Automatic segmentation of high resolution satellite (HRS) imagery is the first step and a very important part of object-oriented
approaches. The HRS sensors increase the spectral within-field heterogeneity and the structural or spatial details
of images. Spatial features are important to HRS image analysis in addition to spectral information. This paper presents a
novel feature extraction method and evaluates its performance on segmentation of HRS images based on adaptively
integrating multiple features. The first two principal component (PC) images are obtained by principal component
analysis (PCA) of a multispectral image and used to calculate the texture and spectral distributions of a region, which are
denoted by two-dimensional (2D) histograms. The 2D texture histogram of a region is the joint distribution of its two
texture labeled images calculated by rotation invariant local binary pattern (LBP) operator. The spectral distribution of a
region is the joint distribution of the pixel values of its two PC images after normalization. The color feature is a 2D
hue/saturation histogram that is computed through IHLS color space. The three features are integrated by a weighted sum
similarity measure and used to hierarchical splitting, modified agglomerative merging and boundary refinement
segmentation framework. The segmentation scheme based on adaptively integrating multiple features demonstrates
promising results.
Automatic segmentation of high resolution satellite (HRS) imagery is the first step and a very important part of object-oriented approaches. As the resolution of satellite imagery increases, the spectral within-field heterogeneity and the structural or spatial details increase at the same time. Spatial features are important to HRS image analysis in addition to spectral information. This paper presents a novel feature extraction method and evaluates its performance on segmentation of HRS images and color texture images. The first two principal component (PC) images are obtained by principal component analysis (PCA) of a multispectral image. Two texture labeled images are calculated pixel-by-pixel on the PC images through a rotation invariant local binary pattern (LBP) form that we present in this paper. The two texture labeled images are used to calculate the discrete two-dimensional texture histogram of the image. The spectral distribution of a region is the joint distribution of the pixel values of its two PC images after normalization. Then the two histograms are regarded as the texture and spectral distributions of the region and used to calculate the texture and spectral similarity between two regions which is used to determine whether to split a region or merge adjacency regions in the split and merge segmentation framework.
Texture is a very important feature in image analysis including content-based image retrieval (CBIR). A common way of retrieving images is to calculate the similarity of features between a sample images and the other images in a database. This paper applies a novel texture analysis approach, local binary patterns (LBP) operator, to 1m Ikonos images retrieval and presents an improved LBP histogram spatially enhanced LBP (SEL) histogram with spatial information by dividing the LBP labeled images into k*k regions. First different neighborhood P and scale factor R were chosen to scan over the whole images, so that their labeled LBP and local variance (VAR) images were calculated, from which we got the LBP, LBP/VAR, and VAR histograms and SEL histograms. The histograms were used as the features for CBIR and a non-parametric statistical test G-statistic was used for similarity measure. The result showed that LBP/VAR based features got a very high retrieval rate with certain values of P and R, and SEL features that are more robust to illumination changes than LBP/VAR also obtained higher retrieval rate than LBP histograms. The comparison to Gabor filter confirmed the effectiveness of the presented approach in CBIR.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.