Zhongming Zhao

Urban building extraction from high-resolution satellite panchromatic image using clustering and edge detection

For decades, large-scale aerial photos have been employed to extract building for mapping application. With the successively launching of high-resolution commercial satellites (e.g. IKONOS and QuickBird), high-resolution satellite imagery has been shown to be a cost-effective alternative to aerial photography in many applications. Drawing on the traditional building extraction approach, this paper proposes an algorithm to extract urban building from high-resolution panchromatic QuickBird image using clustering and edge detection. In the first step, an unsupervised clustering by histogram peak selection is used to split the image into a number of classes. The shadows of building are extracted from the lowest gray class. In the second step, the shadows are used as one of the evidences to verify the presence of buildings. Thus, the candidate building objects are extracted from the clustering classes except for the shadow class. Finally, to refine building boundary and further exclude some false building objects, the Canny operator is applied to detect edge of the candidate building objects in the PAN image. From the Hough transform of the detected edges, the main lines, which compose the polyhedral description of the building, can be found. The building extraction results are compared with manually delineated results. The comparison illustrates the efficiency of the proposed algorithm

Clouds and cloud shadows removal from high-resolution remote sensing images

In the remote sensing images recorded by highresolution optical sensors such as SPOT, TM, IKONOS, QUICKBIRD etc., clouds and cloud shadows may unfortunately contaminate the scene. Removing these portions of an image and then filling in the missing data is an important photo editing work. Traditionally the operators have to mask them out from the scene, and cut a patch with similar ground content from clear regions to fill in. It is a tedious work. However good seamless result is hard to achieve. In this paper, we proposed an improved fast fragment-based image completion technique to accomplish this hard work automatically based on Drori’s work. Compared with Drori’s algorithm, our method can reduce computing time remarkably with almost identical results. The experiment results show that our method is valid and performs well. Keywordsclouds and cloud shadows removal; fragment-based image completion; image matting; image composition;

Road detection from Quickbird fused image using IHS transform and morphology

With the development of sensor technique, the commercial high resolution remote image would be directly served in digital city or monitoring urban changing. The topology feature of urban road is changed form line feature to fixed feature of line and segment. Especially to asphalt road, the shadow of urban building and high tree increases the difficult on describing the fixed feature from high resolution panchromatic image. In this paper, we present a region segmentation algorithm based on IHS transform of multispectral image, develop the orientation projection of candidate segment to get road segments and the intersections, and apply the morphology filter to improve the quality of the road detection. At the end of paper, some result image is presented to show the properties of the road network detection from the Quickbird fused multispectral image.

Remote sensing study based on IRSA Remote Sensing Image Processing System

The IRSA Remote Sensing Image Processing System is multi-functional software used for satellite image processing. It consists of over ten parts of the routine and typical used modules in Remote Sensing Image Processing project, such as viewer & file import/export, basic processing, image restoration. As an indigenous developed software, IRSA combines the advantages and kernels of many import famous systems, such as ERDAS imagine, PCI, ENVI and ER-mapper, and avoids some infrequently used functions or details. Hence, it appears concisely, refinedly and practically, acceptable and understandable. Based on this characteristic, we develop an additional set of interrelated data together with the system to face the college students and people who are not familiar with the Remote Sensing Image Processing work. Our experiences prove that we are successful. With the detailed help documents and instruction as well as our elaborately chose, arranged data, the students can study the system step by step. From these data, they get very intuitionistic and sensible cognition to the remote sensing study

Some key pre-processing techniques on airborne imaging spectrometer data for quantitative analysis

Hyperspectral image possesses incomparable advantage over spaceborne multispectral image when it is employed to quantitatively retrieve these parameters such as vegetation type, coverage, biomass, bare soil moisture, etc. This paper focuses on crucial issues present in the pre-processing of hyperspectral image: band selection, edge radiant correction, tangent correction and spectral reflectivity conversion, exemplified by a case study in which modular airborne OMIS-I imaging spectrometer data are employed to evaluate desertification. The author gives comprehensive consideration to the statistic characteristics of each spectral band, diagnostic spectral reflection of different targets and the purpose of practical application, and fixed upon 41 applicable bands after trying different bands. In the course of edge radiant correction, one correction method based on histogram matching was used, and its result was satisfactory. In addition, tangent correction directing against tangent distortion was carried out, which enriched the normal geometric rectification. Lastly, during the process of surface feature spectral reflectivity conversion, the author converted symbolic model into statistic model by employing some necessary theoretical inference and parameter-setting. The result suggests the quality of OMIS-I data get better improved after these processing and basically can meet the requirements of quantitative retrieval for desertification evaluation.

The indigenous remote sensing image processing system and its exertion strategy

The IRSA Remote Sensing Image Processing System is a multi-functional software system used for remotely sensed image processing. It is developed by the national engineering research center for geoinformatics. It includes more than ten parts of modules such as viewer & file import/export, basic processing, and image restoration. As an indigenous, developed software, the IRSA analyses many famous similar import systems, such as ERDAS imagine, PCI, ENVI and ER-mapper system. It absorbs and combines the advantages and kernels of these systems, while abandons some infrequently used functions or details. So it appears concise, refined and practical; and is thus acceptable and understandable to the Chinese custom. However, for many reasons it is still not easy for people to acquaint themselves with the system. Thus, only by laying out self-characteristics and adopting appropriate promoting strategies can the indigenous system gain wide applications and long last life. Key words-IRSA image processing system, comparisons, exertion strategy, promotion

A new identification method for artificial objects based on various features

Artificial object identification and image classification are two basic issues in remote sensing information extraction, but they are often treated as two different research ways during the long-term development of remote sensing. In fact, this disagreement can be reduced with the improvement of spatial resolution and the continuous development of classification methods, especially with the advent of the objected-oriented classification method during recent two years. Based on the object-oriented classification ideas, the GIS (geographical information system) idea was attempted to introduce into artificial object identification by the segmentation and vectorization of object. Results from our work suggest that the object-oriented classification is feasible in practice and has significance in artificial object extraction.

An integrated classification strategy of hyperspectral imaging spectrometer data

It is one of the hotspots to apply the advanced remote sensing data and processing techniques to monitor the desertification. Some monitor factors, such as vegetation, sand and soil moisture, were identified by use of the OMIS-I hyperspectral data individually and its integration with the 7/sub th/ band of ETM data in this study. The results indicate that the former has a high identification precision in vegetation and sand, but in soil moisture it is not well because of the influence of upper vegetation; this can been greatly improved in the latter and the overall identification precision is higher than the former.

Automatic change detection of artificial objects in multitemporal high spatial resolution remotely sensed imagery

Change detection is one of the most important processes in various monitoring applications in multi-temporal remote sensed imagery. We focus on changes of artificial objects, including whether new artifical objects occur or existing artificial objects have changes. This paper proposes a new method to discriminate such changes in multi-temporal images using optimal quantization and block-based linear regression techniques. In the method, multi-temporal images are represented by less quantization level through optimal quantization method respectively; consequently, a block-based linear regression model is used to establish the relationship between multi-temporal images getting the changes effectively and automatically. The method is successfully applied to detect the changes of artificial objects without being affected by various vegetation covers for panchromatic high spatial resolution images such as IRS satellite images.