A Comparative Study of Sampling Analysis in the Scene Classification of Optical High-Spatial Resolution Remote Sensing Imagery

Abstract

Scene classification, which consists of assigning images with semantic labels by exploiting the local spatial arrangements and structural patterns inside tiled regions, is a key problem in the automatic interpretation of optical high-spatial resolution remote sensing imagery. Many state-of-the-art methods, e.g., the bag-of-visual-words model and its variants, the topic models and unsupervised feature learning-based approaches, share similar procedures: patch sampling, feature learning and classification. Patch sampling is the first and a key procedure, and it has a considerable influence on the results. In the literature, many different sampling strategies have been used, e.g., random sampling and saliency-based sampling. However, the sampling strategy that is most suitable for the scene classification of optical high-spatial resolution remote sensing images remains unclear. In this paper, we comparatively study the effects of different sampling strategies under the scenario of scene classification of optical high-spatial resolution remote sensing images. We divide the existing sampling methods into two types: random sampling and saliency-based sampling. Here, we consider the commonly-used grid sampling to be a specific type of random sampling method, and the saliency-based sampling consists of keypoint-based sampling and salient region-based sampling. To compare their performances, we rely on a standard bag-of-visual-words model to learn the global features for testing because of its simplicity, robustness and efficiency. In addition, we conduct experiments Remote Sens. 2015, 7 14989 using a Fisher kernel framework to validate our conclusions. The experimental results obtained on two commonly-used datasets using different feature learning methods show that random sampling can provide comparable and even better performance than all of the saliency-based strategies.

Fast Binary Coding for the Scene Classification of High-Resolution Remote Sensing Imagery

“…This encouraging result indicates that we can easily obtain a set of suitable filters without any learning procedure. In fact, there are several works [11,49,71,72] that have also shown similar observations that random filters can be very effective in texture and scene classification, and our promising results of RP filters further support this evidence. We also compare the capability of the hand-engineered filters with the learned filters in the FBC framework.…”

Content-Based High-Resolution Remote Sensing Image Retrieval via Unsupervised Feature Learning and Collaborative Affinity Metric Fusion

“…The UCM dataset has been widely utilized in the performance evaluation of high-resolution remote sensing image retrieval [2][3][4][5][6] and high-resolution remote sensing image scene classification [14,25,31,32,[34][35][36][37][38][39][40]. More specifically, the UCM dataset is generated through manually labeling aerial image blocks of large images from the USGS national map urban area imagery.…”

“…The WH dataset is created by labeling satellite image blocks from Google Earth by Wuhan University. It has been widely utilized in the remote sensing image scene classification task [33,[40][41][42][43]. The WH dataset comprises 19 land cover categories, each class contains 50 images with 600 × 600 pixels, and each pixel is measured in the RGB spectral space.…”

Detection of High-Density Crowds in Aerial Images Using Texture Classification

“…In computer vision, these words can be seen as cluster centers in a feature space, leading to the BoW model. The BoW model has been widely used for texture classification [20][21][22][23] and also in remote sensing [24,25], however, never for the detection of a crowd in remotely sensed images.…”