Biology subjects

Ims, R. A.

Publications and source records attributed to Ims, R. A..

3 recordsLinked to original sources

bioRxiv2022

A versatile semiautomated image analysis workflow for time-lapsed camera trap image classification.

O_LICamera trap arrays can generate thousands to millions of images that require exorbitant time and effort to classify and annotate by trained observers. Computer vision has evolved as an automated alternative to manual classification. The most popular computer vision solution is the supervised Machine Learning technique, which uses labeled images to train automated classification algorithms. C_LIO_LIWe propose a multi-step semi-automated workflow that consists of (1) identifying and separating bad-from good-quality images, (2) parsing good images into animals, humans, vehicles, and empty, and (3) cropping animals from images and classifying them into species for manual inspection. We trained, validated, and evaluated this approach using 548,627 images from 46 cameras in two regions of the Arctic (northeastern Norway, and Yamal Peninsula, Russia). C_LIO_LIWe obtained an accuracy of 0.959 for all three steps combined with the complete year test data set at Varanger and 0.922 at Yamal, reducing the number of images that required manual inspection to 7.9% of the original set from Varanger and 3.2% from Yamal. C_LIO_LIResearchers can modify this multi-step process to meet their specific needs for monitoring and surveying wildlife, providing greater flexibility than current options available for image classification. C_LI

ecology↗

bioRxiv2022

A semi-automatic workflow to process camera trap images in R

Camera traps have become popular for monitoring biodiversity and animal populations. Artificial intelligence is increasingly used to automatically classify large image data sets produced by camera traps and many tools that incorporate machine-learning models for automatic image classification have been developed over the last years. However, it is still challenging to combine tools for automatic classification with other tools for processing camera trap images and to adapt these tools to a specific study. Therefore, we propose a semi-automatic workflow for processing camera trap images in R. The workflow includes managing raw images, automatic image classification, a quality check of automatic image labels as well as the possibilities to retrain the model with new images and to manually review subsets of images to correct image labels. We illustrate the workflow with a case-study from the small mammal monitoring program of the Climate-ecological Observatory for Arctic Tundra. We first trained a classification model for small mammals and then transferred the model to new images, including images from newly established camera traps. We could show that retraining the original model with a small number of new images increased model performance and therefore highlight the importance of verifying automatic image labels when a model was transferred to new images. Furthermore, retraining the original model also decreased the time needed for manually reviewing images and correcting image labels substantially. Thus, the proposed workflow results in a data set with high accuracy and minimizes time needed for labeling images manually. This is especially useful for long-term monitoring where new images have to be processed continuously and methods have to be adapted over time. We provide all R scripts and the classification model for small mammals to make the workflow accessible to other ecologists.

ecology↗

bioRxiv2020

A dynamic and hierarchical spatial occupancy model for interacting species

Occupancy models have been extended to account for either multiple spatial scales or species interactions in a dynamic setting. However, as interacting species (e.g., predators and prey) often operate at different spatial scales, including nested spatial structure might be especially relevant to models of interacting species. Here we bridge these two model frameworks by developing a multi-scale, two-species occupancy model. The model is dynamic, i.e. it estimates initial occupancy, colonization and extinction probabilities--including probabilities conditional to the other species presence. With a simulation study, we demonstrate that the model is able to estimate most parameters without marked bias under low, medium and high average occupancy probabilities, as well as low, medium and high detection probabilities, with only a small bias for some parameters in low-detection scenarios. We further evaluate the models ability to deal with sparse field data by applying it to a multi-scale camera trapping dataset on a mustelid-rodent predator-prey system. Most parameters are estimated with low uncertainty (i.e. narrow posterior distributions). More broadly, our model framework creates opportunities to explicitly account for the spatial structure found in many spatially nested study designs, and to study interacting species that have contrasting movement ranges with camera traps.

ecology↗