• Home
  • Search
  • Parallel Detection for Efficient Video Analytics at the Edge
  • Open Access IconOpen Access
  • Cite Icon12
  • https://doi.org/10.1109/cogmi52975.2021.00035Copy DOI Icon

Parallel Detection for Efficient Video Analytics at the Edge

  • Dec 1, 2021
  • Yanzhao Wu +2 more
Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Deep Neural Network (DNN) trained object detec-tors are widely deployed in many mission-critical systems for real time video analytics at the edge, such as autonomous driving, video surveillance and Internet of smart cameras. A common per-formance requirement in these mission-critical edge services is the near real-time latency of online object detection on edge devices. However, even with well-trained DNN object detectors, the online detection quality at edge may deteriorate for a number of reasons, such as limited capacity to run DNN object detection models on heterogeneous edge devices, and detection quality degradation due to random frame dropping when the detection processing rate is significantly slower than the incoming video frame rate. This paper addresses these problems by exploiting multi-model multi-device detection parallelism for fast object detection in edge systems with heterogeneous edge devices. First, we analyze the performance bottleneck of running a well-trained DNN model at edge for real time online object detection. We use the offline detection as a reference model, and examine the root cause by analyzing the mismatch among the incoming video streaming rate, the video processing rate for object detection, and the output rate for real time detection visualization of video streaming. Second, we study performance optimizations by exploiting multi-model detection parallelism. We show that the model-parallel detection approach can effectively speed up the FPS detection processing rate, minimizing the FPS disparity with the incoming video frame rate on heterogeneous edge devices. We evaluate the proposed approach using SSD300 and YOLOv3 (pre-trained DNN models) on benchmark videos of different video stream rates. The results show that exploiting multi-model detection parallelism can speed up the online object detection processing rate and deliver near real-time object detection performance for efficient video analytics at edge.

Similar Papers
  • Conference Article
  • Citations2

Model Parallelism Optimization for Distributed DNN Inference on Edge Devices

  • Nov 24, 2023
  • Meng Wang +4
  • Conference Article

RACI: A Resource-Aware Cooperative Inference Framework on Heterogeneous Edge Devices

  • Oct 27, 2024
  • Zhenyu Wang +6
  • Conference Article
  • Citations6

Towards Resource-aware DNN Partitioning for Edge Devices with Heterogeneous Resources

  • Dec 04, 2022
  • Muhammad Zawish +3
  • Conference Article
  • Citations5

Comparative analysis on Deep Convolution Neural Network models using Pytorch and OpenCV DNN frameworks for identifying optimum fruit detection solution on RISC-V architecture

  • Oct 24, 2021
  • Shalini K +3
  • Book Chapter
  • Citations1

A Hot/Cold Task Partition for Energy-Efficient Neural Network Deployment on Heterogeneous Edge Device

  • Jan 01, 2020
  • Jihe Wang +2
  • Research Article
  • Citations20

Split computing: DNN inference partition with load balancing in IoT-edge platform for beyond 5G

  • Aug 18, 2022
  • Measurement: Sensors
  • Jyotirmoy Karjee +3
  • Research Article
  • Citations1

Enhancing Collaborative Inference on Heterogeneous Edge Devices via Adaptive Ensemble Knowledge Distillation

  • Jan 01, 2025
  • IEEE Journal on Selected Areas in Communications
  • Shangrui Wu +9
  • Conference Article
  • Citations3

Placement of DNN Models on Mobile Edge Devices for Effective Video Analysis

  • Dec 15, 2021
  • George Constantinou +2
  • Research Article
  • Citations30

Self-aware distributed deep learning framework for heterogeneous IoT edge devices

  • Jul 14, 2021
  • Future Generation Computer Systems
  • Yi Jin +8
  • Conference Article
  • Citations18

Automating Deep Neural Network Model Selection for Edge Inference

  • Dec 01, 2019
  • Bingqian Lu +3
  • Research Article
  • Citations28

A comparative evaluation of deep convolutional neural network and deep neural network-based land use/land cover classifications of mining regions using fused multi-sensor satellite data

  • Sep 04, 2023
  • Advances in Space Research
  • Ajay Kumar +1
  • Research Article
  • Citations45

EC²Detect: Real-Time Online Video Object Detection in Edge-Cloud Collaborative IoT

  • Oct 15, 2022
  • IEEE Internet of Things Journal
  • Siyan Guo +4
  • Research Article
  • Citations6

Joint Protection Scheme for Deep Neural Network Hardware Accelerators and Models

  • Dec 01, 2023
  • IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems
  • Jingbo Zhou +1
  • Research Article
  • Citations5

Towards Hardware Supported Domain Generalization in DNN-Based Edge Computing Devices for Health Monitoring.

  • Feb 01, 2025
  • IEEE transactions on biomedical circuits and systems
  • Johnson Loh +3
  • Conference Article
  • Citations27

EdgeFaaSBench: Benchmarking Edge Devices Using Serverless Computing

  • Jul 01, 2022
  • Kaustubh Rajendra Rajput +4
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.