Trail Camera Analysis<\/em><\/strong> <\/mark><\/h2>\n\n\n\n<\/p>\n\n\n\nDeepFaune New England<\/summary>\nDeepFaune New England<\/a> (DFNE) model for species classification analyzes trail camera imagery. This model is a re-trained version of the DeepFaune<\/a> model for classifying European species in trial cameras, fine-tuned to classify taxa from northeastern North America. DFNE classifies 24 taxa, including the “no-species” label indicating the absence of an animal.<\/p>\n\n\n\n![\"\"](\"http:\/\/site.uvm.edu\/amber\/files\/2026\/02\/dpne_annotated_images-scaled.jpg\")
<\/p>\n<\/details>\n\n\n\nSpeciesNet<\/summary>\nSpeciesNet<\/a> is runs two AI models: (1) an object detector that finds objects of interest in wildlife camera images, and (2) an image classifier that classifies those objects to the species level. This ensemble is used for species recognition in the Wildlife Insights<\/a> platform. The code is now open source, allowing AMBER to include SpeciesNet into our machine learning repertoire. <\/p>\n\n\n\nMegaDetector<\/summary>\nMegaDetector<\/a> is an AI model that identifies animals, people, and vehicles in camera trap images (which also makes it useful for eliminating blank images). This model is trained on several million images from a variety of ecosystems.<\/p>\n\n\n\nMegaDetector only finds animals, it doesn’t identify them to species level. Both SpeciesNet and DeepFaune New England use MegaDetector to identify animals within images, and then further classify identified targets to species.<\/p>\n<\/details>\n<\/details>\n\n\n\nMegaDetector<\/summary>\nMegaDetector<\/a> is an AI model that identifies animals, people, and vehicles in camera trap images (which also makes it useful for eliminating blank images). This model is trained on several million images from a variety of ecosystems.<\/p>\n\n\n\nMegaDetector only finds animals, it doesn’t identify them to species level.<\/p>\n<\/details>\n\n\n\n
<\/div>\n\n\n\nAudio Analysis <\/mark><\/em><\/strong><\/h2>\n\n\n\nBirdNet<\/summary>\nBirdNET<\/a> uses deep learning to recognize over 6,000 species globally within audio files. It was developed by the K. Lisa Yang Center for Conservation Bioacoustics<\/a> at the Cornell Lab of Ornithology<\/a> in collaboration with Chemnitz University of Technology<\/a>.<\/p>\n\n\n\nGo to https:\/\/birdnet.cornell.edu<\/a> to learn more about the project.<\/p>\n<\/details>\n\n\n\nHawkEars<\/summary>\nHawkEars<\/a> is a desktop program that scans audio recordings for bird sounds and generates Audacity<\/a> label files. It is inspired by BirdNET<\/a>, and intended as an improved productivity tool for analyzing field recordings. AMBER runs HawkEars directly and stores results in your database, accessed through our web portal.<\/p>\n<\/details>\n\n\n\nRuffed Grouse Drumming Model<\/summary>\nRuffed Grouse are a flagship species in North America, of interest to many conservation groups. See this article<\/a> for more details. <\/p>\n<\/details>\n\n\n\nCustomized Templates<\/summary>\nWhen acoustic targets have a recognizable signal, simple template-matching may be a powerful way to screen audio files for a target wildlife species of interest. AMBER has the ability to create customized templates and screen files for potential signal matches, and further develop machine learning models to locate true detections.<\/p>\n<\/details>\n\n\n\n
DeepFaune New England<\/summary>\nDeepFaune New England<\/a> (DFNE) model for species classification analyzes trail camera imagery. This model is a re-trained version of the DeepFaune<\/a> model for classifying European species in trial cameras, fine-tuned to classify taxa from northeastern North America. DFNE classifies 24 taxa, including the “no-species” label indicating the absence of an animal.<\/p>\n\n\n\n<\/p>\n<\/details>\n\n\n\nSpeciesNet<\/summary>\nSpeciesNet<\/a> is runs two AI models: (1) an object detector that finds objects of interest in wildlife camera images, and (2) an image classifier that classifies those objects to the species level. This ensemble is used for species recognition in the Wildlife Insights<\/a> platform. The code is now open source, allowing AMBER to include SpeciesNet into our machine learning repertoire. <\/p>\n\n\n\nMegaDetector<\/summary>\nMegaDetector<\/a> is an AI model that identifies animals, people, and vehicles in camera trap images (which also makes it useful for eliminating blank images). This model is trained on several million images from a variety of ecosystems.<\/p>\n\n\n\nMegaDetector only finds animals, it doesn’t identify them to species level. Both SpeciesNet and DeepFaune New England use MegaDetector to identify animals within images, and then further classify identified targets to species.<\/p>\n<\/details>\n<\/details>\n\n\n\nMegaDetector<\/summary>\nMegaDetector<\/a> is an AI model that identifies animals, people, and vehicles in camera trap images (which also makes it useful for eliminating blank images). This model is trained on several million images from a variety of ecosystems.<\/p>\n\n\n\nMegaDetector only finds animals, it doesn’t identify them to species level.<\/p>\n<\/details>\n\n\n\n
<\/div>\n\n\n\nAudio Analysis <\/mark><\/em><\/strong><\/h2>\n\n\n\nBirdNet<\/summary>\nBirdNET<\/a> uses deep learning to recognize over 6,000 species globally within audio files. It was developed by the K. Lisa Yang Center for Conservation Bioacoustics<\/a> at the Cornell Lab of Ornithology<\/a> in collaboration with Chemnitz University of Technology<\/a>.<\/p>\n\n\n\nGo to https:\/\/birdnet.cornell.edu<\/a> to learn more about the project.<\/p>\n<\/details>\n\n\n\nHawkEars<\/summary>\nHawkEars<\/a> is a desktop program that scans audio recordings for bird sounds and generates Audacity<\/a> label files. It is inspired by BirdNET<\/a>, and intended as an improved productivity tool for analyzing field recordings. AMBER runs HawkEars directly and stores results in your database, accessed through our web portal.<\/p>\n<\/details>\n\n\n\nRuffed Grouse Drumming Model<\/summary>\nRuffed Grouse are a flagship species in North America, of interest to many conservation groups. See this article<\/a> for more details. <\/p>\n<\/details>\n\n\n\nCustomized Templates<\/summary>\nWhen acoustic targets have a recognizable signal, simple template-matching may be a powerful way to screen audio files for a target wildlife species of interest. AMBER has the ability to create customized templates and screen files for potential signal matches, and further develop machine learning models to locate true detections.<\/p>\n<\/details>\n\n\n\n
SpeciesNet<\/a> is runs two AI models: (1) an object detector that finds objects of interest in wildlife camera images, and (2) an image classifier that classifies those objects to the species level. This ensemble is used for species recognition in the Wildlife Insights<\/a> platform. The code is now open source, allowing AMBER to include SpeciesNet into our machine learning repertoire. <\/p>\n\n\n\n MegaDetector<\/a> is an AI model that identifies animals, people, and vehicles in camera trap images (which also makes it useful for eliminating blank images). This model is trained on several million images from a variety of ecosystems.<\/p>\n\n\n\n MegaDetector only finds animals, it doesn’t identify them to species level. Both SpeciesNet and DeepFaune New England use MegaDetector to identify animals within images, and then further classify identified targets to species.<\/p>\n<\/details>\n<\/details>\n\n\n\n MegaDetector<\/a> is an AI model that identifies animals, people, and vehicles in camera trap images (which also makes it useful for eliminating blank images). This model is trained on several million images from a variety of ecosystems.<\/p>\n\n\n\n MegaDetector only finds animals, it doesn’t identify them to species level.<\/p>\n<\/details>\n\n\n\n BirdNET<\/a> uses deep learning to recognize over 6,000 species globally within audio files. It was developed by the K. Lisa Yang Center for Conservation Bioacoustics<\/a> at the Cornell Lab of Ornithology<\/a> in collaboration with Chemnitz University of Technology<\/a>.<\/p>\n\n\n\n Go to https:\/\/birdnet.cornell.edu<\/a> to learn more about the project.<\/p>\n<\/details>\n\n\n\n HawkEars<\/a> is a desktop program that scans audio recordings for bird sounds and generates Audacity<\/a> label files. It is inspired by BirdNET<\/a>, and intended as an improved productivity tool for analyzing field recordings. AMBER runs HawkEars directly and stores results in your database, accessed through our web portal.<\/p>\n<\/details>\n\n\n\n Ruffed Grouse are a flagship species in North America, of interest to many conservation groups. See this article<\/a> for more details. <\/p>\n<\/details>\n\n\n\n When acoustic targets have a recognizable signal, simple template-matching may be a powerful way to screen audio files for a target wildlife species of interest. AMBER has the ability to create customized templates and screen files for potential signal matches, and further develop machine learning models to locate true detections.<\/p>\n<\/details>\n\n\n\n<\/p>\n<\/details>\n\n\n\nSpeciesNet<\/summary>\n
MegaDetector<\/summary>\n
MegaDetector<\/summary>\n
Audio Analysis <\/mark><\/em><\/strong><\/h2>\n\n\n\n
BirdNet<\/summary>\n
HawkEars<\/summary>\n
Ruffed Grouse Drumming Model<\/summary>\n
Customized Templates<\/summary>\n