This software analyzes images from camera traps to determine whether there is an animal present or not. Camera traps may trigger due to various events. Usually, the camera trap uses an infrared sensor to determine whether a warm-blooded animal is in front of it. However, relatively frequently (based on camera type) , a false detection is made, and the camera captures an image without any animal. To filter these images, usually, a human must take a look at all the data. This can be a very cumbersome and laborious process.
This issue is addressed by this software. It takes the input image and uses a deep neural network to classify it into three classes: an image with an animal, an image without an animal, and an image that needs to be checked by a human expert. This preliminary filtering accelerates the process of obtaining relevant data in a significant way.