• Proceedings of the KIEE Conference
• /
• 1998.07g
• /
• pp.2370-2372
• /
• 1998

Recently we have developed an active stereo head-eye system with vergence, name it KIST HECter(Head-Eye System with Colored Stero Vision), based on the analysis of human's neck and eye motion at visual behavior. Our HECter is a five degree-of-freedom system composed of pan and tilt motion in neck part and independent vergence motion of binocular cameras and commonly shared elevation axis in eye part. And stereo vision Provides two color image, which are processed by powerful each TMS32080 vision board. The shape and size are designed to be almost same as human face. The ability to vergence has significant importance and gives many beneficial merits. On its mechanical implementation we adapt a non-parallelogram 4-bar linkage mechanism since it provides high accuracy in transfering motion and enables compact and flexible design.

• Journal of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• v.20 no.6
• /
• pp.26-34
• /
• 2006

In this paper, We proposed he algorithm for defect extraction and a study of the stereo image modeling o inspect defect for the ball height of BGA(ball grid way) device using 2-dimensional images captured by the BGA device of using the high resolution CCD cameras. This paper propose the package/ball area extraction of BGA device part, the FOV(field of view) calibration part, the top point matching part, and ball height measurement method. Each BGA device propose extraction method by defect, Through the experiment, we verified the result.

• Journal of Multimedia Information System
• /
• v.9 no.3
• /
• pp.183-190
• /
• 2022

Image-based 3D object detection is one of the important and difficult problems in autonomous driving and robotics, and aims to find and represent the location, dimension and orientation of the object of interest. It generates three dimensional (3D) bounding boxes with only 2D images obtained from cameras, so there is no need for devices that provide accurate depth information such as LiDAR or Radar. Image-based methods can be divided into three main categories: monocular, stereo, and multi-view 3D object detection. In this paper, we investigate the recent state-of-the-art models of the above three categories. In the multi-view 3D object detection, which appeared together with the release of the new benchmark datasets, NuScenes and Waymo, we discuss the differences from the existing monocular and stereo methods. Also, we analyze their performance and discuss the advantages and disadvantages of them. Finally, we conclude the remaining challenges and a future direction in this field.

• Journal of the Korean Institute of Telematics and Electronics D
• /
• v.35D no.12
• /
• pp.99-107
• /
• 1998

A stereo vision system such as the structure of human's eyes has two cameras at separated positions from which we can obtain two input images and then put them together to create 3-D image. It can show more virtual effect than the conventional 2-D image system. But, the stereo image system has to control the convergence angle so that the stereo disparity could always be zero because observers can be fatigued and unconscious of stereo image in conditions that the stereo disparity is not zero for a long work. Therefore, in the paper, optical JTC system which can process adaptive tracking of a specific moving object is proposed as a new approach to keep the stereo disparity to be zero. In this method, optical JTC system obtains the values of the relative locations of a moving objects in left and right images and then these values are used for maintaining the stereo disparity to be zero. Through some optical experiments the proposed stereo vision system is proved to be insensitive to background noises and operate in real-time.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.15 no.2
• /
• pp.185-193
• /
• 1997

While close range photogrammetry has been widely applied for static deformation analysis, video cameras have many characteristics that make them the sensors of choice for dynamic analysis of rapidly changing situations. They also have limitations. The aim of this research is to explore the potential of a video system for monitoring dynamic objects. A pilot system consists of two camcorders, VCR, and PC with frame grabber. To estimte the performance of this system for moving objects, a car was imaged covering several phases when starting to drive. The sequential images of a moving car were recorded on VCR. 15 images per second were digitized in an off-line mode by frame grabber. The image coordinates of targets attached to the rear bumper of a car were acquired by IDRISI, and the object coordinates were derived based on DLT. This research suggests that home video cameras, PC, and photogrammetric principles are promising tools for monitoring of the moving objects and vibrations as well as other time dependent situations.

• Proceedings of the Korean Association of Geographic Inforamtion Studies Conference
• /
• 2006.05a
• /
• pp.152-157
• /
• 2006

Satellite imagery is generally used for investigating the damage from natural disaster for wide area and remotely piloted vehicle or aerial photos are used for the local damage. But for more detailed information such as damages of public facilities, these methods are inadequate and so in this case field surveying has been carried out. We tried to estimate the damage of public facilities faster and more accurately using photogrammetric method. We developed a digital stereo camera system by fixing two digital cameras on a frame, and with this system the photos of actually damaged areas were collected. The damages were estimated from these stereo photos. Then the estimated data was compared with field surveying data in order to verify our system.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.25 no.3B
• /
• pp.549-556
• /
• 2000

In this paper, we propose a new adaptive stereo object tracking system that can be used when the back ground image is complex and the cameras are not fixed . In this method, we used the Block Matching Algorithm to separate the tracking object form the background image and then the optical JTC system is used to obtain the convergence-controlling and pa/tilt-controlling values fro the left and right cameras. the experimental results are found to track the object robustly & adaptively for the object tracking in various background images, and the possibility of real-time implementation of the proposed system by using the optical JTC is also suggested.

• Journal of Korea Multimedia Society
• /
• v.11 no.11
• /
• pp.1575-1591
• /
• 2008

In this paper, we propose a new method detecting foot motion capture in order to overlap in realtime foot's 3D virtual model from stereo cameras. In order to overlap foot's virtual model at the same position of the foot, a process of the foot's joint detection to regularly track the foot's joint motion is necessary, and accurate register both foot's virtual model and user's foot in complicated motion is most important problem in this technology. In this paper, we propose a dynamic registration using two types of marker groups. A plane information of the ground handles the relationship between foot's virtual model and user's foot and obtains foot's pose and location. Foot's rotation is predicted by two attached marker groups according to instep of center framework. Consequently, we had implemented our proposed system and estimated the accuracy of the proposed method using various experiments.

• Journal of the Institute of Convergence Signal Processing
• /
• v.4 no.3
• /
• pp.27-33
• /
• 2003

The image-based 3D modeling is the technique of generating a 3D graphic model from images acquired using cameras. It is being researched as an alternative technique for the expensive 3D scanner. In this paper, we propose the image-based, 3D modeling system using calibrated stereo cameras. The proposed algorithm for rendering, 3D model consists of three steps, camera calibration, 3D reconstruction, and 3D registration step. In the camera calibration step, we estimate the camera matrix for the image aquisition camera. In the 3D reconstruction step, we calculate 3D coordinates using triangulation from corresponding points of the stereo image. In the 3D registration step, we estimate the transformation matrix that transforms individually reconstructed 3D coordinates to the reference coordinate to render the single 3D model. As shown the result, we generated relatively accurate 3D model.

• The Transactions of the Korean Institute of Electrical Engineers D
• /
• v.55 no.4
• /
• pp.173-180
• /
• 2006

A key component of autonomous navigation of intelligent home robot is localization and map building with recognized features from the environment. To validate this, accurate measurement of relative location between robot and features is essential. In this paper, we proposed relative localization algorithm based on 3D reconstruction of scale invariant features of two images which are captured from two parallel cameras. We captured two images from parallel cameras which are attached in front of robot and detect scale invariant features in each image using SIFT(scale invariant feature transform). Then, we performed matching for the two image's feature points and got the relative location using 3D reconstruction for the matched points. Stereo camera needs high precision of two camera's extrinsic and matching pixels in two camera image. Because we used two cameras which are different from stereo camera and scale invariant feature point and it's easy to setup the extrinsic parameter. Furthermore, 3D reconstruction does not need any other sensor. And the results can be simultaneously used by obstacle avoidance, map building and localization. We set 20cm the distance between two camera and capture the 3frames per second. The experimental results show :t6cm maximum error in the range of less than 2m and ${\pm}15cm$ maximum error in the range of between 2m and 4m.