Application of 3d-zernike Descriptors in Remote Sensing Target Recognition
نویسندگان
چکیده
In remote sensing (RS) recognition, researchers usually utilize 2D image features to recognize different targets. However, it is always difficult to distinguish targets that have similar image contour but different height. It is because that 2D image contains only 2D contour information, while height information of a target has lost during the imaging process. In this paper, 3D-Zernike descriptors are proposed as a 3D feature to solve this RS recognition problem. 3D-Zernike descriptors have good performance in the field of computer vision [1] and medical image processing [2], however, little work is done in RS field. We tested the characteristics of the feature when working on RS 3D images. Besides, groups of test samples were recognized by using this feature.
منابع مشابه
Shape retrieval using 3D Zernike descriptors
We advocate the usage of 3D Zernike invariants as descriptors for 3D shape retrieval. The basis polynomials of this representation facilitate computation of invariants under rotation, translation and scaling. Some theoretical results have already been summarized in the past from the aspect of pattern recognition and shape analysis. We provide practical analysis of these invariants along with al...
متن کاملAlignment-Independent Comparison of Binding Sites Based on DrugScore Potential Fields Encoded by 3D Zernike Descriptors
Analyzing protein binding sites provides detailed insights into the biological processes proteins are involved in, e.g., into drug-target interactions, and so is of crucial importance in drug discovery. Herein, we present novel alignment-independent binding site descriptors based on DrugScore potential fields. The potential fields are transformed to a set of information-rich descriptors using a...
متن کاملSketch Recognition using Abstract 3D models
We use Abstract 3D models for sketch recognition. The models should be abstract because sketches do not contain texture information which is present in the usual 3D models. Zernike moment descriptors are used for recognition. These descriptors do rotation invariant recognition and also provide the angle of rotation. Also the same concept can be extended to 3D viewpoint detection of the sketch.
متن کاملSurvey on Feature Extraction methods in Object Recognition
Feature extraction is the key process in any pattern recognition issues. There is no exception in object recognition. In this paper, several feature extraction approaches in the field of object recognition are summed up. Zernike and Hu are two invariant moments and geodesic descriptors are applied directly to binary images and so we can have more information about the general shape of the objec...
متن کامل3D Modelling of Under Ground Burried Objects Based on Ground Penetration Radar
There is a growing demand for mapping and 3D modelling of buried objects such as pipelines, agricultural hetitage, landmines and other buried objects. Usually, large scale and high resolution maps from these objects are needed. Manually map generation and modeling of these objects are cost and time consuming and is dependent on lots of resources. Therefore, automating the subsurface mapping and...
متن کامل