• Home
  • Search
  • FINE-TUNING DEEP LEARNING MODELS FOR PEDESTRIAN DETECTION
  • Cite Icon22
  • https://doi.org/10.1590/s1982-21702021000200013Copy DOI Icon

FINE-TUNING DEEP LEARNING MODELS FOR PEDESTRIAN DETECTION

Show More
  • Abstract
  • Highlights & Summary
  • PDF
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Object detection in high resolution images is a new challenge that the remote sensing community is facing thanks to introduction of unmanned aerial vehicles and monitoring cameras. One of the interests is to detect and trace persons in the images. Different from general objects, pedestrians can have different poses and are undergoing constant morphological changes while moving, this task needs an intelligent solution. Fine-tuning has woken up great interest among researchers due to its relevance for retraining convolutional networks for many and interesting applications. For object classification, detection, and segmentation fine-tuned models have shown state-of-the-art performance. In the present work, we evaluate the performance of fine-tuned models with a variation of training data by comparing Faster Region-based Convolutional Neural Network (Faster R-CNN) Inception v2, Single Shot MultiBox Detector (SSD) Inception v2, and SSD Mobilenet v2. To achieve the goal, the effect of varying training data on performance metrics such as accuracy, precision, F1-score, and recall are taken into account. After testing the detectors, it was identified that the precision and recall are more sensitive on the variation of the amount of training data. Under five variation of the amount of training data, we observe that the proportion of 60%-80% consistently achieve highly comparable performance, whereas in all variation of training data Faster R-CNN Inception v2 outperforms SSD Inception v2 and SSD Mobilenet v2 in evaluated metrics, but the SSD converges relatively quickly during the training phase. Overall, partitioning 80% of total data for fine-tuning trained models produces efficient detectors even with only 700 data samples.

Loading PDF

Similar Papers
  • Research Article
  • Citations37

A Comparative Analysis of Modern Object Detection Algorithms: YOLO vs. SSD vs. Faster R-CNN

  • Dec 28, 2023
  • ITEJ (Information Technology Engineering Journals)
  • Dalmar Dakari Aboyomi +1
  • Research Article
  • Citations57

Applications of object detection in modular construction based on a comparative evaluation of deep learning algorithms

  • May 21, 2021
  • Construction Innovation
  • Chang Liu +3
  • Research Article
  • Citations26

Incremental Deep Learning for Robust Object Detection in Unknown Cluttered Environments

  • Jan 01, 2018
  • IEEE Access
  • Dong Kyun Shin +2
  • Research Article
  • Citations14

Modern convolutional object detectors for nuclei detection on pleural effusion cytology images

  • Mar 11, 2019
  • Multimedia Tools and Applications
  • Elif Baykal +4
  • Research Article
  • Citations191

Comparison of convolutional neural networks in fruit detection and counting: A comprehensive evaluation

  • Apr 27, 2020
  • Computers and Electronics in Agriculture
  • J.P Vasconez +3
  • Research Article
  • Citations146

Comparative Research on Deep Learning Approaches for Airplane Detection from Very High-Resolution Satellite Images

  • Feb 01, 2020
  • Remote Sensing
  • Ugur Alganci +2
  • Book Chapter
  • Citations6

Detection and Recognition of Badgers Using Deep Learning

  • Jan 01, 2018
  • Emmanuel Okafor +3
  • Research Article
  • Citations13

Comparison of Deep Learning-Based Object Classification Methods for Detecting Tomato Ripeness

  • Sep 30, 2022
  • INTERNATIONAL JOURNAL of FUZZY LOGIC and INTELLIGENT SYSTEMS
  • Dheo Prasetyo Nugroho +2
  • Research Article
  • Citations4

Application of Principal Component Analysis and Adaptive Median Filter to Improve Real-Time Prostate Capsula Detection

  • Feb 01, 2020
  • Journal of Medical Imaging and Health Informatics
  • Shixiao Wu +2
  • Research Article
  • Citations22

Comparative Study of Some Deep Learning Object Detection Algorithms: R-CNN, FAST R-CNN, FASTER R-CNN, SSD, and YOLO

  • Jan 01, 2023
  • Nile Journal of Engineering and Applied Science
  • Oluwaseyi Olorunshola +2
  • Research Article

Geological map feature extraction using object detection techniques - a comparative analysis

  • Jan 01, 2022
  • i-manager’s Journal on Image Processing
  • P A N Dilhan +1
  • PDF
  • Research Article
  • Citations1

Importance of Adaptive Photometric Augmentation for Different Convolutional Neural Network

  • Jan 01, 2022
  • Computers, Materials & Continua
  • Saraswathi Sivamani +4
  • PDF
  • Research Article
  • Citations24

Automatic identification of benign pigmented skin lesions from clinical images using deep convolutional neural network

  • Oct 10, 2022
  • BMC Biotechnology
  • Hui Ding +8
  • Research Article
  • Citations22

Localization of stroke lesion in MRI images using object detection techniques: A comprehensive review

  • Apr 12, 2022
  • Neuroscience Informatics
  • Sangeeta Rani +3
  • Dissertation

Deep learning for small object detection in images

  • Jul 01, 2020
  • Yang Liu
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.