Search for: All records

Access to large image volumes through camera traps and crowdsourcing provides novel possibilities for animal monitoring and conservation. It calls for automatic methods for analysis, in particular, when re-identifying individual animals from the images. Most existing re-identification methods rely on either hand-crafted local features or end-to-end learning of fur pattern similarity. The former does not need labeled training data, while the latter, although very data-hungry typically outperforms the former when enough training data is available. We propose a novel re-identification pipeline that combines the strengths of both approaches by utilizing modern learnable local features and feature aggregation. This creates representative pattern feature embeddings that provide high re-identification accuracy while allowing us to apply the method to small datasets by using pre-trained feature descriptors. We report a comprehensive comparison of different modern local features and demonstrate the advantages of the proposed pipeline on two very different species.

 

This team science case study explores one cross-disciplinary science institute's change process for redesigning a weekly research coordination meeting. The narrative arc follows four stages of the adaptive process in complex adaptive systems: disequilibrium, amplification, emergence, and new order.

This case study takes an interpretative, participatory approach, where the objective is to understand the phenomena within the social context and deepen understanding of how the process unfolds over time and in context. Multiple data sources were collected and analyzed.

A new adaptive order for the weekly research coordination meeting was established. The mechanism for the success of the change initiative was best explained by complexity leadership theory.

Implications for team science practice include generating momentum for change, re-examining power dynamics, defining critical teaming professional roles, building multiple pathways towards team capacity development, and holding adaptive spaces. Promising areas for further exploration are also presented.

 

Image‐based machine learning tools are an ascendant ‘big data’ research avenue. Citizen science platforms, like iNaturalist, and museum‐led initiatives provide researchers with an abundance of data and knowledge to extract. These include extraction of metadata, species identification, and phenomic data. Ecological and evolutionary biologists are increasingly using complex, multi‐step processes on data. These processes often include machine learning techniques, often built by others, that are difficult to reuse by other members in a collaboration.

We present a conceptual workflow model for machine learning applications using image data to extract biological knowledge in the emerging field of imageomics. We derive an implementation of this conceptual workflow for a specific imageomics application that adheres to FAIR principles as a formal workflow definition that allows fully automated and reproducible execution, and consists of reusable workflow components.

We outline technologies and best practices for creating an automated, reusable and modular workflow, and we show how they promote the reuse of machine learning models and their adaptation for new research questions. This conceptual workflow can be adapted: it can be semi‐automated, contain different components than those presented here, or have parallel components for comparative studies.

We encourage researchers—both computer scientists and biologists—to build upon this conceptual workflow that combines machine learning tools on image data to answer novel scientific questions in their respective fields.

 

Acquiring accurate 3D biological models efficiently and economically is important for morphological data collection and analysis in organismal biology. In recent years, structure-from-motion (SFM) photogrammetry has become increasingly popular in biological research due to its flexibility and being relatively low cost. SFM photogrammetry registers 2D images for reconstructing camera positions as the basis for 3D modeling and texturing. However, most studies of organismal biology still relied on commercial software to reconstruct the 3D model from photographs, which impeded the adoption of this workflow in our field due the blocking issues such as cost and affordability. Also, prior investigations in photogrammetry did not sufficiently assess the geometric accuracy of the models reconstructed. Consequently, this study has two goals. First, we presented an affordable and highly flexible SFM photogrammetry pipeline based on the open-source package OpenDroneMap (ODM) and its user interface WebODM. Second, we assessed the geometric accuracy of the photogrammetric models acquired from the ODM pipeline by comparing them to the models acquired via microCT scanning, the de facto method to image skeleton. Our sample comprised 15 Aplodontia rufa (mountain beaver) skulls. Using models derived from microCT scans of the samples as reference, our results showed that the geometry of the models derived from ODM was sufficiently accurate for gross metric and morphometric analysis as the measurement errors are usually around or below 2%, and morphometric analysis captured consistent patterns of shape variations in both modalities. However, subtle but distinct differences between the photogrammetric and microCT-derived 3D models could affect the landmark placement, which in return affected the downstream shape analysis, especially when the variance within a sample is relatively small. At the minimum, we strongly advise not combining 3D models derived from these two modalities for geometric morphometric analysis. Our findings can be indictive of similar issues in other SFM photogrammetry tools since the underlying pipelines are similar. We recommend that users run a pilot test of geometric accuracy before using photogrammetric models for morphometric analysis. For the research community, we provide detailed guidance on using our pipeline for building 3D models from photographs.

 

Inexpensive and accessible sensors are accelerating data acquisition in animal ecology. These technologies hold great potential for large-scale ecological understanding, but are limited by current processing approaches which inefficiently distill data into relevant information. We argue that animal ecologists can capitalize on large datasets generated by modern sensors by combining machine learning approaches with domain knowledge. Incorporating machine learning into ecological workflows could improve inputs for ecological models and lead to integrated hybrid modeling tools. This approach will require close interdisciplinary collaboration to ensure the quality of novel approaches and train a new generation of data scientists in ecology and conservation.

 

We present a novel usage of Transformers to make image classification interpretable. Unlike mainstream classifiers that wait until the last fully connected layer to incorporate class information to make predictions, we investigate a proactive approach, asking each class to search for itself in an image. We realize this idea via a Transformer encoder-decoder inspired by DEtection TRansformer (DETR). We learn “class-specific” queries (one for each class) as input to the decoder, enabling each class to localize its patterns in an image via cross-attention. We name our approach INterpretable TRansformer (INTR), which is fairly easy to implement and exhibits several compelling properties. We show that INTR intrinsically encourages each class to attend distinctively; the cross-attention weights thus provide a faithful interpretation of the prediction. Interestingly, via “multi-head” cross-attention, INTR could identify different “attributes” of a class, making it particularly suitable for fine-grained classification and analysis, which we demonstrate on eight datasets. Our code and pre-trained models are publicly accessible at the Imageomics Institute GitHub site: https://github.com/Imageomics/INTR. 

We present a novel dataset for animal behavior recognition collected in-situ using video from drones flown over the Mpala Research Centre in Kenya. Videos from DJI Mavic 2S drones flown in January 2023 were acquired at 5.4K resolution in accordance with IACUC protocols, and processed to detect and track each animal in the frames. An image subregion centered on each animal was extracted and combined in sequence to form a “mini-scene”. Be-haviors were then manually labeled for each frame of each mini-scene by a team of annotators overseen by an expert behavioral ecologist. The resulting labeled mini-scenes form our resulting behavior dataset, consisting of more than 10 hours of annotated videos of reticulated gi-raffes, plains zebras, and Grevy's zebras, and encompassing seven types of animal behavior and an additional category for occlusions. Benchmark results for state-of-the-art behavioral recognition architectures show labeling accu-racy of 61.9% for macro-average (per class), and 86.7% for micro-average (per instance). Our dataset complements recent larger, more diverse animal behavior sets and smaller, more specialized ones by being collected in-situ and from drones, both important considerations for the future of an-imal behavior research. The dataset can be accessed at https://dirtmaxim.github.io/kabr. 

In late December 1973, the United States enacted what some would come to call “the pitbull of environmental laws.” In the 50 years since, the formidable regulatory teeth of the Endangered Species Act (ESA) have been credited with considerable successes, obliging agencies to draw upon the best available science to protect species and habitats. Yet human pressures continue to push the planet toward extinctions on a massive scale. With that prospect looming, and with scientific understanding ever changing,Scienceinvited experts to discuss how the ESA has evolved and what its future might hold.—Brad Wible

 

In situ imageomics is a new approach to study ecological, biological and evolutionary systems wherein large image and video data sets are captured in the wild and machine learning methods are used to infer biological traits of individual organisms, animal social groups, species, and even whole ecosystems. Monitoring biological traits over large spaces and long periods of time could enable new, data-driven approaches to wildlife conservation, biodiversity, and sustainable ecosystem management. However, to accurately infer biological traits, machine learning methods for images require voluminous and high quality data. Adaptive, data-driven approaches are hamstrung by the speed at which data can be captured and processed. Camera traps and unmanned aerial vehicles (UAVs) produce voluminous data, but lose track of individuals over large areas, fail to capture social dynamics, and waste time and storage on images with poor lighting and view angles. In this vision paper, we make the case for a research agenda for in situ imageomics that depends on significant advances in autonomic and self-aware computing. Precisely, we seek autonomous data collection that manages camera angles, aircraft positioning, conflicting actions for multiple traits of interest, energy availability, and cost factors. Given the tools to detect object and identify individuals, we propose a research challenge: Which optimization model should the data collection system employ to accurately identify, characterize, and draw inferences from biological traits while respecting a budget? Using zebra and giraffe behavioral data collected over three weeks at the Mpala Research Centre in Laikipia County, Kenya, we quantify the volume and quality of data collected using existing approaches. Our proposed autonomic navigation policy for in situ imageomics collection has an F1 score of 82% compared to an expert pilot, and provides greater safety and consistency, suggesting great potential for state-of-the-art autonomic approaches if they can be scaled up to fully address the problem.