ESOD:Edge-based Task Scheduling for Object Detection

10/20/2021
by   Yihao Wang, et al.
0

Object Detection on the mobile system is a challenge in terms of everything. Nowadays, many object detection models have been designed, and most of them concentrate on precision. However, the computation burden of those models on mobile systems is unacceptable. Researchers have designed some lightweight networks for mobiles by sacrificing precision. We present a novel edge-based task scheduling framework for object detection (termed as ESOD). In detail, we train a DNN model (termed as pre-model) to predict which object detection model to use for the coming task and offloads to which edge servers by physical characteristics of the image task (e.g., brightness, saturation). The results show that ESOD can reduce latency and energy consumption by an average of 22.13 respectively, compared with the SOTA DETR model.

READ FULL TEXT

page 2

page 5

research
08/16/2021

AdaCon: Adaptive Context-Aware Object Detection for Resource-Constrained Embedded Devices

Convolutional Neural Networks achieve state-of-the-art accuracy in objec...
research
01/15/2022

Realtime 3D Object Detection for Headsets

Mobile headsets should be capable of understanding 3D physical environme...
research
08/29/2021

Edge-Cloud Collaborated Object Detection via Difficult-Case Discriminator

As one of the basic tasks of computer vision, object detection has been ...
research
07/16/2020

VIPriors Object Detection Challenge

This paper is a brief report to our submission to the VIPriors Object De...
research
06/19/2019

ViP: Virtual Pooling for Accelerating CNN-based Image Classification and Object Detection

In recent years, Convolutional Neural Networks (CNNs) have shown superio...
research
11/26/2020

Energy Drain of the Object Detection Processing Pipeline for Mobile Devices: Analysis and Implications

Applying deep learning to object detection provides the capability to ac...
research
07/10/2014

ARTOS -- Adaptive Real-Time Object Detection System

ARTOS is all about creating, tuning, and applying object detection model...

Please sign up or login with your details

Forgot password? Click here to reset