• Home
  • Search
  • A Multi-Scale Target Detection Method Using an Improved Faster Region Convolutional Neural Network Based on Enhanced Backbone and Optimized Mechanisms.
  • Cite Icon8
  • https://doi.org/10.3390/jimaging10080197Copy DOI Icon

A Multi-Scale Target Detection Method Using an Improved Faster Region Convolutional Neural Network Based on Enhanced Backbone and Optimized Mechanisms.

Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Currently, existing deep learning methods exhibit many limitations in multi-target detection, such as low accuracy and high rates of false detection and missed detections. This paper proposes an improved Faster R-CNN algorithm, aiming to enhance the algorithm's capability in detecting multi-scale targets. This algorithm has three improvements based on Faster R-CNN. Firstly, the new algorithm uses the ResNet101 network for feature extraction of the detection image, which achieves stronger feature extraction capabilities. Secondly, the new algorithm integrates Online Hard Example Mining (OHEM), Soft non-maximum suppression (Soft-NMS), and Distance Intersection Over Union (DIOU) modules, which improves the positive and negative sample imbalance and the problem of small targets being easily missed during model training. Finally, the Region Proposal Network (RPN) is simplified to achieve a faster detection speed and a lower miss rate. The multi-scale training (MST) strategy is also used to train the improved Faster R-CNN to achieve a balance between detection accuracy and efficiency. Compared to the other detection models, the improved Faster R-CNN demonstrates significant advantages in terms of mAP@0.5, F1-score, and Log average miss rate (LAMR). The model proposed in this paper provides valuable insights and inspiration for many fields, such as smart agriculture, medical diagnosis, and face recognition.

Similar Papers
  • Research Article
  • Citations43

Esophageal cancer detection based on classification of gastrointestinal CT images using improved Faster RCNN

  • May 16, 2021
  • Computer Methods and Programs in Biomedicine
  • Kuan-Bing Chen +3
  • PDF
  • Research Article
  • Citations31

Incorporate Online Hard Example Mining and Multi-Part Combination Into Automatic Safety Helmet Wearing Detection

  • Dec 17, 2020
  • IEEE Access
  • Ning Li +5
  • Conference Article
  • Citations27

An Advanced Deep Learning Approach for Safety Helmet Wearing Detection

  • Jul 01, 2019
  • Yuwan Gu +3
  • PDF
  • Research Article
  • Citations5

Automatic defect detection based on improved Faster RCNN for substation equipment

  • May 01, 2020
  • Journal of Physics: Conference Series
  • Lv Shouguo +5
  • Research Article
  • Citations110

An improved faster R-CNN algorithm for assisted detection of lung nodules

  • Dec 28, 2022
  • Computers in Biology and Medicine
  • Jing Xu +3
  • Conference Article
  • Citations19

Pedestrian Detection Algorithm based on Improved Faster RCNN

  • Mar 12, 2021
  • Xiaoqiang Shao +6
  • Research Article
  • Citations17

Improved faster region convolutional neural network algorithm for UAV target detection in complex environment

  • Jun 28, 2024
  • Results in Engineering
  • Gengyan Cui +1
  • Research Article
  • Citations9

Identification of diatom taxonomy by a combination of region-based full convolutional network, online hard example mining, and shape priors of diatoms

  • Jul 20, 2021
  • International Journal of Legal Medicine
  • Jiehang Deng +9
  • PDF
  • Research Article
  • Citations12

Online hard example mining vs. fixed oversampling strategy for segmentation of new multiple sclerosis lesions from longitudinal FLAIR MRI

  • Nov 04, 2022
  • Frontiers in Neuroscience
  • Marius Schmidt-Mengin +7
  • PDF
  • Research Article
  • Citations113

Insulator Defect Recognition Based on Global Detection and Local Segmentation

  • Jan 01, 2020
  • IEEE Access
  • Xuefeng Li +2
  • Research Article
  • Citations150

Object Detection Based on Multi-Layer Convolution Feature Fusion and Online Hard Example Mining

  • Jan 01, 2018
  • IEEE Access
  • Jun Chu +2
  • PDF
  • Research Article
  • Citations88

Underwater Object Detection Method Based on Improved Faster RCNN

  • Feb 20, 2023
  • Applied Sciences
  • Hao Wang +1
  • Research Article
  • Citations12

Textile Fabric Defect Detection Based on Improved Faster R-CNN

  • Sep 01, 2021
  • AATCC Journal of Research
  • Dongfang He +2
  • Research Article
  • Citations4

SFGNet detecting objects via spatial fine-grained feature and enhanced RPN with spatial context

  • Apr 20, 2022
  • Systems Science & Control Engineering
  • Jun Hu +5
  • Conference Article
  • Citations2957

Training Region-Based Object Detectors with Online Hard Example Mining

  • Jun 01, 2016
  • Abhinav Shrivastava +2
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.