4 docs tagged with "Release 2023-06"

The Camera Traps application is both a simulator and IoT device software for utilizing machine learning on the edge in field research. The first implementation specializes in applying computer vision (detection and classification) to wildlife images for animal ecology studies. Two operational modes are supported: "simulation" mode and "demo" mode. When executed in simulation mode, the software serves as a test bed for studying ML models, protocols and techniques that optimize storage, execution time, power and accuracy. It requires an input dataset of images to act as the images that would be generated an IoT camera device; it uses these images to drive the simulation.

This repository contains tools and instructions for reproducing the experiments in the paper

Region2vec: Community Detection on Spatial Networks Using Graph Embedding with Node Attributes and Spatial Interactions

We present a species classification model that utilizes heterogeneous image contexts organized in a multimodal knowledge graph. The multimodal knowledge graph may include diverse forms of heterogeneous contexts that pertain to different modalities, such as numerical information for locations and time, categorical data for species/taxon IDs, and visual content such as images.