deep-chimpact

Deep Chimpact

Depth Estimation for Wildlife Conservation (1st place solution)

<div align=center> <img src="https://user-images.githubusercontent.com/36858976/138281204-c3cbcb77-11ca-448b-a693-cb3cfa3c5181.png" width=800>

Overview

Healthy natural ecosystems have wide-ranging benefits from public health to the economy to agriculture. In order to protect the Earth's natural resources, conservationists need to be able to monitor species population sizes and population change. Camera traps are widely used in conservation research to capture images and videos of wildlife without human interference. Using statistical models for distance sampling, the frequency of animal sightings can be combined with the distance of each animal from the camera to estimate a species' full population size.

However, getting distances from camera trap footage currently entails an extremely manual, time-intensive process. It takes a researcher more than 10 minutes on average to label distance for every 1 minute of video - that’s a lot of time when you have a million videos! This also creates a bottleneck for critical information that conservationists can use to monitor wildlife populations.

Your goal in this challenge is to use machine learning to automatically estimate the distance between a camera trap and an animal in a series of camera trap videos. You will be given a series of timestamps indicating when animals are visible in each camera trap video. To complete the challenge, you will predict the distance between the animal and the camera at each point in time.

Along the way, keep an eye out for some sneaky leopards hunting at night, baby chimpanzees getting piggy-back rides, and diva elephants that can't get enough of the limelight. By contributing to this challenge, you can help advance cutting-edge methods for keeping these animal populations (and humans) healthy and safe!