Integrating Biological Data into Autonomous Remote Sensing Systems for In Situ Imageomics: A Case Study for Kenyan Animal Behavior Sensing with Unmanned Aerial Vehicles (UAVs)
Jenna M. Kline, Maksim Kholiavchenko, Otto Brookes, Tanya Berger-Wolf, Charles V. Stewart, Christopher Stewart
TL;DR
The paper addresses data bottlenecks in in situ imageomics and proposes a telemetry-guided autonomous UAV framework to optimize wildlife behavior data collection in Kenya. Using the KABR dataset, it couples YOLO-based localization and behavior extraction with altitude- and movement-aware navigation to maximize usable frames. The enhanced model improves accuracy by 18.2 percent and F1 by 8.3 percent over a prior approach, while clarifying altitude and bounding-box regimes that maximize data usability (e.g., typical bounding boxes around 106 by 110 pixels). This work provides practical guidelines for deploying autonomous UAVs in wildlife monitoring and lays groundwork for behavior-aware flight strategies and reinforcement-learning approaches.
Abstract
In situ imageomics leverages machine learning techniques to infer biological traits from images collected in the field, or in situ, to study individuals organisms, groups of wildlife, and whole ecosystems. Such datasets provide real-time social and environmental context to inferred biological traits, which can enable new, data-driven conservation and ecosystem management. The development of machine learning techniques to extract biological traits from images are impeded by the volume and quality data required to train these models. Autonomous, unmanned aerial vehicles (UAVs), are well suited to collect in situ imageomics data as they can traverse remote terrain quickly to collect large volumes of data with greater consistency and reliability compared to manually piloted UAV missions. However, little guidance exists on optimizing autonomous UAV missions for the purposes of remote sensing for conservation and biodiversity monitoring. The UAV video dataset curated by KABR: In-Situ Dataset for Kenyan Animal Behavior Recognition from Drone Videos required three weeks to collect, a time-consuming and expensive endeavor. Our analysis of KABR revealed that a third of the videos gathered were unusable for the purposes of inferring wildlife behavior. We analyzed the flight telemetry data from portions of UAV videos that were usable for inferring wildlife behavior, and demonstrate how these insights can be integrated into an autonomous remote sensing system to track wildlife in real time. Our autonomous remote sensing system optimizes the UAV's actions to increase the yield of usable data, and matches the flight path of an expert pilot with an 87% accuracy rate, representing an 18.2% improvement in accuracy over previously proposed methods.