Radar + Smart Tagging for Detecting Hard-to-See Ticks and Other Small Organisms

Field teams and animal health operators struggle to locate ticks and other tiny organisms because they often remain hidden in vegetation, soil debris, or animal fur where cameras and manual sampling fail. This technology combines a non-invasive, paintable metallic tagging concept with millimeter-wave radar sensing and AI-based signal interpretation so that tagged organisms can be detected even when they are visually occluded. Compared with today's status quo (visual inspection, drag/flag sampling, and lab-based identification), it is expected to reduce labor and enable more frequent, automated monitoring while preserving operation in low-visibility environments. In lab-style evaluations, the approach demonstrated reliable detection of tick-sized organisms under organic occlusion and across different specimen conditions. The platform approach is designed to be extended by retraining models for other small organisms or small tagged items, and it can be integrated into automated monitoring rigs or mobile robotic systems. If productized, it could improve decision-making for vector surveillance and pest management by providing near-real-time presence/absence and location cues without requiring optical access.

Technology Validation:

System-level tests were performed using tick-sized arthropods as the initial model target, including scenarios where the targets were hidden by layers of natural/organic materials. Radar returns from tagged targets were analyzed with machine-learning classifiers to separate target signatures from background clutter. These evaluations demonstrated that the combined tagging-and-radar approach can detect targets that are difficult to observe with conventional optical methods.

Advantages:

-Operates when the target is not visible (works through common organic occluders), addressing a major field constraint.

-Non-invasive tagging approach avoids bulky electronic transponders and is compatible with very small targets.

-AI-based interpretation improves robustness in cluttered environments without requiring complex user intervention.

-Supports automation: can be mounted on stationary monitoring systems or integrated onto mobile/robotic platforms.

-Platform extensibility: new targets can be supported through model retraining and workflow adaptation.

Applications:

-Public health vector surveillance (automated monitoring of tick presence in endemic areas).

-Livestock and companion-animal health monitoring (screening for parasite presence without exhaustive manual checks).

-Agricultural pest detection in crop canopies or ground cover where optical inspection is unreliable.

-Ecology and wildlife research (tracking small, tagged organisms in naturalistic settings).

-Laboratory bioassays (objective, automated counting/monitoring of small organisms under controlled occlusion).

TRL: 4

Intellectual Property:

Provisional-Patent, 2026-03-11, United States