The iWildCam 2021 Competition Dataset
This work provides a benchmark for ecologists and computer vision researchers to improve wildlife monitoring methods, though it is incremental as it builds on existing object detection and re-identification techniques.
The paper tackles the problem of accurately estimating animal abundance from camera trap images by introducing a competition dataset that requires species classification and individual counting across sequences, addressing the challenge of different camera locations and overlapping but non-identical species sets.
Camera traps enable the automatic collection of large quantities of image data. Ecologists use camera traps to monitor animal populations all over the world. In order to estimate the abundance of a species from camera trap data, ecologists need to know not just which species were seen, but also how many individuals of each species were seen. Object detection techniques can be used to find the number of individuals in each image. However, since camera traps collect images in motion-triggered bursts, simply adding up the number of detections over all frames is likely to lead to an incorrect estimate. Overcoming these obstacles may require incorporating spatio-temporal reasoning or individual re-identification in addition to traditional species detection and classification. We have prepared a challenge where the training data and test data are from different cameras spread across the globe. The set of species seen in each camera overlap, but are not identical. The challenge is to classify species and count individual animals across sequences in the test cameras.