This work represents deep learning approach for detecting lizards on the summer grass background. It is the main part of general use case formulation—“how many lizards are located now on this substitute habitat. Determine in which parts they prefer to stay”. For this purpose, the U-Net architecture neural network was implemented. Dilated convolution layer was added to usual U-Net. Smoothly blending filter was applied to result probability patches for connecting them in one big probability map without sewed edges. Designed flexible architecture allows to train neural network for pixel-wise semantic segmentation with accuracy value 0.9863.
Presentation takeaways - Audience will learn unique methods about applying deep learning in conservation and environmental related use case. - Learning about the unique type of dataset and how to increase the model training effectiveness. - Effective methods of Results comparison : Ground truth data by Environmentalists vs AI model Conclusion - Effective use of synthetic data - Pros and cons of deployed architecture