Cloud Chaser: Real Time Deep Learning Computer Vision on Low Computing Power Devices

TL;DR

This paper presents Cloud Chaser, a system that enables low-power devices like Raspberry Pi robots to perform real-time deep learning vision tasks by offloading computation to the cloud, using compression to reduce latency.

Contribution

It introduces a cloud-based approach for real-time deep learning on resource-constrained devices, including a prototype and video streaming compression techniques.

Findings

Effective offloading of deep learning tasks to the cloud

Compression algorithms reduce streaming latency

Demonstrated real-time vision on low-power devices

Abstract

Internet of Things(IoT) devices, mobile phones, and robotic systems are often denied the power of deep learning algorithms due to their limited computing power. However, to provide time-critical services such as emergency response, home assistance, surveillance, etc, these devices often need real-time analysis of their camera data. This paper strives to offer a viable approach to integrate high-performance deep learning-based computer vision algorithms with low-resource and low-power devices by leveraging the computing power of the cloud. By offloading the computation work to the cloud, no dedicated hardware is needed to enable deep neural networks on existing low computing power devices. A Raspberry Pi based robot, Cloud Chaser, is built to demonstrate the power of using cloud computing to perform real-time vision tasks. Furthermore, to reduce latency and improve real-time performance, compression algorithms are proposed and evaluated for streaming real-time video frames to the cloud.