Image Coordinate System Research Articles

A Microscopic Optically Tracking Navigation System That Uses High-resolution 3D Computer Graphics.

Three-dimensional (3D) computer graphics (CG) are useful for preoperative planning of neurosurgical operations. However, application of 3D CG to intraoperative navigation is not widespread because existing commercial operative navigation systems do not show 3D CG in sufficient detail. We have developed a microscopic optically tracking navigation system that uses high-resolution 3D CG. This article presents the technical details of our microscopic optically tracking navigation system. Our navigation system consists of three components: the operative microscope, registration, and the image display system. An optical tracker was attached to the microscope to monitor the position and attitude of the microscope in real time; point-pair registration was used to register the operation room coordinate system, and the image coordinate system; and the image display system showed the 3D CG image in the field-of-view of the microscope. Ten neurosurgeons (seven males, two females; mean age 32.9 years) participated in an experiment to assess the accuracy of this system using a phantom model. Accuracy of our system was compared with the commercial system. The 3D CG provided by the navigation system coincided well with the operative scene under the microscope. Target registration error for our system was 2.9 ± 1.9 mm. Our navigation system provides a clear image of the operation position and the surrounding structures. Systems like this may reduce intraoperative complications.

Historical Image Registration and Land-Use Land-Cover Change Analysis

Historical aerial images are important to retain past ground surface information. The land-use land-cover change in the past can be identified using historical aerial images. Automatic historical image registration and stitching is essential because the historical image pose information was usually lost. In this study, the Scale Invariant Feature Transform (SIFT) algorithm was used for feature extraction. Subsequently, the present study used the automatic affine transformation algorithm for historical image registration, based on SIFT features and control points. This study automatically determined image affine parameters and simultaneously transformed from an image coordinate system to a ground coordinate system. After historical aerial image registration, the land-use land-cover change was analyzed between two different years (1947 and 1975) at the Tseng Wen River estuary. Results show that sandbars and water zones were transformed into a large number of fish ponds between 1947 and 1975.

Vanishing point-based image transforms for enhancement of probabilistic occupancy map-based people localization.

The widespread use of vision-based surveillance systems has inspired many research efforts on people localization. In this paper, a series of novel image transforms based on the vanishing point of vertical lines is proposed for enhancement of the probabilistic occupancy map (POM)-based people localization scheme. Utilizing the characteristic that the extensions of vertical lines intersect at a vanishing point, the proposed transforms, based on image or ground plane coordinate system, aims at producing transformed images wherein each standing/walking person will have an upright appearance. Thus, the degradation in localization accuracy due to the deviation of camera configuration constraint specified can be alleviated, while the computation efficiency resulted from the applicability of integral image can be retained. Experimental results show that significant improvement in POM-based people localization for more general camera configurations can indeed be achieved with the proposed image transforms.

임의의 위치에서 사용 가능한 영상 기반 변위 계측 시스템

In this study, a vision-based displacement measurement system is developed to accurately measure the displacement of a structure with locating the camera at arbitrary position. The previous vision-based system brings error when the optical axis of a camera has an angle with the measured structure, which limits the applicability at large structures. The developed system measures displacement by processing the images of a target plate that is attached on the measured position of a structure. To measure displacement regardless of the angle between the optical axis of the camera and the target plate, planar homography is employed to match two planes in image and world coordinate systems. To validate the performance of the present system, a laboratory test is carried out using a small 2-story shear building model. The result shows that the present system measures accurate displacement of the structure even with a camera significantly angled with the target plate.

Observation of Rip Current Velocity at an Accidental Event by using Video Image Analysis

ABSTRACT Yoon, S.B.; Park, W.K., and Choi, J., 2014. Observation of rip current velocity at an accidental event by using video image analysis. In order to investigate the magnitude of rip currents of an accident event, in which dozens of people were rescued by coast guards at Haeundae beach, the floating velocities of swimming tubes of people caught by the rip current were estimated by using an analysis of video camera images. The analysis was conducted by tracking the locations of the floating tubes in the video images, converting the image coordinate system into the conventional map coordinate system, and evaluating their Lagrangian velocities. The rip current was strongly developed southwardly from the shore at the center of the beach and its maximum velocity was about 1.12 m/s when observing waves with Hs =0.9 m, Ts=8.2 sec, and θp =S4°E. The observation results was used for a verification of the numerical simulation performed using the nonlinear Boussinesq model FUNWAVE which can resolve wave-phase i...

Calculating Intrinsic and Extrinsic Camera Parameters Based on the PnP Problem

The classical PnP problem is premised on given intrinsic camera parameters. However, for unknown intrinsic camera parameters, given n space points in a world coordinate system and their coordinates in an image coordinate system, the extrinsic camera parameters can be determined. Regarding the existence and uniqueness of a solution for the classical PnP problem, for 4 control points in a plane and an uncalibrated camera, a set of linear equations can be solved based on the correspondence between the space points and the image points. The results show that this approach is feasible and has high calculation precision.

Efficiency of Orientation Parameters on Georeferencing Accuracy of SPOT-5 HRG Level-1A Stereoimages

The efficiency of interior orientation parameters (IOPs) and exterior orientation parameters (EOPs) of the Satellite Pour l'Observation de la Terre 5 (SPOT-5) has been investigated with respect to georeferencing accuracy. A couple of SPOT-5 high-resolution geometric panchromatic level-1A stereoimages with 5-m ground sampling distance covering Zonguldak (Turkey) test field were used for this purpose using orientation parameters provided by metadata files. Ground control points are obtained by Global Positioning System observations. For the purpose of establishing geometric relationship between image and ground coordinate systems, an orbit-attitude parametric model has been used considering imaging geometry of sensor and ephemeris data of satellite. Adjustment consisting of the Gauss-Helmert model was performed in pre- and bundle-adjustment steps. Analyses show that the most efficient parameters are IOPs defined by look angles while EOPs are not significant on the accuracy. The validation of the EOPs and the correlation among IOPs and EOPs are also statistically analyzed. Different variations of point distribution and EOP configurations were preferred, achieving the georeferencing accuracies as ~ ±1 m and ~ ± 5 m at control and check points, respectively. All computations are performed via the developed program package called GeoSpot in Matlab platform.

2A1-Q02 ハンドアイの画像座標に基づくロボットアーム制御(アクチュエータの機構と制御(1))

2A1-Q02 ハンドアイの画像座標に基づくロボットアーム制御(アクチュエータの機構と制御(1))

Automatic Feature Extraction Using Replica Based Approach in Digital Fundus Images

In diabetic retinopathy, exudates play a major part which causes blindness to the diabetic patients. Diabetic patients lost its vision if the exudates will extend to the macular area of the retina. Spreading of this disease on the retina is prevented by automated early detection of presence of exudates. So, it is necessary to prevent the exudates which act as a major challenge in diagnostic task. The presence of exudates is identified based on the variation in grey color presents in retina. The recognition of the optic disc is necessary in the exudates detection procedure while both are related in terms of color, contrast, etc. A various techniques has studied before like morphological approach, region growing approach and so on for the detection of automatic diabetic retinopathy. But the automatic retinal detection leads to a greater chance of loss of sight if the detection is not done properly. So, to enhance the automatic feature extraction in digital fundus images, in this work, we are going to implement replica based approach. Here Optic disk is restricted by the Localized Principal Component Analysis (LPCA) and its shape is detected by a Customized Dynamic Shape Model (CDSM). The extraction of exudates fluid is done by mutual region growing and edge recognition methods. A digital fundus image coordinate system is built to present an enhanced depiction of the features. The success of the LPCA and CDSM algorithms can be attributed to the utilization of the Replica-Based methods. Performance of the replica based approach is measured in terms of optic disk boundary detection, sensitivity and specificity.

Potential Accuracy of Traffic Signs' Positions Extracted From Google Street View

This work demonstrates the potential use of Google Street View (GSV) in engineering measurements. An investigation was conducted to assess the geopositioning accuracy of traffic signs extracted from GSV. A direct linear transformation (DLT) model is used to establish the relationship between the GSV image coordinate system and the ground coordinate system with the aid of ground control points (GCPs). The ground coordinates of the traffic sign can be retrieved by using the solved DLT coefficients. It is found that the root-mean-square (RMS) error of the extracted traffic sign's location is less than 1 m in general. By increasing the number of GSV images and GCPs, the RMS error can be further reduced to 0.5 m or less. This preliminary study demonstrates a viable solution to extract the location of traffic signs from GSV.

3D trajectories re-construction of droplets ejected in controlled tungsten melting studies in ASDEX Upgrade

Two fast visible range camera systems with vertically and tangentially oriented crossed viewing fields in the divertor region of ASDEX Upgrade were used to observe tungsten (W) droplets ejected from a melting W-pin into the divertor plasma. To obtain the spatial (3D) trajectories of the tungsten droplets, the trajectory of a given droplet in the (2D) camera image coordinate system was derived for each view separately. From these data, the 3D droplet position was derived by computing the shortest line segment connecting crossed viewing chords to a given droplet taking the centre coordinate of the line segment as actual coordinate. The experimental error of the derived position was estimated from the length of the connecting line segment. In the toroidal direction, the computed trajectories can be described by an analytical transport model for the droplets assuming an initial droplet diameter in the range of 60–100 μm. In the vertical direction the vertical distance droplets travelled when reaching the edge of the viewing field also agrees with the model predictions. However, discrepancies are found with respect to the time point whence a droplet reverts its initial downwards motion due to centrifugal forces exceeding gravity and plasma generated force components.

2-DOF Angle Measurement of Rocket Nozzle with Multivision

A real-time measurement method is presented for the 2-DOF swing angles of rocket nozzle by the use of multivision and rocket nozzle rotation axes. This method takes offline processing to measure the position of two nozzle rotation axes in image coordinate system by means of multi-vision and identify the rotation transformation relation between image coordinate system and fixed-nozzle coordinate system. During real-time measurement, the nozzle 2-DOF swing angles can be measured with transformation of marker coordinate from image coordinate system to fixed-nozzle coordinate system. This method can effectively resolve the problem of occlusion by markers in wide swing range of the nozzle. Experiments were conducted to validate its correctness and high measurement accuracy.

Lane Model and Calculation of Lane Geometric Structure and Vehicle Deviation Angle and Position in Lane for Intelligent Vehicle

Lane model, lane geometric structure calculation, and vehicle deviation angle and position calculation is a crucial part in automatic drive of intelligent vehicle. In this paper, we introduce a lane model and calculation equations of lane geometric structure and vehicle deviation angle and position in lane. Firstly, we establish the world coordinate system and derive the lane boundary equation based on the actual lane alignment. Secondly, we derive the lane boundary equation in the camera coordinate system through the coordinate transformation. Then we build up the image coordinate system and the pixel coordinate system and derive the lane projective parameter model. Finally, we derive the calculation equations of lane geometric structure and vehicle deviation angle and position in lane. For we introduce the camera roll angle, the lane curvature change rate, and the reasonable assumption in the derivation, the lane model and the calculation are more general and accurate.

基于单幅二维图像的摄像机标定方法研究<br>A Camera Calibration Method Study Based on Single Two-Dimensional Image

为提高场景摄像机的标定精度和标定效率，本文利用摄像机透镜成像原理，基于针孔成像模型，提出了一种基于单幅二维图像的摄像机标定方法。该方法利用最小二乘法直接计算世界坐标系与计算机图像坐标系之间的数学模型，有效解决了摄像机内外参数难以直接计算，且计算精度不高的问题。方法简单有效，实现摄像机快速标定的同时保证了标定精度和可靠性，并提高了标定效率。通常情况下，当空间存在6个已知点的三维世界坐标及其计算机图像坐标时，即可实现摄像机标定。增加空间已知点的数量，还可进一步提高标定精度。利用大量的标定图像数据进行验证，结果表明，该标定算法计算精度高，计算量小，提高了摄像机标定的可靠性和精确性，具有一定的理论意义和实用价值。 In order to improve the calibration accuracy and efficiency of the camera, a camera calibration method based on single two-dimensional image is proposed in this paper. Method of least squares is used to calculate the mathematical model between the world coordinate system and the computer image coordinate system, so that the problem that the Internal and external camera parameters and difficult to calculate directly and that the calculation accuracy is not high can be solved effectively. Calibration accuracy and reliability are guaranteed and also the calibration efficiency is improved in this method. Under normal circumstances, when there are three-dimensional world coordinates and its computer image coordinates of six known points in the space, then camera calibration can be realized. The calibration accuracy can be further improved if the number of space known point is increased. A large number of calibration image data is tested to improve that this calibration method has high accuracy and small amount of calculation, and improves the reliability and accuracy of the camera calibration. This method has theoretical significance and practical value.

스마트폰 자이로센서를 이용한 Frontal-View 변환 알고리즘 설계 및 구현

Attempt to use as a marker of natural objects directly in the real world, but there is a way to use the accelerometer of the smartphone, to convert the Frontal-View virtual, because it asks only the pitch of the camera, from the side there is a drawback that can not be converted to images. The proposed algorithm, to obtain the rotation matrix of axis 3 pitch, roll, yaw, we set the reference point of the yaw of the target image. Then, to compensate for the rotation matrix to determine Myon`inji any floor, wall, the ceiling of the target image. Finally, to obtain the homography matrix for obtaining the Frontal-View to account for the difference between the gyro sensor coordinate system and image coordinate system, so we can get the Frontal-View from the captured images through the projection transformation was designed. Was tested to convert Frontal-View the picture was taken in an environment smartphone environment surrounding floor, walls and ceiling in order to evaluate the conversion program Frontal-View has been implemented, in this paper, design and The conversion algorithm implementation, it was confirmed that to convert a regular basis Frontal-View footage taken from multiple angles.

Genetic Algorithm in the Computation of the Camera External Orientation

The article addresses the solution of the external orientation of the camera by means of a generic algorithm which replaces complicated calculation models using the matrix inverse. The computation requires the knowledge of four control points in the spatial coordinate system and the image coordinate system. The computation procedure fits very well computer-based solutions thanks to it being very simple.

Research of Intelligent Localization of Target for Manipulator Based on the Monocular Vision

A kind of calculation model of 3D space transformation is introduced, which is applicable to the monocular vision of robot manipulator, and the three-dimensional space plane mapping problem of image plane to the actual horizontal plane of monocular vision has been solved. It transforms the imaging coordinate system of target in monocular vision into the world coordinate system of the manipulator, so as to calculate the relative position of targets and the manipulator. The algorithm has better accuracy and reliability, which is proved by contrasting and testing the calculation result of object coordinate system transformed to the actual position coordinates to the sampling points in embedded platform.

Passive vision based seam tracking system for pulse-MAG welding

Welding robots have been widely used in manufacturing process to substitute for human welders. However, most of them are rigid and cannot adjust to variations in the weld seam positions caused by natural welding environmental factors. To address this problem, this paper presents a passive vision-based robotic welding system, which can realize the seam tracking function for pulse-MAG welding. In this paper, the light spectrum of the welding process is analyzed to determine the optical filters used during the image capture. Then, a robust image processing method is proposed to extract the offset from the image which contains much noise. The transformation formula is calibrated to obtain the relationship between the image coordinate system and the robot coordinate system. The tracking strategy is designed to improve the tracking precision and the stability of the welding process. Finally, experiments are conducted on straight line and curved line seam to verify the feasibility of the developed system.

Comparison of Multi Freedom Degrees for Patient Positioning Using Kilovoltage Cone Beam CT in Image-Guided Radiotherapy

Kilovoltage Cone Beam CT (kV CBCT) based image guided radiotherapy (IGRT) is an important approach to correct patient setup which can generate 3D patient anatomy image in radiotherapy process. This paper discusses multi degrees of freedom patient positioning using CBCT based IGRT and presents a new coordinate system classification method. We can conclude that it is essential for correct patient setup to overlap three key points, namely the center of mass (CM) of tumor target, the origin of treatment planning CT image coordinate system, the origin of CBCT image coordinate system). In addition, this paper gives the implementing method of overlapping these three points.

REAL TIME SPEED ESTIMATION FROM MONOCULAR VIDEO

Abstract. In this paper, detailed studies have been performed for developing a real time system to be used for surveillance of the traffic flow by using monocular video cameras to find speeds of the vehicles for secure travelling are presented. We assume that the studied road segment is planar and straight, the camera is tilted downward a bridge and the length of one line segment in the image is known. In order to estimate the speed of a moving vehicle from a video camera, rectification of video images is performed to eliminate the perspective effects and then the interest region namely the ROI is determined for tracking the vehicles. Velocity vectors of a sufficient number of reference points are identified on the image of the vehicle from each video frame. For this purpose sufficient number of points from the vehicle is selected, and these points must be accurately tracked on at least two successive video frames. In the second step, by using the displacement vectors of the tracked points and passed time, the velocity vectors of those points are computed. Computed velocity vectors are defined in the video image coordinate system and displacement vectors are measured by the means of pixel units. Then the magnitudes of the computed vectors in the image space are transformed to the object space to find the absolute values of these magnitudes. The accuracy of the estimated speed is approximately ±1 – 2 km/h. In order to solve the real time speed estimation problem, the authors have written a software system in C++ programming language. This software system has been used for all of the computations and test applications.