Projects per year
I am a zoologist / experimental psychologist whose research interests primarily concern computational approaches to applied vision and questions lying at the intersection of sensory biology, psychology, history and art. I am particularly passionate about how visual scenes can be “understood” using computer vision and what comparisons can be drawn with biological visual systems.
Projects I work on:
Automatic disease detection and monitoring in calves
I am an EPSRC Innovation Fellow on a project developing automatic disease detection and monitoring in domestic cattle calves. The project uses artificial intelligence techniques, coupled with visible-range and thermal cameras, to identify Bovine Respiratory Disease (BRD), one of the most common and costly diseases affecting cattle in the world, at the earliest possible stage. My work includes building sensors, deploying and maintaining equipment on farms, establishing efficient data transfer protocols and analysing data using deep neural networks.
An ongoing research to develop a toolkit and pipeline in order to establish the best (or worst) camouflage for any object in any environment for any viewer using deep neural networks. A paper on establishing optimal colours for concealing and visibility can be found here.
Modelling the evolution of camouflage using Generative Adversarial Networks
This research, supported by Nvidia, investigates how competing deep neural networks can be used to evolve camouflage patterns. Our team has demonstrated how Generative Adversarial Networks (GAN) can be utilised to simulate an evolutionary arms-race between a synthetic prey and predator.
Understanding art reception from eye movements using AI-generated artworks
The project examines how we can predict preference to visual artworks using eye movements of observers and artworks generated by deep neural networks.
Cultural evolution of military camouflage uniform patterns
My PhD work focused on how camouflage uniform patterns evolved since the early 20th century. The research uses methods from computer vision to establish similarity metrics between patterns and phylogenetics to model how patterns of allied / hostile countries have influenced each other’s designs.
1/04/20 → 31/03/21
The Camouflage Machine: Optimizing protective coloration using deep learning with genetic algorithmsFennell, J. G., Tálas, L., Baddeley, R. J., Cuthill, I. C. & Scott-Samuel, N. E., 18 Jan 2021, In: Evolution. 75, 3, p. 614-624 11 p.
Research output: Contribution to journal › Article (Academic Journal) › peer-reviewOpen AccessFile23 Downloads (Pure)
Talas, L., Fennell, J., Kjernsmo, K., Cuthill, I., Scott-Samuel, N. & Baddeley, R., 1 Feb 2020, In: Methods in Ecology and Evolution. 11, 2, p. 240-247 8 p.
Research output: Contribution to journal › Article (Academic Journal) › peer-reviewOpen AccessFile427 Downloads (Pure)
Kjernsmo, K., Whitney, H. M., Scott-Samuel, N. E., Hall, J. R., Knowles, H., Tálas, L. & Cuthill, I. C., 3 Feb 2020, In: Current Biology. 30, 3, p. 551-555.e3 9 p.
Research output: Contribution to journal › Article (Academic Journal) › peer-reviewOpen AccessFile71 Downloads (Pure)