In order to fully consider the local spatial constraints between neighboring objects in object-based change detection (OBCD), an OBCD approach is presented by introducing a refined Markov random field (MRF). First, two periods of images are stacked and segmented to produce image objects. Second, object spectral and textual histogram features are extracted and G-statistic is implemented to measure the distance among different histogram distributions. Meanwhile, object heterogeneity is calculated by combining spectral and textual histogram distance using adaptive weight. Third, an expectation-maximization algorithm is applied for determining the change category of each object and the initial change map is then generated. Finally, a refined change map is produced by employing the proposed refined object-based MRF method. Three experiments were conducted and compared with some state-of-the-art unsupervised OBCD methods to evaluate the effectiveness of the proposed method. Experimental results demonstrate that the proposed method obtains the highest accuracy among the methods used in this paper, which confirms its validness and effectiveness in OBCD.
As an advanced technology, satellite remote sensing has been applied in a variety of fields and has brought numerous social benefits. This paper introduces a new operational satellite imagery processing system and conducts a case study using it by processing ZY-02C and ZY-3 satellite imagery. By way of this case study, this paper proposes a workflow involving the key generation technologies with fully automatic generation of advanced remote sensing products, such as the digital elevation model (DEM), the digital orthophoto map (DOM), and the high-resolution color-fused image. The proposed workflow in this system tackles the key practical issues related to the domestic satellite imagery process, such as low processing efficiency, low utilization, poor integration, etc. This system utilizes the following key generation technologies: automatic registration between the satellite imagery and the existing multi-geographic data, strip aerial triangulation of three-line array satellite images, multi-sensor image registration and fusion, dense matching of photogrammetric point clouds, and automatic correct splicing of wide range images. The proposed process system consists of two parts. The first part is the creation of a geographic information production mode with no manual intervention. This mode aims to improve the accuracy and efficiency of mass domestic satellite images to produce highly precise orientation by using global public basic geographic information databases like Map World, Google Earth, etc. The second part is the design of a workflow to ensure the stability of the production time and quality of domestic satellite imagery's advance product generation. Finally, this paper also discusses the accuracy of the process of image orientation and the precision of advanced products such as high-resolution color-fused image (ZY-02C), DEM (ZY-3), and DOM (ZY-3). The results show that the products of the proposed process system meet the requirements in both efficiency and quality, and the proposed process system is ready for future real-time domestic remote satellite imagery generation.
For the purpose of improving the efficiency of GIS data-updating over urban areas, a new approach of aerial
triangulation (AT) with ground control points auto extracted from the existing AT results is introduced in the paper. The
existing AT results mean the existing aerial imagery with interior and exterior orientation parameters. Through a multi-views
image matching between the new aerial photos and old photos, enormous ground control points could be auto
extracted and their ground coordinates could be calculated by the forward-intersecting of old aerial photos. The
efficiency and accuracy of the method have been tested and analysed with several actual aerial imagery blocks. The
experiment results presented in this paper shows that the method could not only extract enormous GCPs automatically
which lead to a greatly improvement of the efficiency of AT over urban areas, but also achieve the same level of
accuracy of the old AT results.
In this paper, the different methods of orientating different resolution satellite images with the existing vector maps are
introduced. To moderate high resolution satellite image, such as SPOT5 image, the vector road maps are often used for
the orientation, and the vector lines in the maps usually represent the road central lines. And to higher resolution satellite
image, such as QuickBird image, the vector lines in the maps usually represent the road edges, instead. Beside that, the
different extend of details of the images makes it necessary to handle them with different methods. Because in very high
resolution satellite images a lot of disturbing image features will be extracted along with the wanted one. A voting
algorithm is employed to solve the problem, the approach is based on the previous work where an edge-based voting
strategy was studied. The voting algorithm has the advantages of globally optimal and robust to noise. It can directly
estimate the transformation parameters, meanwhile providing the potential matches of edge points, these matches can
then be used in calculating the accurate orientation parameters, and providing the chance of change detection since the
unchanged objects can be marked out with this method.
Three key techniques in registration of CBERS-02B image are introduced in this paper. Including an improved image
matching strategy aided by a voting algorithm, the voting algorithm directly estimates the transformation parameters of
image instead of finding the one to one corresponding, making the image matching much more efficient and reliable.
Beside that, the method of handling the interior deformation problem caused by the incorrect splicing of three sub CCD
arrays is introduced. At last, a virtual combination of satellite image technique is introduced, the adjacent satellite images
in the same orbit are virtually combined to form a large image which is taken as the orientation unit, purposed on
accelerating the orientation process speed and decreasing the probability of orientation failure. With the techniques
mentioned above, the two main problems about CBERS-02B image: the inaccurate ephemeris parameters and the poor
internal accuracy caused by the incorrect splicing of three sub CCD arrays are solved successfully, the absolute
positioning accuracy reaches 1:10000 mapping accuracy and the internal accuracy reaches sub-pixel after the orientation
process. It indicates that extensive usage of Chinese high resolution satellite imagery may become possible and practical.
A new approach for three-dimensional reconstruction of industrial parts with non-metric image sequences and hybrid point-line photogrammetry is proposed. Non-metric image sequence and CAD-designed data are used as source of information. The strategy of our approach is to reconstruct the parts automatically with points and line segments extracted from imagery. Hybrid point-line photogrammetry is used to reconstruct sheetmetal parts accurately, and the reconstructed model can be used for visualization and inspection. The reconstruction system can run automatically and fastly, and the output of hybrid point-line photogrammetry is the final 3D geometric model of the part. Results of real images of several parts are very satisfying, which shows a promising potential in automatic 3D reconstruction of widely existed industrial parts mainly composed of points and lines.
A flexible new camera calibration technique using 2D-DLT and bundle adjustment with planar scenes is proposed in this paper. The equation of principal line under image coordinate system represented with 2D-DLT parameters is educed using the correspondence between collinearity equations and 2D-DLT. A novel algorithm to obtain the initial value of principal point is put forward in this paper. The practical decomposition algorithm of exterior parameters using initial values of principal point, focal length and 2D-DLT parameters is discussed elaborately. Planar-scene camera calibration algorithm with bundle adjustment is addressed. For the proposed technique, either the camera or the planar pattern can be moved freely, and the motion need not be known. Very good results have been obtained with real data calibration. The calibration result can be used in some high precision applications, such as reverse engineering and industrial inspection.