• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 1994.10a
• /
• pp.510-514
• /
• 1994

This paper deals with an application of neural network to camera calibration with wide angle lens and 2-D range finding. Wide angle lens has an advantage of having wide view angles for mobile environment recognition ans robot eye in hand system. But, it has severe radial distortion. Multilayer neural network is used for the calibration of the camera considering lens distortion, and is trained it by error back-propagation method. MLP can map between camera image plane and plane the made by structured light. In experiments, Calibration of camers was executed with calibration chart which was printed by using laser printer with 300 d.p.i. resolution. High distortion lens, COSMICAR 4.2mm, was used to see whether the neural network could effectively calibrate camera distortion. 2-D range of several objects well be measured with laser range finding system composed of camera, frame grabber and laser structured light. The performance of 3-D range finding system was evaluated through experiments and analysis of the results.

• Proceedings of the KIEE Conference
• /
• 2000.07d
• /
• pp.3031-3033
• /
• 2000

Surveillance system on the internet has attained lots of interests recently. Computer gives surveillance system various functions like remote control and motion detecting. In this paper. auto target tracking system using Pan/Tilt camera is suggested. It consists of UNIX server and Pan/Tilt camera. When UNIX server detect motions from images it sends Pan/Tilt command to camera and camera moves by command. After finishing movement camera replies to server and server starts detecting motion again. To improve performance of motion detecting and tracking images are divided into 9 sub-regions and camera behaves differently. It is certain that robust tracking is achieved when sub-region is applied.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 1999.06a
• /
• pp.125-131
• /
• 1999

In this paper, we address practical methods for calculating camera lens distortion for real time applications. Although the lens distortion problem can be easily ignored for constant-parameter lenses, in the field of real-time camera calibrations, for zoom lenses a large number of calculations are needed to calculate the distortion. However, if the distortion can be calculated independently of the other camera parameter, we can easily calibrate a camera without the need for a large number of calculations. Based on Tsai's camera model, we propose two different methods for calculating lens distortion. These methods are so simple and require so few calculations that the lens distortion can be rapidly calculated even in real-time applications. The first method is to refer to the focal length - lens distortion Look Up Table(LUT), which is constructed in the initialization process. The second method is to use the relationship between the feature points found in the image. Experiments were carried out for both methods, results of which show that the proposed methods are favorably comparable in performance with non-real full optimization method.

• Journal of radiological science and technology
• /
• v.5 no.1
• /
• pp.71-75
• /
• 1982

• Proceedings of the IEEK Conference
• /
• 2003.11a
• /
• pp.417-420
• /
• 2003

Most Embedded Web Camera Server products currently deployed on the market adopt JPEG for compression of video data continuously acquired from the cameras. However, JPEG does not efficiently compress the continuous video stream, and is not appropriate for the Internet where the transmission bandwidth is not guaranteed. In our previous work, we presented the result of designing and implementing an embedded web camera streaming server using MPEG4 codec. But the server in our previous work did not show good performance since one CPU had to both compress and process the network transmission. In this paper, we present our efforts to improve our previous result by using dual CPUs, where DSP is employed for data compression and StrongARM is used for network processing. Better performance has been observed, but it is found that still more time is needed to optimize the performance.

• Journal of the Korean Society for Precision Engineering
• /
• v.20 no.10
• /
• pp.82-88
• /
• 2003

Many visual servoing algorithms have been recently developed by the robot vision researchers. They do not, however, consider the stability of servoing system. The camera calibration is the most important factor to the control stability and performance of position based visual servoing. In this article we describe the ECL(End Point Closed Loop) servoing can make no steady state error for the control of 6-DOF robot of which accuracy is dependent on the camera calibration and kinematics. And we propose a dynamic calibration algorithm, which can improve stability and performance of ECL visual servoing. To verify the potential of our approach, we run assembly experiments and present our finding.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2011.10a
• /
• pp.802-804
• /
• 2011

There are various monitoring and control system using CCTV camera. However, it is important to consider disaster and terrorism with unauthorized changes on location information. Therefore we analyzed performance of observation when the camera is break down as a result from hacking to CCTV monitoring and control system.

• Current Optics and Photonics
• /
• v.7 no.4
• /
• pp.354-361
• /
• 2023

We present the optical design and experimental verification of resolving performance of a 3× long wavelength infrared (LWIR) zoom camera for drones. The effective focal length of the system varies from 24.5 mm at the wide angle position to 75.1 mm at the telephoto position. The design specifications of the system were derived from ground resolved distance (GRD) to recognize 3 m × 6 m target at a distance of 1 km, at the telephoto position. To satisfy the system requirement, the aperture (f-number) of the system is taken as F/1.6 and the final modulation transfer function (MTF) should be higher than 0.1 (10%). The measured MTF in the laboratory was 0.127 (12.7%), exceeds the system requirement. Outdoor targets were used to verify the comprehensive performance of the system. The system resolved 4-bar targets corresponding to the spatial resolution at the distance of 1 km, 1.4 km and 2 km.

• Korean Journal of Air-Conditioning and Refrigeration Engineering
• /
• v.22 no.6
• /
• pp.404-412
• /
• 2010

The purpose of this study is to accomplished an in-site evaluation method for existing building insulation status using Infra-red camera and to consider improvement performance to prevent condensation and draw the optimum insulation design method for building using simulation tool. The research contents of this study are to evaluate validity and suitability of building insulation defect survey using Infra-red camera for apartment housing with temperature and heat flow pattern analyze method. Based on this research, the three corners, weak part in condensation, were selected in apartment building and conducted simulation by three-dimensional steady state. From the results, it is required to strengthen insulation design, and it is founded that existing insulation system typically applied to most Korean apartment housings have serious insulation defect that insulation is disconnected by structural components at the joints of wall-slab and wall-wall in envelope. Thus, it is considerate to need a concrete technology improvement.

• Journal of Institute of Control, Robotics and Systems
• /
• v.21 no.8
• /
• pp.766-772
• /
• 2015

This paper proposes an object detection method based on motion estimation using background subtraction in the fisheye images obtained through omni-directional camera mounted on the vehicle. Recently, most of the vehicles installed with rear camera as a standard option, as well as various camera systems for safety. However, differently from the conventional object detection using the image obtained from the camera, the embedded system installed in the vehicle is difficult to apply a complicated algorithm because of its inherent low processing performance. In general, the embedded system needs system-dependent algorithm because it has lower processing performance than the computer. In this paper, the location of object is estimated from the information of object's motion obtained by applying a background subtraction method which compares the previous frames with the current ones. The real-time detection performance of the proposed method for object detection is verified experimentally on embedded board by comparing the proposed algorithm with the object detection based on LKOF (Lucas-Kanade optical flow).