Efficient resource management in UAVs for Visual Assistance

TL;DR

This paper presents a novel method to optimize real-time visual processing tasks on UAVs, reducing memory and power usage without compromising accuracy or flight time, enabling efficient deployment of deep learning models in resource-constrained UAV hardware.

Contribution

It introduces an innovative optimization approach tailored for UAV hardware that maintains model performance while reducing resource consumption.

Findings

Significant reduction in memory usage and power consumption.

Maintained accuracy and latency in object detection and tracking.

Enhanced feasibility of deploying deep learning models on low-end UAV processors.

Abstract

There is an increased interest in the use of Unmanned Aerial Vehicles (UAVs) for agriculture, military, disaster management and aerial photography around the world. UAVs are scalable, flexible and are useful in various environments where direct human intervention is difficult. In general, the use of UAVs with cameras mounted to them has increased in number due to their wide range of applications in real life scenarios. With the advent of deep learning models in computer vision many models have shown great success in visual tasks. But most of evaluation models are done on high end CPUs and GPUs. One of major challenges in using UAVs for Visual Assistance tasks in real time is managing the memory usage and power consumption of the these tasks which are computationally intensive and are difficult to be performed on low end processor board of the UAV. This projects describes a novel method to optimize the general image processing tasks like object tracking and object detection for UAV hardware in real time scenarios without affecting the flight time and not tampering the latency and accuracy of these models.