Skip to content
Open access

A Copy-and-Paste Augmentation Framework for Human Detection in Oblique Drone Imagery

Sep 2026 · Drones · Vol 10, pp. 716 · 0 citations · 40 references

TL;DR

Results suggest that, under the acquisition conditions evaluated in this study, aligning pasted person size with the image-position-dependent perspective scale can improve the effectiveness of synthetic augmentation when the chip-level person-count distribution is controlled to match that of the real training data.

Abstract

Human detection in drone imagery is an important capability for applications that require information on the location and number of people, including search and rescue, urban pedestrian-flow analysis, crowd-density assessment, and public-space safety management. However, in oblique drone imagery, acquiring and annotating sufficient real data remains difficult because of crowd density, privacy constraints, background clutter, and position-dependent scale variation. This study proposes a copy-and-paste-based synthetic data augmentation procedure for imagery acquired using a DJI Phantom 4 RTK under a 30° camera pitch angle and a 30 m flight altitude, following DJI search-and-rescue observation guidelines. The proposed procedure combines human-free drone background images with a public full-body human dataset and incorporates perspective-based geometry-aware scaling, context-aware placement, and density-matched chip selection based on real person-count distributions. Three YOLO-family detectors (YOLOv8x, YOLO11x, and YOLO26x) and the Transformer-based RT-DETR-X were evaluated at three real-data proportions (10%, 25%, and 100%). Across these twelve combinations, four augmentation strategies (random, geometry-, context-, and combined geometry- and context-aware augmentation) were compared under the same 50% synthetic ratio. For the YOLO family, geometry-aware augmentation improved mAP50-95 in eight of the nine combinations and achieved a mean gain of +0.64 percentage points over the real-only baseline, with the largest gain of +1.99 percentage points under the YOLO11x 25% real-data condition. For RT-DETR-X, the corresponding changes were +0.23, −1.83, and −0.15 percentage points at 10%, 25%, and 100% real data, respectively. These results suggest that, under the acquisition conditions evaluated in this study, aligning pasted person size with the image-position-dependent perspective scale can improve the effectiveness of synthetic augmentation when the chip-level person-count distribution is controlled to match that of the real training data.

Read PDF

Similar papers

Open access 2026

An Intelligent Person Detection System for Public Spaces Using YOLOv11

The increasing use of camera-based monitoring in public spaces requires person detection systems that can operate across changes in illumination, viewpoint, background complexity, crowd density, and object scale. This paper presents an intelligent person detection framework based on YOLOv11m for open-area surveillance....

P. P. Aditya · 0 citations
Open access 2026

SL-YOLO: Scale- and Lighting-Aware Object Detection for Challenging UAV Imagery

Complex illumination, perspective-induced scale variation, and repeated downsampling degrade object representations in unmanned aerial vehicle (UAV) imagery and make small-object localization highly sensitive to pixel-level shifts. To address these issues, we propose Scale- and Lighting-Aware YOLO (SL-YOLO), a lightwei...

Heng-Sheng Cai, Yuan-Lin Wang, Li Zhao et al. · 0 citations
Open access Sep 2026

Human-in-the-loop collaborative enhancement for rotation-aware small object detection in aerial images

Small object detection in aerial images remains challenging due to low resolution, arbitrary orientation, complex background, and extreme sparsity of targets. Existing deep learning methods struggle with weak feature discrimination and insufficient context modeling for tiny targets, and they largely treat human kno...

Xing-Ye Qiu, Chen-Huan Chen, Li Zhang · 0 citations
Open access Sep 2026

SFC-DETR: a small object detection model for drone images based on spatial and frequency domain collaborative enhancement

A frequency-augmented polarity-aware attention module (FAPAM) that combines polarity-aware attention with adaptive frequency domain enhancement (SFC-DETR) is introduced that outperforms state-of-the-art models in small object detection tasks.

Zhi-Feng Zhang, Xiao-Bo Wen, Ming Chen et al. · 0 citations
Preprint Sep 2026

Small Object Detection in Drone Aerial Imagery with LAF-YOLOv10

General-purpose object detectors lose accuracy on UAV footage, where targets span only a handful of pixels and onboard compute is limited. Prior work composes independently-validated architectural techniques into one detector, assuming gains reported in isolation transfer once combined. We stress-test that assumption d...

Quratulain Nayeem, Fahmina Taranum, Mohammed Mudassir Uddin · 0 citations
Preprint Oct 2026

TriSAR-3D and PaintFusion: A Novel Trimodal LiDAR-RGB-Thermal Dataset and Method for 3D Person Detection in Search and Rescue

Reliable 3D person detection is important for rescue robotics to give first responders situational awareness. Yet most multimodal 3D detection research targets automotive scenarios in which pedestrians mostly appear in a narrow range of upright, near-road poses. It is therefore unclear how much of the reported performa...

Markus Kramer, Jan Wachenfeld, O. von Stryk · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.