• Journal of the Korean Society for Nondestructive Testing
• /
• v.34 no.3
• /
• pp.248-253
• /
• 2014

Camera calibration is an indispensable process for improving measurement accuracy in industry fields such as machine vision. However, existing calibration cannot be applied to the calibration of mid-wave and long-wave infrared cameras. Recently, with the growing use of infrared thermal cameras that can measure defects from thermal properties, development of an applicable calibration target has become necessary. Thus, based on heat conduction analysis using finite element analysis, we developed a calibration target that can be used with both existing visible cameras and infrared thermal cameras, by implementing optimal design conditions, with consideration of factors such as thermal conductivity and emissivity, colors and materials. We performed comparative experiments on calibration target images from infrared thermal cameras and visible cameras. The results demonstrated the effectiveness of the proposed calibration target.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.3 no.4
• /
• pp.867-873
• /
• 1999

Camera calibration is a procedure which calculates internal and external parameters of a camera with the Down world coordinates of the control points. Accurate camera calibration is required for achieving accurate visual measurements. In this paper, we propose a simple and flexible camera calibration using neural networks which doesn't require a special knowledge of 3D geometry and camera optics. There are some applications which are not in need of the values of the internal and external parameters. The proposed method is very useful to these applications. Also, the proposed camera calibration has advantage that resolves the ill-condition as object plane is near parallel image plane. The ill-condition is frequently met in product inspection. For little more accurate calibration, acquired image is divided into two regions according to radial distortion of lens and neural network is applied to each region. Experimental results and comparison with Tsai's algorithm prove the validity of the proposed camera calibration.

• 제어로봇시스템학회:학술대회논문집
• /
• 2004.08a
• /
• pp.1458-1463
• /
• 2004

Tracking is one of the most important pre-required task for many application such as human-computer interaction through gesture and face recognition, motion analysis, visual servoing, augment reality, industrial assembly and robot obstacle avoidance. Recently, 3D information of object is required in realtime for many aforementioned applications. 3D tracking is difficult problem to solve because during the image formation process of the camera, explicit 3D information about objects in the scene is lost. Recently, many vision system use stereo camera especially for 3D tracking. The 3D feature based tracking(3DFBT) which is on of the 3D tracking system using stereo vision have many advantage compare to other tracking methods. If we assumed the correspondence problem which is one of the subproblem of 3DFBT is solved, the accuracy of tracking depends on the accuracy of camera calibration. However, The existing calibration method based on accurate camera model so that modelling error and weakness to lens distortion are embedded. Therefore, this thesis proposes 3D feature based tracking method using SVM which is used to solve reconstruction problem.

• Proceedings of the KIEE Conference
• /
• 2003.07d
• /
• pp.2372-2374
• /
• 2003

With 3-D vision measuring, camera calibration is necessary to calculate parameters accurately. Camera calibration was developed widely in two categories. The first establishes reference points in space, and the second uses a grid type frame and statistical method. But, the former has difficulty to setup reference points and the latter has low accuracy. In this paper we present an algorithm for camera calibration using perspective ratio of the grid type frame with different line widths. It can easily estimate camera calibration parameters such as focal length, scale factor, pose, orientations, and distance. But, radial lens distortion is not modeled. The advantage of this algorithm is that it can estimate the distance of the object. Also, the proposed camera calibration method is possible estimate distance in dynamic environment such as autonomous navigation. To validate proposed method, we set up the experiments with a frame on rotator at a distance of 1,2,3,4[m] from camera and rotate the frame from -60 to 60 degrees. Both computer simulation and real data have been used to test the proposed method and very good results have been obtained. We have investigated the distance error affected by scale factor or different line widths and experimentally found an average scale factor that includes the least distance error with each image. It advances camera calibration one more step from static environments to real world such as autonomous land vehicle use.

• Korean Journal of Remote Sensing
• /
• v.32 no.1
• /
• pp.49-60
• /
• 2016

This paper presents a set of methods to evaluate the image quality of smartphone cameras as compared with that of a DSLR camera. In recent years, smartphone cameras have been used broadly for many purposes. As the performance of smartphone cameras has been enhanced considerably, they can be considered to be used for precise mapping instead of metric cameras. To evaluate the possibility, we tested the quality of one DSLR camera and 3 smartphone cameras. In the first step, we compare the amount of lens distortions inherent in each camera using camera calibration sheet images. Then, we acquired target sheet images, extracted reference lines from them and evaluated the geometric quality of smartphone cameras based on the amount of errors occurring in fitting a straight line to observed points. In addition, we present a method to evaluate the radiometric quality of the images taken by each camera based on planar fitting errors. Also, we propose a method to quantify the geometric quality of the selected camera using edge displacements observed in target sheet images. The experimental results show that the geometric and radiometric qualities of smartphone cameras are comparable to those of a DSLR camera except lens distortion parameters.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.8 no.5
• /
• pp.39-44
• /
• 1998

Determining the absolute location of a mobile robot is essential in the navigation of a mobile robot. In this paper, a method to determine the position of a mobile robot through the visual image of a landrnark using neural networks is proposed. In determining the position of a mobile robot on the world coordinate, there is a position error because of uncertainty in pixels, incorrect camera calibration and lens distortion. To reduce the errors, a method using a BPNN(Back Propagation Neural Network) is proposed. The experimental results are presented to illustrate the superiority of the proposed method when comparing with the conventional methods.

• Proceedings of the KIEE Conference
• /
• 2003.11b
• /
• pp.287-290
• /
• 2003

Over the last few years computer based image processing has become more prominent in forensic science. The image quality from many CCTV systems is too poor for facial recognition. but there are other human characteristics which allow us to recognize individuals from a distance. one of these parameters is a human's height. In this paper, we propose useful height measurement method by auto Position, size adjustment which uses image superimposition and edge detection regardless of lens distortion and not uses conventional photogrammetry calibration methods.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 1996.10a
• /
• pp.219-222
• /
• 1996

During the navigation of mobile robot, one of the essential task is to determination the absolute location of mobile robot. In this paper, we proposed a method to determine the position of the camera from a landmark through the visual image of a quadrangle typed landmark using neural network. In determining the position of the camera on the world coordinate, there is difference between real value and calculated value because of uncertainty in pixels, incorrect camera calibration and lens distortion etc. This paper describes the solution of the above problem using BPN(Back Propagation Network). The experimental results show the superiority of the proposed method in comparison to conventional method in the performance of determining camera position.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 1997.11a
• /
• pp.165-170
• /
• 1997

During the navigation of mobile robot, one of the essential task if to determine the absolute position of mobile robot. In this paper, a method to determine the position of the camera using a vanishing point and neural networks without landmark if proposed. In determining the position of the camera on the world coordinate, there are differences between the real value and the calculated value because of uncertainty in pixels, incorrect camera calibration and lens distortion etc. This paper describes the solution of the above problem using BPNN(Back Propagation Neural Network) and experimental results show the capability to adapt for a mobile robot.

• Journal of the Korea Society of Computer and Information
• /
• v.14 no.6
• /
• pp.41-49
• /
• 2009

In this paper, the multi-camera calibration algorithm for optical motion capture system is proposed. This algorithm performs 1st camera calibration using DLT(Direct linear transformation} method and 3-axis calibration frame with 7 optical markers. And 2nd calibration is performed by waving with a wand of known length(so called wand dance} throughout desired calibration volume. In the 1st camera calibration, it is obtained not only camera parameter but also radial lens distortion parameters. These parameters are used initial solution for optimization in the 2nd camera calibration. In the 2nd camera calibration, the optimization is performed. The objective function is to minimize the difference of distance between real markers and reconstructed markers. For verification of the proposed algorithm, re-projection errors are calculated and the distance among markers in the 3-axis frame and in the wand calculated. And then it compares the proposed algorithm with commercial motion capture system. In the 3D reconstruction error of 3-axis frame, average error presents 1.7042mm(commercial system) and 0.8765mm(proposed algorithm). Average error reduces to 51.4 percent in commercial system. In the distance between markers in the wand, the average error shows 1.8897mm in the commercial system and 2.0183mm in the proposed algorithm.