Trail Camera Data Classification with AI (primary focus on Fishers)
Description
An AI accelerated workflow begins with detection of the camera trigger with the use of MegaDetector, then species classification is initiated with either an already trained classifier (SpeciesNet) or a classifier trained on NJFW data (Mega Efficient Wildlife Classifier). Once classification is complete, human verification then takes place in a database (Timelapse). According to the creators of MegaDetector, it can detect humans, vehicles, animals, or empty images at a rate of ~9.5 images per second using a GPU such as the NVIDIA A4000 (or similar). The Mega Efficient Wildlife Classifier and SpeciesNet will perform at similar rates on the NVIDIA A4000. At these rates, detection of wildlife and classification of footage can be completed within days and human verification can be completed in a few weeks to months compared to years without AI classification. AI accelerated workflow will significantly decrease the time and effort required, thus resulting in a more achievable goal. The goal of implementing an AI accelerated workflow is achievable with current staff that have knowledge and experience with the programs and workflow
Problem Statement
2. Tremendous volumes of wildlife imagery data (identifying Fishers and other species) now exist and are being collected faster than they can be processed into usable information.
Revisited in December with Pete and Kurt and program. New software developments allow progress locally without needing to use WSL. This led to deployment of heavy GIS unit to remote office for the project to proceed at Programs direction
Meeting with Pete and Kurt. We discussed two viable or preferred options to provide AI processing capacity that do not use the GIS-heavy machines deployed locally. These are 1. Enabling access to an API to a machine hosted here at 401 (configured directly with Linux, no WSL) - no program cost. 2. Enabling an Azure subscription with costs routed direct to the program via the CAR. Knute to review option with Kim and Kaitlyn.