The iWildCam 2020 Competition Dataset
This addresses a key challenge for biologists using camera traps to monitor animal populations across diverse regions, though it is incremental as it focuses on dataset creation rather than novel methods.
The paper tackles the problem of training species classification models that generalize to new, unseen camera trap locations by introducing a competition dataset with training and test data from geographically distinct cameras, supplemented by remote sensing and citizen science imagery.
Camera traps enable the automatic collection of large quantities of image data. Biologists all over the world use camera traps to monitor animal populations. We have recently been making strides towards automatic species classification in camera trap images. However, as we try to expand the geographic scope of these models we are faced with an interesting question: how do we train models that perform well on new (unseen during training) camera trap locations? Can we leverage data from other modalities, such as citizen science data and remote sensing data? In order to tackle this problem, we have prepared a challenge where the training data and test data are from different cameras spread across the globe. For each camera, we provide a series of remote sensing imagery that is tied to the location of the camera. We also provide citizen science imagery from the set of species seen in our data. The challenge is to correctly classify species in the test camera traps.