• Home
  • Search
  • Speed-Up of Object Detection Neural Network with GPU
  • Cite Icon19
  • https://doi.org/10.1109/icip.2018.8451814Copy DOI Icon

Speed-Up of Object Detection Neural Network with GPU

  • Oct 1, 2018
  • Takuya Fukagai +6 more
Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

We realized a speed-up of an object detection neural network with GPU. We improved the object detection speed of faster R-CNN [1], which is one of the most commonly used detection networks [2]. The speed of the original faster R-CNN (py - faster - rcnn [3]) was 72.4ms per image on our GPU server 11OS: Ubuntu 14.04.5 LTS (GNU/Linux 4.2.0-42-generic x86_64), CPU: Intel(R) Xeon(R) CPU E5-2680 v4 @ 2.40GHz, GPU: GPU (Tesla P100-PCIE-16GB) x 1, Libraries: MKL, CUDA 8.0, cuDNN v5.1.5. We accelerated the detection speed by implementing our new algorithms that are suitable for GPUs. The speed-up is realized without sacrificing the object detection accuracy (mAP). Our GPU-accelerated faster R-CNN can detect objects with 55.8ms per image. This is nearly 30% speed-up. In detection networks, the processes of building scored candidate regions, sorting and non-maximum-suppression (nms) are commonly used. In faster R-CNN, these processes are executed in proposal layer. We reduced the processing time of the proposal layer from 5.6ms to 2.2ms. This is 2.5 times as fast as the original one. We also evaluated the detection speed with larger batch sizes. By applying batch size 16, it is accelerated to 44.9ms per image. This is 1.6 times as fast as the original faster R-CNN (py-faster-rcnn). Since we realized a speed-up of common basic methods for detection networks, our speed-up methods are also applicable to other detection networks such as R-FCN [4], YOLO [5] [6] and SSD [7].

Similar Papers
  • Conference Article
  • Citations38

Text Detection by Faster R-CNN with Multiple Region Proposal Networks

  • Nov 01, 2017
  • Yoshito Nagaoka +3
  • Research Article
  • Citations62

Improved YOLOv3-Based Bridge Surface Defect Detection by Combining High- and Low-Resolution Feature Images

  • Aug 12, 2022
  • Buildings
  • Shuai Teng +2
  • Research Article
  • Citations1

YOLO Vs Faster RCNN for Object Detection and Recognition

  • Jan 01, 2025
  • International Research Journal of Multidisciplinary Scope
  • Ranjana Shende +1
  • Research Article
  • Citations30

BDNN: Binary convolution neural networks for fast object detection

  • Apr 08, 2019
  • Pattern Recognition Letters
  • Hanyu Peng +1
  • Research Article

FASTER R-CNN DECODED: ELEVATING OBJECT DETECTION WITH PRECISION AND SPEED

  • Jan 20, 2024
  • International Research Journal of Modernization in Engineering Technology and Science
  • Shreya Panda +1
  • Research Article
  • Citations55620

Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks.

  • Jun 06, 2016
  • IEEE Transactions on Pattern Analysis and Machine Intelligence
  • Shaoqing Ren +3
  • PDF
  • Research Article
  • Citations1

Detection of objects in the image in streaming mode using YOLOv5 і Faster R-CNN

  • Mar 19, 2024
  • System technologies
  • Bozhukha Liliia +1
  • PDF
  • Research Article
  • Citations24

An Improved Faster R-CNN for Pulmonary Embolism Detection From CTPA Images

  • Jan 01, 2021
  • IEEE Access
  • Hongfang Yuan +3
  • Research Article
  • Citations8

Efficient approach to automated pavement manhole cover detection with modified faster R-CNN

  • Sep 01, 2022
  • Intelligent Transportation Infrastructure
  • Hang Zhang +8
  • PDF
  • Research Article
  • Citations39

High-Efficiency Classification of White Blood Cells Based on Object Detection

  • Sep 13, 2021
  • Journal of Healthcare Engineering
  • Jiangfan Yao +7
  • Research Article
  • Citations72

Detection Approach Based on an Improved Faster RCNN for Brace Sleeve Screws in High-Speed Railways

  • Sep 19, 2019
  • IEEE Transactions on Instrumentation and Measurement
  • Zhigang Liu +3
  • Book Chapter
  • Citations3

Rich Features and Precise Localization with Region Proposal Network for Object Detection

  • Jan 01, 2017
  • Mengdie Chu +3
  • Research Article
  • Citations15

A New Multi-scale Pedestrian Detection Algorithm in Traffic Environment

  • Feb 11, 2021
  • Journal of Electrical Engineering & Technology
  • Jin Ren +1
  • Research Article
  • Citations8

Research on efficient detection network method for remote sensing images based on self attention mechanism

  • Dec 17, 2023
  • Image and Vision Computing
  • Jing Li +1
  • Book Chapter

BackNet: An Enhanced Backbone Network for Accurate Detection of Objects with Large Scale Variations

  • Jan 01, 2019
  • Md Tahmid Hossain +2
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.