What Frame-Level Labels Can and Cannot Do for Small-UAV Point Detection in Thermal Video

Key points

• We focus on learning localization from frame-level target presence/absence labels when sensor or scene changes make spatial annotations for additional training burdensome.1
• We analyze the detection capability, learning behavior, and potential applications of an existing architecture for point detection of small UAVs, trained with presence/absence labels and requiring no external detector.1
• On two thermal infrared datasets, CST Anti-UAV and Anti-UAV410, we evaluate localization hit rates and detection rates under false-alarm constraints, analyze the effects of training stages, label allocation, synthesis, and model configuration, and compare with bounding-box detectors.1
• We also explore potential applications on Airborne Object Tracking (AOT) using its visible-light imagery and frame labels.1

Sources (1)

• [1]What Frame-Level Labels Can and Cannot Do for Small-UAV Point Detection in Thermal Video
  arXiv (AI, ML, NLP, CV, robotics, multi-agent) · Oct 6, 03:58 AM

  The growing use of unmanned aerial vehicles (UAVs) has increased the importance of image-based UAV detection.

  We focus on learning localization from frame-level target presence/absence labels when sensor or scene changes make spatial annotations for additional training burdensome.

Extractive summary: sentences quoted from the sources.