CamoEvo: An open access toolbox for artificial camouflage evolution experiments

Abstract

Camouflage research has long shaped our understanding of evolution by natural selection, and elucidating the mechanisms by which camouflage operates remains a key question in visual ecology. However, the vast diversity of color patterns found in animals and their backgrounds, combined with the scope for complex interactions with receiver vision, presents a fundamental challenge for investigating optimal camouflage strategies. Genetic algorithms (GAs) have provided a potential method for accounting for these interactions, but with limited accessibility. Here, we present CamoEvo, an open-access toolbox for investigating camouflage pattern optimization by using tailored GAs, animal and egg maculation theory, and artificial predation experiments. This system allows for camouflage evolution within the span of just 10-30 generations (∼1-2 min per generation), producing patterns that are both significantly harder to detect and that are optimized to their background. CamoEvo was built in ImageJ to allow for integration with an array of existing open access camouflage analysis tools. We provide guides for editing and adjusting the predation experiment and GA as well as an example experiment. The speed and flexibility of this toolbox makes it adaptable for a wide range of computer-based phenotype optimization experiments.

A Hyperspectral Camouflage Colorant Inspired by Natural Leaves

“…Artificial camouflage originated from the camouflage behavior of nature, [42,43] and developed as the need of military, hunting and aesthetics. Recent developments in spectral imaging technology for target detection are pushing camouflage technology into higher dimension and precision.…”

Analysing biological colour patterns from digital images: An introduction to the current toolbox

“…Machine learning approaches can also be used to help inform future research questions. The CamoEvo toolbox is an open access resource that is used to study the evolution of camouflage (Hancock & Troscianko, 2022).…”

Adapting genetic algorithms for artificial evolution of visual patterns under selection from wild predators

“…We developed a methodology for generating and testing artificial prey in the field using genetic algorithms, by substantially adapting an existing screen-based implementation, the CamoEvo toolbox [12], released here as CamoPrint in CamoEvo V2.0 (see supporting code).…”

“…Targets were oval, with colourations occupying a CIELAB space with ranges 0 -100 in luminance, -50 -50 in A (green-red) and -10 -70 in B (blue-yellow). Every population began with an identical set of patterns, randomly-generated using these parameters with a uniform distribution of genes (Generation 0; S2 Fig) . Details of the pattern generation and genetic algorithm framework can be found in [12].…”

“…Originally developed as a general solution to optimisation problems with vast parameter spaces [6], genetic algorithms are an increasingly popular technique in biological research, ideally suited to exploring visual pattern space. So far, genetic algorithms have been used to investigate the evolution of several aspects of visual signalling, primarily camouflage patterns [4,[7][8][9][10][11][12], but also aposematism [13], motion dazzle [14] and even nectar guides in flowers [15]. In brief, genetic algorithms set out both virtual genetic structures underpinning phenotypes and rules governing survival and reproduction into the next generation, based on the responses of an observer; across multiple encounters with the observer in successive generations, optimal solutions to the task should arise.…”