Comparing SIFT descriptors and gabor texture features for classification of remote sensed imagery
By Yi Yang, Shawn D. Newsam. 2008
153 citations recorded by the source corpus.
A richer set of land-cover classes are observable in satellite imagery than ever before due to the increased sub-meter resolution. Individual objects, such as cars and houses, are now recognizable. This work considers a new category of image descriptors based on local measures of saliency for labelling land-cover classes characterized by identifiable objects. These descriptors have been successfully applied to object recognition in standard (non-remote sensed) imagery. We show they perform comparably to state-of-the-art texture descriptors for classifying complex land-cover classes in high- resolution satellite imagery while being approximately an order of magnitude faster to compute. This speedup makes them attractive for realtime applications. To the best of our knowledge, this is the first time this new category of descriptors has been applied to the classification of remote sensed imagery.
Subfields: Computer Vision and Pattern Recognition, 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
- Liangpei Zhang
- Gui-Song Xia
- Xiaoqiang Lu
- Jocelyn Chanussot
- Yanfei Zhong
- Xiang Bai
- Junwei Han
- Jingwen Hu
In Remote Sensing
- Liangpei Zhang
- Keiller Nogueira
- Yanfei Zhong
- Gui-Song Xia
- Jingwen Hu
- Fan Hu
- Otávio Augusto Bizetto Penatti
- J. A. D. Santos
Citations in the corpus
- Ieee Geoscience and Remote Sensing Letters Fusion of Global and Local Descriptors for Remote Sensing Image Classification (unknown): “BoW classifiers of aerial images have been thoroughly investigated in [5] and [17].”
- AID: A Benchmark Data Set for Performance Evaluation of Aerial Scene Classification (2016, methodology): “Although single type of features works well for classification [54], [55], [61], the combinations of complementary features can often improve the results [12], [19], [27].”
- Training Small Networks for Scene Classification of Remote Sensing Images via Knowledge Distillation (2018, methodology): “Low-level methods first extract low-level hand-crafted features, including SIFT (scale invariant feature transform) [13,14], HOG (histogram of oriented gradients) [15], structural texture similarity [16], LBP (local binary patterns) [17], Gabor descriptors [18], etc.”
- Towards better exploiting convolutional neural networks for remote sensing scene classification (2016, methodology): “Although several of these visual descriptors have been proposed or successfully used for remote sensing image processing [26, 2, 27], there are many applications that demand more specific techniques mainly due to the presence of non-visible information provided by multiple spectral bands and the…”
- New machine learning method for image-based diagnosis of COVID-19 (2020, methodology): “Image classification achieved by extracting the import features from the images by a descriptor (e.g., SIFT [9] and image moment [10]), and then these features can be used in the classification task using classifiers such as SVM [11].”
- Hyperspectral Image Classification—Traditional to Deep Models: A Survey for Future Prospects (2021, methodology): “Usually they are used to construct bag-of-visualwords (BoVW) models [30], [31], [34], [62], [66]–[71] and HOG”
- Do deep features generalize from everyday objects to remote sensing and aerial scenes domains? (2015, methodology): “Although many descriptors have been proposed or successfully used for RS image processing [42, 11, 3], some applications require more specific description techniques.”
- 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].”