Detection Models
We offer a broad range of pretrained object and pose detection models ready for your footage. Each model supports videos shot underwater as well as aerial footage from airplanes or UAVs.
Contact us if none of the pretrained models fits your needs.
Shark Pose
-
detected classes: hammerhead, lemon, great white, bull, silk, sandbar shark, bait crate, person, common bottlenose dolphin, bait
-
keypoints: snout, dorsal fin top, dorsal fin base, caudal fin top, caudal fin base
Manta Pose
-
detected classes: manta, person
-
keypoints: left wingtip, right wingtip, left eye, right eye, tail base
Human Pose
detected classes: person
keypoints: left ear, right ear, nose, neck, left shoulder, right shoulder, left elbow, right elbow, left hand, right hand, left hip, right hip, left knee, right knee, left ankle, right ankle
Generic Animal Detection
-
detected classes: person, bird, cat, dog, horse, sheep, cow, elephant, bear, zebra, giraffe
-
no keypoints are detected, but oftentimes local movement extrema can be extracted from the changing bounding box aspect ratio
Your own private Model
We offer the creation of custom datasets based on your private videos. Our custom labeling pipeline enables rapid model creation.
Consulting Service
We are happy to advise you in your journey to use AI and Computer Vision to speed up your research and operations. Just reach out to us!