronic trap (e-trap) and provides data on its field performance to surveil three major invasive FF ( Ceratitis capitata , Bactrocera dorsalis and B. zonata ). Using FF male lures, the e-trap attracts the flies and retains them on a sticky surface placed in the internal part of the trap. The e-trap captures frames of the trapped adults and automatically uploads the images to the remote server for identification conducted on a novel algorithm involving deep learning. Both the e-trap and the developed code were tested in the field in Greece, Austria, Italy, South Africa and Israel. The FF classification code was initially trained using a machine-learning algorithm and FF images derived from laboratory colonies of two of the species ( C. capitata and B. zonata ). Field tests were then conducted to investigate the electronic, communication and attractive performance of the e-trap, and the model accuracy to classify FFs. Our results demonstrated a relatively good communication, electronic performance and trapping efficacy of the e-trap. The classification model provided average precision results (93–95%) for the three target FFs from images uploaded remotely from e-traps deployed in field conditions. The developed and field tested e-trap system complies with the suggested attributes required for an advanced camera-based smart-trap.