Bag-of-visual-words and spatial extensions for land-use classification

By Yi Yang, Shawn D. Newsam. 2010

3,081 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Media Technology

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

Citations in the corpus

EuroSAT: A Novel Dataset and Deep Learning Benchmark for Land Use and Land Cover Classification (2017, methodology): “studied [6], [19], [20], [27], [29] remotely sensed image classification dataset known as UC Merced (UCM) land use dataset was introduced by Yang et al.”
Remote Sensing Image Scene Classification: Benchmark and State of the Art (2017, methodology): “The early works for scene classification are mainly based on handcrafted features [22, 23, 27, 38, 44, 51, 56, 62, 80, 82, 99-103].”
Knowledge Capture and Replay for Continual Learning (2020, methodology): “Continual reconstruction is also compared on UC Merced Land Use [23], a real-world large-scale remote sensing dataset with 256x256 resolution and 21 classes.”
WILDS: A Benchmark of in-the-Wild Distribution Shifts (2020, neutral): “A number of existing remote sensing datasets have limited spatial or temporal scope, including the UC Merced Land Use Dataset (Yang and Newsam, 2010), TorontoCity (Wang et al., 2017), and SpaceNet (DigitalGlobe and Works, 2016).”
TI-POOLING: Transformation-Invariant Pooling for Feature Learning in Convolutional Neural Networks (2016, background): “With minor modifications, also rotation-invariance can be achieved [29].”
Application and Evaluation of a Hierarchical Patch Clustering Method for Remote Sensing Images (2016, methodology): “Dataset 3 was the UC Merced land use dataset [30], which consisted of 21 classes of optical image patches, with 100 patches in each class and 2100 patches in total.”
Land-Use Scene Classification in High-Resolution Remote Sensing Images Using Improved Correlatons (2015, methodology): “HRIs provide more of the appearance and spatial arrangement information helpful in land-use scene category recognition [2].”
Self-Supervised Pretraining Improves Self-Supervised Pretraining (2021, neutral): “UC-Merced [62] is a 21-class aerial imagery dataset [1260/420/420].”
A Color-Texture-Structure Descriptor for High-Resolution Satellite Image Classification (2016, methodology): “K ÿ T k ÿ In addition, HIK SVM is also widely-used to compare BOW models. an object-based scene: the 21-class UC Merced dataset [55], which was manually generated from large images from the USGS National Map Urban Area Imagery collection for various urban areas around the United States.”
The Fisher Kernel Coding Framework for High Spatial Resolution Scene Classification (2016, methodology): “During the training of the SVM classifier, the histogram intersection kernel (HIK) is adopted due to its performance in image classification [44].”
Unsupervised Feature Learning for Aerial Scene Classification (2014, methodology): “Remaining rows show sample images from the UCMERCED data set [1].”
MARTA GANs: Unsupervised Representation Learning for Remote Sensing Image Classification (2016, methodology): “The dataset (Yang & Newsam, 2010) consists of images of 21 land-use classes selected from aerial optical images of the US Geological Survey, taken over various regions of the United States.”
Satlas: A Large-Scale, Multi-Task Dataset for Remote Sensing Image Understanding (2022, methodology): “Four are existing large-scale remote sensing datasets that involve classiﬁcation with between 21 and 63 categories: UCM [53], AID [52], RESISC45 [18], and FMoW [21].”
A High Resolution Optical Satellite Image Dataset for Ship Recognition and Some New Baselines (2017, background): “Yang et al. (Yang and Newsam, 2010) introduced a public dataset “LULC”, which contains some overhead ship images collected from the United States Geological Survey National Map.”
Bag-of-Visual-Words Scene Classifier With Local and Global Features for High Spatial Resolution Remote Sensing Imagery (2016, methodology): “To further evaluate the performance of LGFBOVW, the experimental results utilizing spatial pyramid matching (SPM) [16] and the experimental results on the UC Merced data set, as published in the latest papers by Yang and Newsam in 2010 [4], Cheriyadat in 2014 [5], Chen and Tian in 2015 [8], and Mekh”
A Comparative Study of Sampling Analysis in the Scene Classification of Optical High-Spatial Resolution Remote Sensing Imagery (2015, methodology): “Although the methods of scene classification involve many different methodologies, such as the bag-of-visual-words (BoVW) models [1,4,9], the topic models [3,8] and unsupervised feature learning-based methods [10,13,14], it is clear that one can summarize these”