Advanced Human Detection for Collapsed Structure Search and Rescue Using Drone

Search and rescue operations in areas affected by earthquake, landslide, and structural collapse are difficult due to the unstable nature of the debris, low visibility, and difficult environment. In this paper, we suggest a multi-sensor system on drones to facilitate remote sensing of disaster areas. The system is composed of the UAV platform, flight controller, GPS unit, visual webcam, thermal sensor, microwave motion sensor, environmental and gas sensors and distance sensor. A computer vision system based on a pre-trained YOLO model is suggested for detection of visible people in the webcam images. Fine-tuning of the model can be done using annotated images in similar search and rescue environments and tested based on existing object detection metrics. The microwave motion sensor is used for additional motion sensing, and other sensors give additional thermal, environmental, and distance data. This data will help rescue personnel identify areas that need to be investigated further. The suggested system includes a robotic arm that will facilitate the controlled delivery of a light-weight first aid kit at an easily accessible point near the potential survivor. The system cannot independently verify the presence of an invisible person or determine the state of health of the person.

Authors

Publication Details

Journal
Preprints.org
Published
2026-11-18
DOI
https://doi.org/10.20944/preprints202611.1777.v1
Primary Topic
Advanced Neural Network Applications
Type
preprint
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
preprint

Advanced Human Detection for Collapsed Structure Search and Rescue Using Drone

Dharanesh M, K. Anusindhiya, Shree Nivas K S, Rahul Srinivas P
Preprints.org
Advanced Neural Network Applications
preprint

Advanced Human Detection for Collapsed Structure Search and Rescue Using Drone

Dharanesh M, K. Anusindhiya, Shree Nivas K S, Rahul Srinivas P
preprint en

Abstract

Search and rescue operations in areas affected by earthquake, landslide, and structural collapse are difficult due to the unstable nature of the debris, low visibility, and difficult environment. In this paper, we suggest a multi-sensor system on drones to facilitate remote sensing of disaster areas. The system is composed of the UAV platform, flight controller, GPS unit, visual webcam, thermal sensor, microwave motion sensor, environmental and gas sensors and distance sensor. A computer vision system based on a pre-trained YOLO model is suggested for detection of visible people in the webcam images. Fine-tuning of the model can be done using annotated images in similar search and rescue environments and tested based on existing object detection metrics. The microwave motion sensor is used for additional motion sensing, and other sensors give additional thermal, environmental, and distance data. This data will help rescue personnel identify areas that need to be investigated further. The suggested system includes a robotic arm that will facilitate the controlled delivery of a light-weight first aid kit at an easily accessible point near the potential survivor. The system cannot independently verify the presence of an invisible person or determine the state of health of the person.

Preprints.org
Advanced Neural Network Applications
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon