Submitted to: Annals of the Entomological Society of America
Publication Type: Peer Reviewed Journal
Publication Acceptance Date: 12/13/2018
Publication Date: 1/23/2019
Citation: Manoukis, N., Collier, T.C. 2019. Computer vision to enhance behavioral research on insects. Annals of the Entomological Society of America. 112(3):227-235. https://doi.org/10.1093/aesa/say062.
Interpretive Summary: Understanding of insect behavior can be enhanced by being able to measure the behavior. New tools in computer vision help to make these measurements automatically. In this paper we describe the steps needed for an automated analysis of insect behavior, starting from capturing images with cameras to extracting data from the images to conducting analysis of the data to obtain answers to research questions. Information on insect behavior can be critical to control of damaging pests or disease vectors. This paper is a starting point for those interested in delving deeper into how computer vision can be applied to their research.
Technical Abstract: New or improved technologies can enable entomologists to address previously intractable questions, especially in the area of insect behavior. In this review, we describe the basic elements of applied computer vision for entomologists: Image capture, data extraction, and analysis. We describe some of the currently available options in imaging hardware and cameras, lighting, software, as well as some basic analytical approaches from previous studies and through examples. We conclude that the study of insect behavior is increasingly based on the quantification of behavioral phenomena, that use of computer vision techniques to obtain these quantification is likely to increase, and that the application of these tools and approaches will bring new insight and answers to questions in entomology. To accelerate this process entomologists studying behavior must be aware of the general approaches and tools currently available, and we hope this review can serve as a starting point for those interested in delving deeper into how computer vision can be applied to their research.