• Home
  • Search
  • Aggregating Rich Hierarchical Features for Scene Classification in Remote Sensing Imagery
  • Cite Icon106
  • https://doi.org/10.1109/jstars.2017.2705419Copy DOI Icon

Aggregating Rich Hierarchical Features for Scene Classification in Remote Sensing Imagery

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

Scene classification is one of the most important issues in remote sensing image processing. To obtain a high discriminative feature representation for an image to be classified, traditional methods usually consider to densely accumulate hand-crafted low-level descriptors (e.g., scale-invariant feature transform) by feature encoding techniques. However, the performance is largely limited by the hand-crafted descriptors as they are not capable of describing the rich semantic information contained in various remote sensing images. To alleviate this problem, we propose a novel method to extract discriminative image features from the rich hierarchical information contained in convolutional neural networks (CNNs). Specifically, the low-level and middle-level intermediate convolutional features are, respectively, encoded by vector of locally aggregated descriptors (VLAD) and then reduced by principal component analysis to obtain hierarchical global features; meanwhile, the fully connected features are average pooled and subsequently normalized to form new global features. The proposed encoded mixed-resolution representation (EMR) is the concatenation of all the above-mentioned global features. Due to the usage of encoding strategies (VLAD and average pooling), our method can deal with images of different sizes. In addition, to reduce the computational consumption in the training stage, we directly extract EMR from VGG-VD and ResNet pretrained on the ImageNet dataset. We show in this paper that CNNs pretrained on the natural image dataset are more easily applied to the remote sensing dataset when the local structure similarity between two datasets is higher. Experimental evaluations on the UC-Merced and Brazilian Coffee Scenes datasets demonstrate that our method is superior to the state of the art.

Similar Papers
  • PDF
  • Research Article
  • Citations1236

Transferring Deep Convolutional Neural Networks for the Scene Classification of High-Resolution Remote Sensing Imagery

  • Nov 05, 2015
  • Remote Sensing
  • Fan Hu +3
  • Conference Article
  • Citations12

Traffic scene recognition based on deep CNN and VLAD spatial pyramids

  • Jul 01, 2017
  • Fang-Yu Wu +3
  • Conference Article

Fusion of Global and Local Deep Features Using Bag of Words and VLAD Models for Human Activity Recognition

  • Nov 01, 2020
  • Amany Abdelbaky +1
  • Conference Article
  • Citations7

VLAD encoded Deep Convolutional features for unconstrained face verification

  • Dec 01, 2016
  • Jingxiao Zheng +4
  • Research Article
  • Citations4

Compressed sensing based feature fusion for image retrieval

  • Jun 18, 2018
  • Journal of Ambient Intelligence and Humanized Computing
  • Yanhong Wang +5
  • PDF
  • Research Article
  • Citations2

Remote Sensing Image Retrieval Based on 3D-Local Ternary Pattern (LTP) Features and Non-subsampled Shearlet Transform (NSST) Domain Statistical Features

  • Jan 01, 2022
  • Computer Modeling in Engineering & Sciences
  • Hilly Gohain Baruah +2
  • PDF
  • Research Article
  • Citations78

Remote Sensing Big Data: Theory, Methods and Applications

  • May 04, 2018
  • Remote Sensing
  • Peng Liu +3
  • PDF
  • Research Article
  • Citations6

Exploiting Hierarchical Label Information in an Attention-Embedding, Multi-Task, Multi-Grained, Network for Scene Classification of Remote Sensing Imagery

  • Aug 30, 2022
  • Applied Sciences
  • Peng Zeng +3
  • Conference Article
  • Citations12

2D-DFrFT Based Deep Network for Ship Classification in Remote Sensing Imagery

  • Aug 01, 2018
  • Qiaoqiao Shi +2
  • Book Chapter
  • Citations2

Bag of Features vs Vector of Locally Aggregated Descriptors

  • Aug 23, 2017
  • Farkhunda Younas +4
  • PDF
  • Research Article
  • Citations36

Remote Sensing Scene Classification Using Sparse Representation-Based Framework With Deep Feature Fusion

  • Jan 01, 2021
  • IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
  • Shaohui Mei +5
  • PDF
  • Research Article
  • Citations16

WS-AM: Weakly Supervised Attention Map for Scene Recognition

  • Sep 21, 2019
  • Electronics
  • Shifeng Xia +3
  • Conference Article

Multi-Order Feature Fusion Joint Training Network for Remote Sensing Scene Classification

  • Nov 01, 2019
  • Kang Ni +3
  • Research Article
  • Citations9

Codebook-Free Compact Descriptor for Scalable Visual Search

  • Feb 01, 2019
  • IEEE Transactions on Multimedia
  • Yuwei Wu +6
  • Research Article
  • Citations1

A Comprehensive Study on VLAD

  • Apr 03, 2021
  • Neural Processing Letters
  • Xin Li +3
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.