Geographic Image Retrieval Using Local Invariant Features

By Yi Yang, Shawn D. Newsam. 2013

353 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Media Technology, Information Retrieval & Search, Remote Sensing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Media Technology

In Information Retrieval & Search

In Remote Sensing

Citations in the corpus

Pyramid of Spatial Relatons for Scene-Level Land Use Classification (2015, methodology): “The LULC data set [42] is one of the largest geographical image databases with ground truth, which are publicly available.”
Deep learning in remote sensing: a review (2017, background): “Remote-sensing image retrieval aims at retrieving images having a similar visual content with respect to a query image from a database [109].”
AID: A Benchmark Data Set for Performance Evaluation of Aerial Scene Classification (2016, methodology): “Thus, in our cases, we tested the dictionary size used for IFK and VLAD on the interval [16, 1024], while the interval [128, 8192] for that of BoVW, LLC, LDA, pLSA, and SPM.”
Do deep features generalize from everyday objects to remote sensing and aerial scenes domains? (2015, methodology): “The descriptors we have selected for evaluation were mainly based on previous works [42, 11, 37, 26, 44, 12], in which they were evaluated for remote sensing image classification, texture and color image retrieval/classification, and web image retrieval.”
Unsupervised Quaternion Feature Learning for Remote Sensing Image Classification (2016, methodology): “Bag-of-words image representations based on SIFT or HOG descriptors are common in classification and retrieval tasks for general-purpose [14], as well as for remote sensing images [1], [2], [5], [15], [16].”
Semantic Annotation of High-Resolution Satellite Images via Weakly Supervised Learning (2016, methodology): “and sparse residential, which mainly differ from each other in the density of structures [8].”
A Three-Layered Graph-Based Learning Approach for Remote Sensing Image Retrieval (2016, methodology): “[8] later extended the low-level feature analysis in [23] to the “bag of morphological words” approach for content-based geographical retrieval.”
Training Small Networks for Scene Classification of Remote Sensing Images via Knowledge Distillation (2018, background): “These scene classification methods based on low-level features are efficient on some structures and arrangements, but cannot easily depict the highly diverse and non-homogeneous spatial distributions in images [21].”
Local structure learning in high resolution remote sensing image retrieval (2016, methodology): “Introduction Image retrieval is one of the most challenging tasks in the high resolution remote sensing image (HRRSI) analysis [1].”
Content-Based High-Resolution Remote Sensing Image Retrieval via Unsupervised Feature Learning and Collaborative Affinity Metric Fusion (2016, methodology): “In [2], different similarity metrics for single features are systematically evaluated.”
High-resolution remote-sensing imagery retrieval using sparse features by auto-encoder (2015, background): “Yang and Newsam (2013) exploited Scale Invariant Feature Transform (SIFT) to generate visual words for bag of visual words (BOVW) representation and explored BOVW for aerial image retrieval.”
Classification and Segmentation of Satellite Orthoimagery Using Convolutional Neural Networks (2016, methodology): “Existing methods for solving the object recognition task usually rely on segmentation and feature extraction [9–15].”
Scene-Level Geographic Image Classification Based on a Covariance Descriptor Using Supervised Collaborative Kernel Coding (2016, methodology): “As is illustrated in [2,5], BOVW can represent the image by compact representation through a visual word counts histogram and provides further invariance to the image transformations.”
PatternNet: A Benchmark Dataset for Performance Evaluation of Remote Sensing Image Retrieval (2017, methodology): “Other global features like simple statistics (Yang and Newsam, 2013), and GIST features (Oliva and Torralba, 2001) have also been used for RSIR.”