Efficient Pipeline for Camera Trap Image Review

By Sara Beery, Dan Morris, Siyu Yang. 2019

212 citations recorded by the source corpus.

Biologists all over the world use camera traps to monitor biodiversity and wildlife population density. The computer vision community has been making strides towards automating the species classification challenge in camera traps, but it has proven difficult to to apply models trained in one region to images collected in different geographic areas. In some cases, accuracy falls off catastrophically in new region, due to both changes in background and the presence of previously-unseen species. We propose a pipeline that takes advantage of a pre-trained general animal detector and a smaller set of labeled images to train a classification model that can efficiently achieve accurate results in a new region.

Subfields: Computer Vision and Pattern Recognition, Molecular Biology, Human-Computer Interaction

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Molecular Biology

In Human-Computer Interaction

Citations in the corpus

SOCRATES: Introducing Depth in Visual Wildlife Monitoring Using Stereo Vision (2022, methodology): “To be able to use all observations without leaking information from the training dataset of our instance segmentation model, in this study, we use not the instance masks but the bounding boxes of MegaDetector (Beery et al., 2019) and the sampling approach by Haucke et al. (2022).”
WILDS: A Benchmark of in-the-Wild Distribution Shifts (2020, positive): “To better understand and monitor wildlife biodiversity loss, ecologists commonly deploy camera traps— heat or motion-activated static cameras placed in the wild (Wearn & Glover-Kapfer, 2017)—and then use ML models to process the data collected (Weinstein, 2018; Norouzzadeh et al., 2019; Tabak et al.”
Automated distance estimation for wildlife camera trapping (2022, methodology): “In the localization branch (right), animals are visually detected in each video frame by using the MegaDetector-framework (Section 2.2.3, (Beery et al., 2019)) that outputs the bounding boxes of every animal detection (red rectangles).”
Overcoming the distance estimation bottleneck in estimating animal abundance with camera traps (2021, unknown): “Localization of the observed animal in this calibrated depth image For animal detection we employ MegaDetector (Beery et al., 2019), a deeplearning animal detection model based on the Faster R-CNN (Ren et al.”
Perspectives in machine learning for wildlife conservation (2021, methodology): “has proven to be a valuable and robust tool for filtering blank images, and many ecologists have already incorporated open source ML approaches for blank filtering (such as the Microsoft AI4Earth MegaDetector (42), see Table 1 and Box ) into their camera trap workflows.”
The iWildCam 2021 Competition Dataset (2021, methodology): “We provide competitors with species labels along with weakly-supervised detections [10] and instance segmentations [15] to help them to disambiguate individuals.”