Extended Abstract Version: CNN-based Human Detection System for UAVs in Search and Rescue

TL;DR

This paper presents a CNN-based human detection system integrated with a quadcopter for search and rescue, demonstrating effective performance on a Raspberry Pi B despite sensor noise challenges.

Contribution

It introduces a CNN-powered detection system on a UAV platform using low-cost hardware and addresses sensor noise issues for real-time search and rescue applications.

Findings

System achieves 3 fps processing speed on Raspberry Pi B.

Sensor noise mitigation improves detection reliability.

Effective integration of CNN with UAV hardware for rescue tasks.

Abstract

This paper proposes an approach for the task of searching and detecting human using a convolutional neural network and a Quadcopter hardware platform. A pre-trained CNN model is applied to a Raspberry Pi B and a single camera is equipped at the bottom of the Quadcopter. The Quadcopter uses accelerometer-gyroscope sensor and ultrasonic sensor for balancing control. However, these sensors are susceptible to noise caused by the driving forces such as the vibration of the motors, thus, noise processing is implemented. Experiments proved that the system works well on the Raspberry Pi B with a processing speed of 3 fps.