Papers by Keyword: Image Processing

Abstract: In this paper, we consider the problem of automatic monitoring of industrial environments. We propose a self-learning algorithm for safe cooperation in industrial environments. Our algorithm is based on the system of mobile robots.

Abstract: This paper proposes a novel non-contact single point ranging method in which the laser light source is replaced by the white light in the projector. It will project the blank points on the standard plate. With the videos by CCD camera, the advanced image processing technology will be applied to correct the image accuracy and remove the exterior interference to finish the ranging optimization. The experiment results illustrate the method is accessible and the measurement errors are acceptable.

Abstract: In this paper we present a fast indoor stereo matching algorithm based on canny edge detection and line moments. We first detect image edge by using Canny operator, then find the target objects according line moments, the feature points of the objects’ contours are extracted. Finally, matching the pixel in stereo image pair according the angle vector. The algorithm effectively reduces the computational complexity, computational cost is decreased greatly. The experimental results show that the algorithm is possible and valid.

Abstract: In this article, a level ruler Precision Verification System program of the mobile-camera image processing technology that is based on the camera mobile image processing technology is proposed, as a result of the research for the existing barcode type level ruler verification system and a high-precision grating sensor system hardware structure is also built. Secondly, we calculate the uncertainty of the system, and at last do the system stability test that the results show that the system achieves the test requirements. On the barcode type level existing ruler verification system research, proposed a camera mobile image processing technology based on the level ruler of precision calibration system, builds a detection sensor system with high precision grating, realizes automatic acquisition level ruler barcode image, method of application without barcode image with barcode image subtraction the preliminary processing of image acquisition, eliminate the influence of background light on the image acquisition, the uncertainty of the calibration system of the theoretical calculation and experimental verification, the results show that the system achieves the test requirements.

Abstract: In the task of the image processing and analysis, the background noise removal is a important step. In the image background noise removal, there are many methods which is popular for the researchers. For example, the gray threshold methods are commonly taken to remove the noises which have large contrast to the interest objects. However, there are many noises with no variance with the interest objects in the gray level. For these noises, the gray level based noise removal method is totally futile, while the contour feature has its super performance for reducing this sort of noise. For the contour feature based image background removal method, the contour model is the key. This paper proposes a novel method for modeling the contour feature of the interest objects. With this method, a novel background noise which has the same gray level to the background noise is totally removed.

Abstract: Automatic recognition of the line in the image is an important work in the field of machine vision and image processing. Focusing on the problem of the computational cost and large invalid sampling in the line extraction algorithm using standard Hough transform (HT). An improved HT algorithm is proposed to solve these problems. The parameters of the improved algorithm can be reduced to one and the accumulator is operated by setting the tolerance. Then the existence of linear is determined by seting the threshold. The experimental results show that the algorithm not only can effectively solve the problem of local maxima and improves the algorithm speed and reduces the storage space,but also the accuracy of line extraction is improved.

Abstract: This paper presents a component of unified processing for remote sensing image files based on GDAL. The component, which developed an interface specification for unified remote sensing image processing, encapsulates processing operations of remote sensing image files to form an integral, such as GeoTIFF, HDF, SHP, etc.. The component effectively achieves a variety format image files to read and write, save, display, and conversion, to facilitate the development and application of remote sensing image processing system, and reduce the cost of software development.

Abstract: The circle-end-face centering device which is in the base of image processing accomplishes the center of the cylinders end face by digital image processing. Through edge extraction and doing the matching in the calculation of the least square method, the coordinate of the central of the circle can be calculated. At last, the drill will be moved to the central of the circle and do the punching by the actuator. This equipment is in the high accuracy and speed compared with the traditional way and the concentric circle laser of marking with the center. Meanwhile, the actuator consists of the programmable logic controller, touch panel and servo drivers which is in the high stability and accuracy. Certainly it is easy to be controlled by the method.

Abstract: Mean free path of dislocation motion have a significant effect on mechanical properties because dislocation motion is blocked by eutectics and intermetallics in Al-Si casting alloys. In this study, we proposed a statistical method to evaluate mean free path of dislocation motion by using image processing, and investigated relation between the measured mean free path and mechanical properties of Al-Si casting alloys.

Abstract: Cross-gratings or two-dimensional gratings have found applications in precision displacement measurement for nanoscale machine tools or mask-wafer alignment in photo-lithography. The orthogonality of displacement measurement or alignment in two perpendicular directions is assured by the orthogonality of the grating grooves. Once the grooves are not exactly normal to each other, it should be calibrated before measurement or alignment to guarantee the accuracy. Scanning probe microscopy (SPM) and optical diffractometry (OD) are commonly used for highly accurate calibration of cross-grating orthogonality. In this paper, two methods based on diffraction are proposed for middle accuracy measurement at relative higher speed. At first, we briefly explain the configuration of each method. The calibration results of cross-gratings are shown. We also discuss the results of uncertainty analysis and the cause of main uncertainty sources.