EKF-Based Depth Camera and Deep Learning Fusion for UAV-Person Distance Estimation and Following in SAR Operations
arXiv:2602.20958v2 Announce Type: replace-cross Abstract: Vision-based Unmanned Aerial Vehicles (UAVs) frameworks aid human search tasks by detecting and recognizing specific individuals, then tracking and following them while maintaining a safe distance. A key safety requirement for UAV following is the accurate estimation of the distance between camera and target object under real-world conditions, achieved by fusing multiple image modalities. As part of the system for automatic people detection and face recognition using deep learning, in this paper we present the fusion of depth camera mea
The increasing sophistication of vision-based AI and miniaturized hardware allows for complex autonomous functions like UAV-person tracking to move from theoretical research to practical application, especially in critical sectors.
This development enhances the capabilities of autonomous systems in critical applications such as search and rescue, offering precise, real-time tracking and safety assurance in dynamic environments.
The ability of UAVs to accurately estimate distance and safely follow individuals using sensor fusion and deep learning moves beyond basic object detection, enabling more reliable and autonomous human-UAV interaction.
- · Search and Rescue organizations
- · UAV manufacturers
- · AI/Computer Vision developers
- · Defence and Security industries
- · Traditional manned SAR operations
Improved efficiency and safety in search and rescue missions due to enhanced UAV autonomy.
Expansion of UAV applications to other human-centric tasks requiring precise proximity control and interaction.
Ethical and regulatory discussions around autonomous systems' interaction with humans, particularly concerning data privacy and control in sensitive contexts.
This signal links to a primary source. Continuum Brief monitors and indexes it as part of the live intelligence stream — we do not republish source content.
Read at arXiv cs.AI