The Fisher Kernel Coding Framework for High Spatial Resolution Scene Classification

High spatial resolution (HSR) image scene classification is aimed at bridging the semantic gap between low-level features and high-level semantic concepts, which is a challenging task due to the complex distribution of ground objects in HSR images. Scene classification based on the bag-of-visual-words (BOVW) model is one of the most successful ways to acquire the high-level semantic concepts. However, the BOVW model assigns local low-level features to their closest visual words in the “visual vocabulary” (the codebook obtained by k-means clustering), which discards too many useful details of the low-level features in HSR images. In this paper, a feature coding method under the Fisher kernel (FK) coding framework is introduced to extend the BOVW model by characterizing the low-level features with a gradient vector instead of the count statistics in the BOVW model, which results in a significant decrease in the codebook size and an acceleration of the codebook learning process. By considering the differences in the distributions of the ground objects in different regions of the images, local FK (LFK) is proposed for the HSR image scene classification method. The experimental results show that the proposed scene classification methods under the FK coding framework can greatly reduce the computational cost, and can obtain a better scene classification accuracy than the methods based on the traditional BOVW model.

• Publication year

  2016

• Venue

  Remote Sensing

• Publication date

  2016-02-19

• Fields of study

  Computer Science, Geology

• Identifiers
  DOI 10.3390/rs8020157
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Dirichlet-Derived Multiple Topic Scene Classification Model for High Spatial Resolution Remote Sensing Imagery

  2016cited by this paper
• A Comparative Study of Bag-of-Words and Bag-of-Topics Models of EO Image Patches

  2015cited by this paper
• Object Detection in Optical Remote Sensing Images Based on Weakly Supervised Learning and High-Level Feature Learning

  2015cited by this paper
• Auto-encoder-based shared mid-level visual dictionary learning for scene classification using very high resolution remote sensing images

  2015cited by this paper
• Remote Sens

  2015cited by this paper
• Pyramid of Spatial Relatons for Scene-Level Land Use Classification

  2015cited by this paper
• Scene Classification Based on the Multifeature Fusion Probabilistic Topic Model for High Spatial Resolution Remote Sensing Imagery

  2015cited by this paper
• A Linear Dirichlet Mixture Model for decomposing scenes: Application to analyzing urban functional zonings

  2015cited by this paper
• Saliency-Guided Unsupervised Feature Learning for Scene Classification

  2015cited by this paper
• Unsupervised Feature Learning Via Spectral Clustering of Multidimensional Patches for Remotely Sensed Scene Classification

  2015cited by this paper
• Multiagent Object-Based Classifier for High Spatial Resolution Imagery

  2014cited by this paper
• Unsupervised Feature Learning for Aerial Scene Classification

  2014cited by this paper
• Feature Coding in Image Classification: A Comprehensive Study

  2014cited by this paper
• A Hybrid Object-Oriented Conditional Random Field Classification Framework for High Spatial Resolution Remote Sensing Imagery

  2014cited by this paper
• A Multichannel Gray Level Co-Occurrence Matrix for Multi/Hyperspectral Image Texture Representation

  2014cited by this paper
• Multi-class geospatial object detection and geographic image classification based on collection of part detectors

  2014cited by this paper
• Efficient, simultaneous detection of multi-class geospatial targets based on visual saliency modeling and discriminative learning of sparse coding

  2014cited by this paper
• Land-Use Scene Classification Using a Concentric Circle-Structured Multiscale Bag-of-Visual-Words Model

  2014cited by this paper
• Semantic Annotation of Satellite Images Using Author–Genre–Topic Model

  2014cited by this paper
• Geographic Object-Based Image Analysis – Towards a new paradigm

  2014cited by this paper
• Automatic Annotation of Satellite Images via Multifeature Joint Sparse Coding With Spatial Relation Constraint

  2013cited by this paper
• High-Resolution Remote-Sensing Image Classification via an Approximate Earth Mover's Distance-Based Bag-of-Features Model

  2013cited by this paper
• Scene classification via latent Dirichlet allocation using a hybrid generative/discriminative strategy for high spatial resolution remote sensing imagery

  2013cited by this paper
• Land-Cover Mapping by Markov Modeling of Spatial–Contextual Information in Very-High-Resolution Remote Sensing Images

  2013cited by this paper
• High-resolution satellite scene classification using a sparse coding based multiple feature combination

  2012cited by this paper
• Probabilistic topic models

  2012cited by this paper
• Satellite Image Classification via Two-Layer Sparse Coding With Biased Image Representation

  2011cited by this paper
• Spatial pyramid co-occurrence for image classification

  2011influential reference
• LIBSVM: A library for support vector machines

  2011cited by this paper
• Multi-scale GEOBIA with very high spatial resolution digital aerial imagery: scale, texture and image objects

  2011cited by this paper
• Bag-of-visual-words and spatial extensions for land-use classification

  2010influential reference
• Object Classification of Aerial Images With Bag-of-Visual Words

  2010cited by this paper
• Improving the Fisher Kernel for Large-Scale Image Classification

  2010cited by this paper
• Semantic Annotation of Satellite Images Using Latent Dirichlet Allocation

  2010influential reference
• Rule-Based Classification of a Very High Resolution Image in an Urban Environment Using Multispectral Segmentation Guided by Cartographic Data

  2010cited by this paper
• Urban-Area Segmentation Using Visual Words

  2009cited by this paper
• Latent Dirichlet Allocation

  2009cited by this paper
• Fisher Kernels on Visual Vocabularies for Image Categorization

  2007cited by this paper
• Beyond Bags of Features: Spatial Pyramid Matching for Recognizing Natural Scene Categories

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

  2004influential reference
• Histogram intersection kernel for image classification

  2003cited by this paper
• Visual categorization with bags of keypoints

  2002cited by this paper
• Textural Features for Image Classification

  1973cited by this paper
• Strathprints Institutional Repository Shuhui and Ren, Jinchang (2015) Effective and Efficient Midlevel Visual Elements-oriented Land-use Classification Using Vhr Remote Sensing Images. Ieee Transactions on Geoscience and Remote Sensing, 53 (8). Pp. 4238-4249. Issn 0196-2892 Effective and Efficient M

  year unknowncited by this paper
• This article has been accepted for inclusion in a future issue of this journal. Content is final as presented, with the exception of pagination. IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING 1 Hyperspectral Image Segmentation Using a New Bayesian App

  year unknowncited by this paper

• Fusing Geometric and Semantic Features via Cosine Similarity Cross-Attention for Remote Sensing Scene Classification

  2026cites this paper
• Towards Lightweight and Multi-Scale Scene Classification: A Lie Group-Guided Deep Learning Network with Collaborative Attention

  2026cites this paper
• PDFIN: Prompt-Guided Dynamic Feature Integration Network for Few-Shot Class-Incremental Remote Sensing Scene Classification

  2025cites this paper
• Optimizing Lie Group SVM with Laplace Distribution for Robust Image Classification

  2025cites this paper
• Towards Faithful Reasoning in Remote Sensing: A Perceptually-Grounded GeoSpatial Chain-of-Thought for Vision-Language Models

  2025cites this paper
• A Denoising Method for Salt and Pepper Noise in Remote Sensing Based on Swin‐Transformer Convolution U‐Net and Filtering—FSCU‐Net

  2025cites this paper
• Multi-temporal high-resolution urban land-use mapping and change analysis based on a deep geospatial-temporal adaptation network

  2025cites this paper
• FUSE-RSVLM: Feature Fusion Vision-Language Model for Remote Sensing

  2025cites this paper
• SeG-SR: Integrating Semantic Knowledge Into Remote Sensing Image Super-Resolution via Vision-Language Model

  2025cites this paper
• A Lie group-based model for remote scene classification with multi-scale feature fusion and mixed attention mechanisms

  2025cites this paper
• High resolution descriptors for UAV mapping in biodiversity conservation – A case study of sandy steppe habitat renewal

  2025cites this paper
• Multibranch Fusion-Based Feature Enhance for Remote-Sensing Scene Classification

  2025cites this paper
• A Novel Depth-Wise Separable Convolutional Model for Remote Sensing Scene Classification

  2024cites this paper
• Multiscale Urban Functional Zone Recognition Based on Landmark Semantic Constraints

  2024cites this paper
• Deep Clustering of Remote Sensing Scenes through Heterogeneous Transfer Learning

  2024cites this paper
• A Grad-CAM and capsule network hybrid method for remote sensing image scene classification

  2024cites this paper
• Spectral Swin Transformer Network for Hyperspectral Image Classification

  2023cites this paper
• Domain adaptation framework with ensemble of fuzzy rules-based ELMs for remote-sensing image classification

  2023cites this paper
• CoI2A: Collaborative Inter-domain and Intra-domain Alignments for Multisource Domain Adaptation

  2023cites this paper
• Remote Sensing Image Scene Classification Based on Head-Tail Global Joint Dual Attention Discrimination Network

  2023cites this paper
• Contrastive Learning Based on Multiscale Hard Features for Remote-Sensing Image Scene Classification

  2023cites this paper
• SATIN: A Multi-Task Metadataset for Classifying Satellite Imagery using Vision-Language Models

  2023cites this paper
• Remote Sensing Image Scene Classification: Advances and Open Challenges

  2023cites this paper
• Dynamic Loss Reweighting Method Based on Cumulative Classification Scores for Long-Tailed Remote Sensing Image Classification

  2023cites this paper
• A Lightweight Model of VGG-U-Net for Remote Sensing Image Classification

  2022cites this paper
• Geoprocessing Applied to the Assessment of Carbon Storage and Sequestration in a Brazilian Medium-Sized City

  2022cites this paper
• Lie Group spatial attention mechanism model for remote sensing scene classification

  2022cites this paper
• A Novel Approach of Transfer Learning for Satellite Image Classification

  2022cites this paper
• Optimizable Image Segmentation Method with Superpixels and Feature Migration for Aerospace Structures

  2022cites this paper
• A Survey of Semantic Construction and Application of Satellite Remote Sensing Images and Data

  2021cites this paper
• Scene-Driven Multitask Parallel Attention Network for Building Extraction in High-Resolution Remote Sensing Images

  2021cites this paper
• Multilevel Capsule Weighted Aggregation Network Based on a Decoupled Dynamic Filter for Remote Sensing Scene Classification

  2021cites this paper
• Landslide Detection from Open Satellite Imagery Using Distant Domain Transfer Learning

  2021cites this paper
• Mangrove Loss and Gain in a Densely Populated Urban Estuary: Lessons From the Guangdong-Hong Kong-Macao Greater Bay Area

  2021cites this paper
• Hyperspectral Image Classification—Traditional to Deep Models: A Survey for Future Prospects

  2021cites this paper
• Remote Sensing Scene Classification Using Sparse Representation-Based Framework With Deep Feature Fusion

  2021cites this paper
• Pre-training of gated convolution neural network for remote sensing image super-resolution

  2021cites this paper
• A Lightweight and Robust Lie Group-Convolutional Neural Networks Joint Representation for Remote Sensing Scene Classification

  2021cites this paper
• NaSC-TG2: Natural Scene Classification With Tiangong-2 Remotely Sensed Imagery

  2021cites this paper
• High level visual scene classification using background knowledge of objects

  2021cites this paper
• Multi-Objective Net Architecture Pruning for Remote Sensing Classification

  2021cites this paper
• Random Topology and Random Multiscale Mapping: An Automated Design of Multiscale and Lightweight Neural Network for Remote-Sensing Image Recognition

  2021cites this paper
• A Deep Neural Network Combined CNN and GCN for Remote Sensing Scene Classification

  2020cites this paper
• RSI-CB: A Large-Scale Remote Sensing Image Classification Benchmark Using Crowdsourced Data

  2020cites this paper
• Global Optimal Structured Embedding Learning for Remote Sensing Image Retrieval

  2020influential citation
• Further Exploring Convolutional Neural Networks’ Potential for Land-Use Scene Classification

  2020cites this paper
• An Efficient Convolutional Neural Network for Remote-Sensing Scene Image Classification

  2020cites this paper
• An Efficient and Lightweight Convolutional Neural Network for Remote Sensing Image Scene Classification

  2020cites this paper
• Satellite image super-resolution based on progressive residual deep neural network

  2020cites this paper
• Open-source data-driven urban land-use mapping integrating point-line-polygon semantic objects: A case study of Chinese cities

  2020cites this paper
• A Framework for Land Use Scenes Classification Based on Landscape Photos

  2020cites this paper
• On the Evaluation of CNN Models in Remote-Sensing Scene Classification Domain

  2020cites this paper
• RSNet: The Search for Remote Sensing Deep Neural Networks in Recognition Tasks

  2020cites this paper
• Invariant Deep Compressible Covariance Pooling for Aerial Scene Categorization

  2020cites this paper
• A STUDY OF DEEP LEARNING DATASETS AND MODEL IN REMOTE SENSING IMAGES CLASSIFICATION

  2020cites this paper
• Remote Sensing Scene Classification Using Heterogeneous Feature Extraction and Multi-Level Fusion

  2020cites this paper
• Hierarchical feature coding model for high-resolution satellite scene classification

  2019cites this paper
• Bag of words KAZE (BoWK) with two-step classification for high-resolution remote sensing images

  2019influential citation
• Scene classification of high-resolution remote sensing images based on IMFNet

  2019cites this paper
• Land-Use Detection Using Residual Convolutional Neural Network

  2019cites this paper
• Aggregated Deep Fisher Feature for VHR Remote Sensing Scene Classification

  2019cites this paper
• Novel Context-aware Classification for Highly Accurate Automatic Toll Collection

  2019cites this paper
• Unsupervised Deep Feature Learning With Iteratively Refined Pseudo Classes for Scene Representation

  2019cites this paper
• A Lightweight and Discriminative Model for Remote Sensing Scene Classification With Multidilation Pooling Module

  2019cites this paper
• A Feature Aggregation Convolutional Neural Network for Remote Sensing Scene Classification

  2019cites this paper
• Scene classification based on the bag-of-visual-words and Doc2Vec models for high-spatial resolution remote-sensing imagery

  2019cites this paper
• Joint Learning of the Center Points and Deep Metrics for Land-Use Classification in Remote Sensing

  2019cites this paper
• Multiple resolution block feature for remote-sensing scene classification

  2019cites this paper
• Aggregated Deep Local Features for Remote Sensing Image Retrieval

  2019cites this paper
• Remote Sensing Image Scene Classification Based on SURF Feature and Deep Learning

  2019cites this paper
• Application of convolutional neural networks to building segmentation in aerial images

  2018cites this paper
• Urban land-use mapping using a deep convolutional neural network with high spatial resolution multispectral remote sensing imagery

  2018cites this paper
• Scene classification of remote sensing image based on deep network and multi-scale features fusion

  2018cites this paper
• Partial randomness hashing applied to remote sensing object classification

  2018cites this paper
• Scene classification of remote sensing image based on deep convolutional neural network

  2018cites this paper
• Feature Fusion with Deep Supervision for Remote-Sensing Image Scene Classification

  2018cites this paper
• Object Classification of Remote Sensing Images Based on Partial Randomness Supervised Discrete Hashing

  2018cites this paper
• Unsupervised Deep Feature Learning for Remote Sensing Image Retrieval

  2018cites this paper
• Inducing Contextual Classifications With Kernel Functions Into Support Vector Machines

  2018cites this paper
• Diversity-Promoting Deep Structural Metric Learning for Remote Sensing Scene Classification

  2018cites this paper
• Improving Remote Sensing Scene Classification by Integrating Global-Context and Local-Object Features

  2018cites this paper
• Scene Classification Based on a Deep Random-Scale Stretched Convolutional Neural Network

  2018cites this paper
• Deep Salient Feature Based Anti-Noise Transfer Network for Scene Classification of Remote Sensing Imagery

  2018cites this paper
• RSI-CB: A Large Scale Remote Sensing Image Classification Benchmark via Crowdsource Data

  2017cites this paper
• Scene Classification Based on Multiscale Convolutional Neural Network

  2017cites this paper
• Scene Semantic Understanding Based on the Spatial Context Relations of Multiple Objects

  2017cites this paper
• Improved Class-Specific Codebook with Two-Step Classification for Scene-Level Classification of High Resolution Remote Sensing Images

  2017cites this paper
• Scene semantic classification based on scale invariance convolutional neural networks

  2017cites this paper
• Transfer Learning With Fully Pretrained Deep Convolution Networks for Land-Use Classification

  2017cites this paper
• Scene Classification Based on the Fully Sparse Semantic Topic Model

  2017cites this paper
• Remote Sensing Scene Classification Using a Preclassification Strategy and an Improved Structural Feature

  2017cites this paper
• Aggregating Rich Hierarchical Features for Scene Classification in Remote Sensing Imagery

  2017influential citation
• Building block level urban land-use information retrieval based on Google Street View images

  2017cites this paper
• Mid-Level Feature Representation via Sparse Autoencoder for Remotely Sensed Scene Classification

  2017cites this paper
• Scene classification based on a hierarchical convolutional sparse auto-encoder for high spatial resolution imagery

  2017cites this paper
• Kernel Slow Feature Analysis for Scene Change Detection

  2017cites this paper
• Remote Sensing Image Scene Classification: Benchmark and State of the Art

  2017cites this paper
• SCENE CLASSFICATION BASED ON THE SEMANTIC-FEATURE FUSION FULLY SPARSE TOPIC MODEL FOR HIGH SPATIAL RESOLUTION REMOTE SENSING IMAGERY

  2016cites this paper
• Bag-of-Visual-Words Scene Classifier With Local and Global Features for High Spatial Resolution Remote Sensing Imagery

  2016cites this paper
• Large patch convolutional neural networks for the scene classification of high spatial resolution imagery

  2016cites this paper