Flight Tracker

Technology it uses

• Stereo Thermal Cameras Two thermal sensors with calibrated relative geometry, used to reconstruct 3D flight tracks (height, range, speed) from overlapping views. Deployed at wind-farm sites for collision-risk assessment and at cave entrances for altitude-aware emergence counts.
• Stereo Colour Cameras Calibrated stereo colour camera pairs for high-resolution visual capture and species-ID-grade snippet extraction at wind energy sites. Used alongside thermal stereo for daytime collision-risk work and curtailment-relevant species classification.
• Wildlife Radar X-band micro-Doppler wildlife radar for continuous aerial biomass monitoring across multi-kilometre ranges. Captures activity at heights and during conditions where optical or acoustic methods are blind. Central to wind-energy collision-risk monitoring.
• LiDAR Time-of-flight 3D point-cloud sensors used for two distinct purposes: quantitative cave structure and condition monitoring (geometry over time), and 3D bat flight tracking inside caves and at infrastructure for collision-risk calculation.
• GPS Tracking Sub-gram and altitude-capable GPS tags for individual-animal movement and flight-altitude data. The only practical way to get per-individual altitude for bats — population-level methods cannot resolve which individual flew where.
• Helikite Tethered helium kite carrying ultrasonic recording equipment to ~100 m altitude. The only practical method for recording bat echolocation in the rotor-swept zone of operating wind turbines without using the turbine itself as a platform.
• Field Platform The physical and electronic base that lets every monitoring system run unattended for months at a time. Custom Linux-based edge nodes with regulated solar power, satellite communications, hardened enclosures, integrated sensor I/O, and remote fleet management. Engineered for Pilbara heat and dust, NSW forests, cave humidity, and cyclone-rated installations.
• Visual Tracking Algorithms for associating detections over time into trajectories — Kalman-filter and pair-based tracking, ID-linking across frames, and 3D reconstruction from stereo views. Turns frame-level detections into per-individual flight tracks suitable for collision-risk analysis and emergence counting.
• Bulk ML Inference High-throughput cloud GPU pipelines for processing archived recordings. This supports retrospective surveys, classifier comparison, and rare-event searches across years of SongMeter, Anabat, or Pettersson audio. We use custom classifiers for Australian threatened species alongside re-engineered baselines such as BirdNET and Google Perch.
• Dashboards & Review Tools Client dashboards provide access, replay, and report downloads. Analyst review tools support annotation, model comparison, and confidence review. Together they turn model results into information clients can use in approvals and operations.