• Home
  • Search
  • Deep learning for small object detection in images
  • https://doi.org/10.32469/10355/79470Copy DOI Icon

Deep learning for small object detection in images

  • Jul 1, 2020
  • Yang Liu
Show More
  • Abstract
  • Literature Map
  • Similar Papers
Abstract

[ACCESS RESTRICTED TO THE UNIVERSITY OF MISSOURI AT REQUEST OF AUTHOR.] With the rapid development of deep learning in computer vision, especially deep convolutional neural networks (CNNs), significant advances have been made in recent years on object recognition and detection in images. Highly accurate detection results have been achieved for large objects, whereas detection accuracy on small objects remains to be low. This dissertation focuses on investigating deep learning methods for small object detection in images and proposing new methods with improved performance. First, we conducted a comprehensive review of existing deep learning methods for small object detections, in which we summarized and categorized major techniques and models, identified major challenges, and listed some future research directions. Existing techniques were categorized into using contextual information, combining multiple feature maps, creating sufficient positive examples, and balancing foreground and background examples. Methods developed in four related areas, generic object detection, face detection, object detection in aerial imagery, and segmentation, were summarized and compared. In addition, the performances of several leading deep learning methods for small object detection, including YOLOv3, Faster R-CNN, and SSD, were evaluated based on three large benchmark image datasets of small objects. Experimental results showed that Faster R-CNN performed the best, while YOLOv3 was a close second. Furthermore, a new deep learning method, called Retina-context Net, was proposed and outperformed state-of-the art one-stage deep learning models, including SSD, YOLOv3 and RetinaNet, on the COCO and SUN benchmark datasets. Secondly, we created a new dataset for bird detection, called Little Birds in Aerial Imagery (LBAI), from real-life aerial imagery. LBAI contains birds with sizes ranging from 10 by 10 pixels to 40 by 40 pixels. We adapted and applied several state-of-the-art deep learning models to LBAI, including object detection models such as YOLOv2, SSH, and Tiny Face, and instance segmentation models such as U-Net and Mask R-CNN. Our empirical results illustrated the strength and weakness of these methods, showing that SSH performed the best for easy cases, whereas Tiny Face performed the best for hard cases with cluttered backgrounds. Among small instance segmentation methods, U-Net achieved slightly better performance than Mask R-CNN. Thirdly, we proposed a new graph neural network-based object detection algorithm, called GODM, to take the spatial information of candidate objects into consideration in small object detection. Instead of detecting small objects independently as the existing deep learning methods do, GODM treats the candidate bounding boxes generated by existing object detectors as nodes and creates edges based on the spatial or semantic relationship between the candidate bounding boxes. GODM contains four major components: node feature generation, graph generation, node class labelling, and graph convolutional neural network model. Several graph generation methods were proposed. Experimental results on the LBDA dataset show that GODM outperformed existing state-of-the-art object detector Faster R-CNN significantly, up to 12% better in accuracy. Finally, we proposed a new computer vision-based grass analysis using machine learning. To deal with the variation of lighting condition, a two-stage segmentation strategy is proposed for grass coverage computation based on a blackboard background. On a real world dataset we collected from natural environments, the proposed method was robust to varying environments, lighting, and colors. For grass detection and coverage computation, the error rate was just 3%.

Similar Papers
  • PDF
  • Research Article
  • Citations2

APPLICATION OF MACHINE LEARNING FOR OBJECT DETECTION IN OBLIQUE AERIAL IMAGES

  • May 30, 2022
  • ˜The œinternational archives of the photogrammetry, remote sensing and spatial information sciences/International archives of the photogrammetry, remote sensing and spatial information sciences
  • P Zachar +2
  • Dissertation

Improving object recognition in aerial image and ambulatory assessment analysis by deep learning

  • Dec 01, 2019
  • Peng Sun
  • Research Article
  • Citations77

An empirical study of multi-scale object detection in high resolution UAV images

  • Sep 28, 2020
  • Neurocomputing
  • Haijun Zhang +5
  • Conference Article
  • Citations39

Deep learning based multi-category object detection in aerial images

  • May 01, 2017
  • Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE
  • Lars W Sommer +2
  • Research Article
  • Citations13

UIR-Net: Object Detection in Infrared Imaging of Thermomechanical Processes in Automotive Manufacturing

  • Oct 01, 2022
  • IEEE Transactions on Automation Science and Engineering
  • Shenghan Guo +3
  • PDF
  • Research Article
  • Citations16

Eagle-YOLO: An Eagle-Inspired YOLO for Object Detection in Unmanned Aerial Vehicles Scenarios

  • Apr 28, 2023
  • Mathematics
  • Lyuchao Liao +5
  • Conference Article

Multi Object Detection and Shadow Identification in Images: State-of-Art

  • Sep 21, 2022
  • Sana Pavan Kumar Reddy +2
  • Research Article
  • Citations636

A survey and performance evaluation of deep learning methods for small object detection

  • Jan 19, 2021
  • Expert Systems with Applications
  • Yang Liu +3
  • Conference Article
  • Citations7

Object Detection in Image with Complex Background

  • Jan 01, 2013
  • Li Dong +3
  • Conference Article
  • Citations7

An Investigate on Moving Object Tracking and Detection in Images

  • Apr 28, 2021
  • Abbas S B Sadkhan +2
  • Research Article
  • Citations5

Small aircraft detection in infrared aerial imagery based on deep neural network

  • Nov 04, 2024
  • Infrared Physics and Technology
  • Kai Zhang +3
  • Conference Article
  • Citations11

Plain objects detection in image based on a contour tracing algorithm in a binary image

  • Jun 01, 2014
  • A Kazlouski +1
  • Research Article
  • Citations8

Small object detection in side-scan sonar images based on SOCA-YOLO and image restoration

  • Apr 15, 2025
  • Frontiers in Marine Science
  • Xiaodong Cui +4
  • Research Article

Research on machine learning methods for detecting objects in difficult shooting conditions

  • May 23, 2025
  • Radioelectronic and Computer Systems
  • Vitalii Serdechnyi +4
  • PDF
  • Research Article
  • Citations14

Object detection of aerial image using mask-region convolutional neural network (mask R-CNN)

  • Jun 01, 2020
  • IOP Conference Series: Earth and Environmental Science
  • Musyarofah +2
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.