Affine-Function Transformation-Based Object Matching for Vehicle Detection from Unmanned Aerial Vehicle Imagery

Vehicle detection from remote sensing images plays a significant role in transportation related applications. However, the scale variations, orientation variations, illumination variations, and partial occlusions of vehicles, as well as the image qualities, bring great challenges for accurate vehicle detection. In this paper, we present an affine-function transformation-based object matching framework for vehicle detection from unmanned aerial vehicle (UAV) images. First, meaningful and non-redundant patches are generated through a superpixel segmentation strategy. Then, the affine-function transformation-based object matching framework is applied to a vehicle template and each of the patches for vehicle existence estimation. Finally, vehicles are detected and located after matching cost thresholding, vehicle location estimation, and multiple response elimination. Quantitative evaluations on two UAV image datasets show that the proposed method achieves an average completeness, correctness, quality, and F1-measure of 0.909, 0.969, 0.883, and 0.938, respectively. Comparative studies also demonstrate that the proposed method achieves compatible performance with the Faster R-CNN and outperforms the other eight existing methods in accurately detecting vehicles of various conditions.

• Publication year

  2019

• Venue

  Remote Sensing

• Publication date

  2019-07-19

• Fields of study

  Geology, Computer Science, Engineering, Environmental Science

• Identifiers
  DOI 10.3390/RS11141708
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Comprehensive Analysis of Deep Learning-Based Vehicle Detection in Aerial Images

  2019cited by this paper
• Vehicle Detection in High-Resolution Images Using Superpixel Segmentation and CNN Iteration Strategy

  2019cited by this paper
• Convolutional SVM Networks for Object Detection in UAV Imagery

  2018cited by this paper
• Vehicle Instance Segmentation From Aerial Image and Video Using a Multitask Learning Residual Fully Convolutional Network

  2018cited by this paper
• Symmetrical Dense-Shortcut Deep Fully Convolutional Networks for Semantic Segmentation of Very-High-Resolution Remote Sensing Images

  2018cited by this paper
• Car Detection in Aerial Images of Dense Urban Areas

  2018cited by this paper
• Object-based detection of vehicles using combined optical and elevation data

  2018cited by this paper
• A light and faster regional convolutional neural network for object detection in optical remote sensing images

  2018cited by this paper
• A deep learning framework for remote sensing image registration

  2018cited by this paper
• A CNN-Based Method of Vehicle Detection from Aerial Images Using Hard Example Mining

  2018cited by this paper
• Detection of Vehicles in Multisensor Data via Multibranch Convolutional Neural Networks

  2018cited by this paper
• YOLOv3: An Incremental Improvement

  2018cited by this paper
• Detection of Asphalt Pavement Potholes and Cracks Based on the Unmanned Aerial Vehicle Multispectral Imagery

  2018cited by this paper
• Robust Vehicle Detection in Aerial Images Using Bag-of-Words and Orientation Aware Scanning

  2018influential reference
• Vehicle Object Detection in Remote Sensing Imagery Based on Multi-Perspective Convolutional Neural Network

  2018cited by this paper
• Algorithms for semantic segmentation of multispectral remote sensing imagery using deep learning

  2017cited by this paper
• On Detecting Road Regions in a Single UAV Image

  2017cited by this paper
• Vehicle Detection in Aerial Images Based on Region Convolutional Neural Networks and Hard Negative Example Mining

  2017cited by this paper
• Robust Vehicle Detection in Aerial Images Based on Cascaded Convolutional Neural Networks

  2017cited by this paper
• Traffic congestion detection by use of satellites view

  2017cited by this paper
• Weakly supervised vehicle detection in satellite images via multi-instance discriminative learning

  2017cited by this paper
• Arbitrary-Oriented Vehicle Detection in Aerial Imagery with Single Convolutional Neural Networks

  2017cited by this paper
• Affine Invariant Description and Large-Margin Dimensionality Reduction for Target Detection in Optical Remote Sensing Images

  2017influential reference
• An On-Road Vehicle Detection Method for High-Resolution Aerial Images Based on Local and Global Structure Learning

  2017cited by this paper
• Deep Learning Approach for Car Detection in UAV Imagery

  2017cited by this paper
• Toward Fast and Accurate Vehicle Detection in Aerial Images Using Coupled Region-Based Convolutional Neural Networks

  2017cited by this paper
• Segment-before-Detect: Vehicle Detection and Classification through Semantic Segmentation of Aerial Images

  2017cited by this paper
• An Enhanced Viola-Jones Vehicle Detection Method From Unmanned Aerial Vehicles Imagery

  2017cited by this paper
• A hybrid MLP-CNN classifier for very fine resolution remotely sensed image classification

  2017cited by this paper
• Orientation aware vehicle detection in aerial images

  2017cited by this paper
• A semi-supervised generative framework with deep learning features for high-resolution remote sensing image scene classification

  2017cited by this paper
• Vehicle detection in aerial imagery : A small target detection benchmark

  2016cited by this paper
• Rotation-and-scale-invariant airplane detection in high-resolution satellite images based on deep-Hough-forests

  2016cited by this paper
• Vehicle Detection in High-Resolution Aerial Images via Sparse Representation and Superpixels

  2016cited by this paper
• Robust vehicle detection by combining deep features with exemplar classification

  2016cited by this paper
• Region-based urban road extraction from VHR satellite images using Binary Partition Tree

  2016cited by this paper
• Vehicle detection from highway satellite images via transfer learning

  2016cited by this paper
• Vehicle Detection in High-Resolution Aerial Images Based on Fast Sparse Representation Classification and Multiorder Feature

  2016cited by this paper
• A Hybrid Vehicle Detection Method Based on Viola-Jones and HOG + SVM from UAV Images

  2016cited by this paper
• Vehicle detection from aerial color imagery and airborne LiDAR data

  2016cited by this paper
• Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks

  2015cited by this paper
• Fast Multiclass Vehicle Detection on Aerial Images

  2015cited by this paper
• Detecting Cars in UAV Images With a Catalog-Based Approach

  2014cited by this paper
• Learning with Hierarchical-Deep Models

  2013cited by this paper
• Airborne Vehicle Detection in Dense Urban Areas Using HoG Features and Disparity Maps

  2013cited by this paper
• A Novel Vehicle Detection Method With High Resolution Highway Aerial Image

  2013cited by this paper
• ImageNet classification with deep convolutional neural networks

  2012cited by this paper
• SLIC Superpixels Compared to State-of-the-Art Superpixel Methods

  2012cited by this paper
• Vehicle Detection Using Partial Least Squares

  2011cited by this paper
• Automated Vehicle Extraction and Speed Determination From QuickBird Satellite Images

  2011cited by this paper
• Automatic traffic monitoring using satellite images

  2010cited by this paper
• Automated road pavement marking detection from high resolution aerial images based on multi-resolution image analysis and anisotropic Gaussian filtering

  2010cited by this paper
• Object-based Detection and Classification of Vehicles from High-resolution Aerial Photography

  2009cited by this paper
• Road detection from high-resolution satellite images using artificial neural networks

  2007cited by this paper
• Matching by Linear Programming and Successive Convexification

  2007cited by this paper
• A semi-automatic framework for highway extraction and vehicle detection based on a geometric deformable model

  2006cited by this paper
• Efficient Non-Maximum Suppression

  2006influential reference
• Distinctive Image Features from Scale-Invariant Keypoints

  2004cited by this paper
• Surflet-pair-relation histograms: a statistical 3D-shape representation for rapid classification

  2003cited by this paper

• MSIMRS: Multi-Scale Superpixel Segmentation Integrating Multi-Source Remote Sensing Data for Lithology Identification in Semi-Arid Area

  2025cites this paper
• Intelligent Transportation Surveillance via YOLOv9 and NASNet over Aerial Imagery

  2025cites this paper
• Multi-Vehicles Classification on Aerial Images using ResNet and Transformer Networks

  2025cites this paper
• Lightweight CNN model: automated vehicle detection in aerial images

  2022cites this paper
• Selecting Post-Processing Schemes for Accurate Detection of Small Objects in Low-Resolution Wide-Area Aerial Imagery

  2022cites this paper
• Improving Car Detection from Aerial Footage with Elevation Information and Markov Random Fields

  2022cites this paper
• A Study on Distance Measurement Module for Driving Vehicle Velocity Estimation in Multi-Lanes Using Drones

  2021cites this paper
• Real-Time Tracking Algorithm for Aerial Vehicles Using Improved Convolutional Neural Network and Transfer Learning

  2021influential citation
• YOLO-RTUAV: Towards Real-Time Vehicle Detection through Aerial Images with Low-Cost Edge Devices

  2021cites this paper
• Editorial for Special Issue "Remote Sensing for Target Object Detection and Identification"

  2020cites this paper
• VAID: An Aerial Image Dataset for Vehicle Detection and Classification

  2020cites this paper
• ComNet: Combinational Neural Network for Object Detection in UAV-Borne Thermal Images

  2020cites this paper
• Joint-SRVDNet: Joint Super Resolution and Vehicle Detection Network

  2020cites this paper