The Fisher Kernel Coding Framework for High Spatial Resolution Scene Classification

By Bei Zhao, Yanfei Zhong, Liangpei Zhang, Bo Huang. 2016

101 citations recorded by the source corpus.

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.

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

1. Liangpei Zhang
2. Yanfei Zhong
3. Gui-Song Xia
4. Bei Zhao
5. Feng Fei
6. Qiqi Zhu
7. Bo Du
8. Gong Cheng

In Media Technology

1. Liangpei Zhang
2. Yanfei Zhong
3. Gui-Song Xia
4. Bei Zhao
5. Feng Fei
6. Qiqi Zhu
7. Bo Du
8. Gong Cheng

Citations in the corpus

• Bag-of-Visual-Words Scene Classifier With Local and Global Features for High Spatial Resolution Remote Sensing Imagery (2016, methodology): “be used to bridge the semantic gap [7].”
• Hyperspectral Image Classification—Traditional to Deep Models: A Survey for Future Prospects (2021, unknown): “Some popular feature encoding or pooling strategies to enhance the performance of BoVW are Fisher vector coding [51], [73], [74], Spatial Pyramid Matching (SPM) [75], and Probabilistic Topic Model (PTM) [71], [76]– [78].”
• Large patch convolutional neural networks for the scene classification of high spatial resolution imagery (2016, background): “6 12 – 14 In general, BoVW can be summarized into three major steps: (1) feature learning; (2) feature representation (using the learned feature descriptors); and (3) feature classification.”