KAMERA: Enhancing Aerial Surveys of Ice-associated Seals in Arctic Environments

2025-09-23

AI Summary

To address challenges in aerial surveys of ice-edge seals in the Arctic—including real-time detection difficulties, slow data processing, and low-accuracy multi-source image fusion—this study develops an open-source multispectral synchronous aerial monitoring system. The system integrates visible-light and short-wave infrared (SWIR) cameras, achieving cross-spectral target co-detection via hardware-level temporal synchronization and rigorous geometric-radiometric calibration. We propose a lightweight real-time detection model and establish precise geospatial mapping between detections and geographic coordinates, enabling automated identification of seals and polar bears as well as accurate estimation of survey area extent. Compared to conventional manual interpretation, the system improves data processing efficiency by 80%, while significantly enhancing detection accuracy and spatial consistency. This work establishes a reproducible, scalable technical paradigm for polar wildlife monitoring.

Technology Category

• Computer Vision: Remote Sensing / Geospatial AI
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Machine Learning: Multimodal Learning

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Web Mining and Content Analysis: Mining multimedia, multimodal, multilingual, cross-lingual Web data

Abstract

We introduce KAMERA: a comprehensive system for multi-camera, multi-spectral synchronization and real-time detection of seals and polar bears. Utilized in aerial surveys for ice-associated seals in the Bering, Chukchi, and Beaufort seas around Alaska, KAMERA provides up to an 80% reduction in dataset processing time over previous methods. Our rigorous calibration and hardware synchronization enable using multiple spectra for object detection. All collected data are annotated with metadata so they can be easily referenced later. All imagery and animal detections from a survey are mapped onto a world plane for accurate surveyed area estimates and quick assessment of survey results. We hope KAMERA will inspire other mapping and detection efforts in the scientific community, with all software, models, and schematics fully open-sourced.

Problem

• Developing a multi-spectral aerial system for seal detection
• Reducing data processing time in Arctic wildlife surveys
• Enabling accurate mapping of animal detections from surveys

Innovation

• Multi-camera multi-spectral synchronization system
• Real-time detection for seals and polar bears
• Open-sourced software and models for mapping