Work

Fly High or Fly Low? Selecting Time-Efficient UAV Search Strategies for High-Recall Aerial Detection

Year: 2026

Type: article

Abstract: The use of uncrewed aerial vehicles (UAVs) for remote sensing continues to increase, and, in missions such as search and rescue (SAR) and landmine detection, a vision-based detector with high recall is critical. Flying at a higher altitude covers a larger area in each pass but enlarges the ground sample distance, reducing recall and precision. Recall can be maintained by lowering the detector’s confidence threshold, at the cost of precision. In those instances, any additional false positives can be resolved by a verification flight. This work compares two strategies for completing a survey in the minimum time while maintaining high recall. Strategy 1 surveys the entire area at a constant low altitude, where precision is high enough that flagged locations need no verification. Strategy 2 performs a rapid high-altitude survey, then visits each flagged location on a low-altitude verification flight, ordered efficiently by a Travelling Salesman Problem (TSP) solver. Experimental results indicate that Strategy 1 is more effective when targets are dense, and Strategy 2 when targets are sparse, provided its survey altitude is well above the verification altitude. Our approach also generates a decision table and a break-even altitude ratio that mission planners can use to select the better strategy from the estimated target density and the detector’s measured false-positive rate.

Source: Remote Sensing

DOI: 10.3390/rs18183129

Authors: Frank Loewenich, Frederic Maire, Juan Sandino, Felipe Gonzalez

Institution: Queensland University of Technology

Language: English

Topic: UAV Applications and Optimization

Subfield: Aerospace Engineering

Field: Engineering

Domain: Physical Sciences

Open Access status: gold

Estimated APC paid: $3,258

Funder: Australian Research Council