Quoc-Dat Nguyen

Extraction of 3D Line Segment Using Digital Elevation Data

3D line segment can be regarded as one of the most useful features in constructing 3D model. In this context, this paper presents a new 3D line segment extraction method by using line fitting of elevation data on 2D line coordinates of ortho-image. In order to use elevation in line fitting, the elevation itself should be reliable. To measure the reliability of elevation, in this paper, we employ the concept of self-consistency. We test the effectiveness of the proposed method with a quantitative accuracy analysis using synthetic images generated from Avenches data set of Ascona aerial images. Experimental results indicate that our method generates 3D line segments almost 10 times more accurate than raw elevations obtained by area-based method.

Terrain classification based on 3D co-occurrence features

This paper suggests 3D co-occurrence texture features by extending the concept of co-occurrence feature to the 3D world. The suggested 3D features are described as a 3D co-occurrence matrix by using a co-occurrence histogram of digital elevations at two contiguous positions. With the addition of 3D co-occurrence features, we encounter the high dimensionality problem in the classification process. Since these ANN (Artificial Neural Networks) clustering algorithms are known as robust in this situation, FCM (Fuzzy C-mean) and GBFCM (Gradient Based Fuzzy C-mean) clustering algorithms are employed to implement the terrain classifier. Experimental results show that the classification accuracy with the addition of 3D co-occurrence features is significantly improved over the conventional classification method only with 2D features.

Application of 3d co-occurrence features to terrain classification

Texture analysis has been efficiently utilized in the area of terrain classification. In this application, features have been obtained in the 2D image domain. This paper suggests 3D co-occurrence texture features by extending the concept of co-occurrence feature to the 3D world. The suggested 3D features are described as a 3D co-occurrence matrix by using a co-occurrence histogram of digital elevations at two contiguous positions. The practical construction of the co-occurrence matrix limits the number of levels of digital elevation. If the digital elevation is quantized into a few levels over the whole DEM (Digital Elevation Map), distinctive features cannot be obtained. To resolve this quantization problem, we employ the local quantization technique which can preserve the variation of elevations with a small number of quantization levels. Experiments are carried out using an ANN (Artificial Neural Network) classifier, and it is shown that the classification accuracy is significantly improved over the conventional classification methods with 2D features.

Terrain Classification Using Clustering Algorithms

Texture analysis has been efficiently utilized in the area of terrain classification. The widely used co-occurrence features have been reported most effective for this application. Since the number of co-occurrence features is very high, a terrain classifier based on co-occurrence features should deal with high dimensionality problem. This paper deals with how to solve high dimensionality problems by employing a conventional linear discriminant classifier and clustering algorithms based on ANN (Artificial Neural Network). A implemented linear discriminant classifier is based on dimensionality reduction by using FST (Foley-Sammon transform), and its result is compared with ANN clustering algorithm FCM (Fuzzy C-mean). Experimental results show that the overall classification accuracy using clustering algorithm is good, especially for some particular classes.

Building Extraction Using Fast Graph Search

This paper presents a new building rooftop extraction method from aerial images. In our approach, we extract the useful building location information from the generated disparity map to segment the interested objects and consequently reduce unnecessary line segments extracted in low level feature extraction step. Hypothesis selection is carried out by using undirected graph, in which close cycles represent complete rooftops hypotheses. We test the proposed method with the synthetic images generated from Avenches dataset of Ascona aerial images. The experiment result shows that the extracted 3D line segments of the reconstructed buildings have an average error of 1.69m and our method can be efficiently used for the task of building detection and reconstruction from aerial images.

3D rooftop extraction using perceptual organization based on fast graph search

This paper presents a new building rooftop extraction method from aerial images. In our approach, we extract the useful building location information from the generated disparity map to segment the interested objects and consequently reduce unnecessary line segments extracted in low level feature extraction step. Hypothesis selection is carried out by using undirected graph, in which close cycles represent complete rooftops hypotheses. We test the proposed method with the synthetic images generated from Avenches dataset of Ascona aerial images. The experiment result shows that the extracted 3D line segments of the reconstructed buildings reflect the actual building structure and our method can be efficiently used for the task of building detection and reconstruction from aerial images.

Effects of 3D Co-Occurrence Features on Terrain Classification

This paper suggests 3D co-occurrence texture features by extending the concept of co-occurrence feature to the 3D world. The suggested 3D features are described as a 3D co-occurrence matrix by using a co-occurrence histogram of digital elevations at two contiguous positions. With the addition of 3D co-occurrence features, we encounter the high dimensionality problem in the classification process. In this context, FCM (Fuzzy C-mean) clustering algorithm is employed to implement the terrain classifier, since this ANN (Artificial Neural Networks) clustering algorithms is known as robust in this particular situation. Experimental results show that the classification accuracy with the addition of 3D co-occurrence features is significantly improved over the conventional classification method only with 2D features.