Jong-Eun Ha

Foreground objects detection using multiple difference images

In visual surveillance, robust foreground object detection is an essential step for further processing such as segmentation, tracking, and extraction of a scenes contextual information. Typical approaches continuously update background images and use then for detecting foreground objects. They involve many parameters that should be adjusted according to the situation where surveillance cameras are operating. We propose an algorithm for the robust detection of foreground objects using multiple difference images that requires only one parameter to adjust. We show that the proposed algorithm gives comparable results with less computation time through experimental results using test images with groundtruths.

Automatic detection of chessboard and its applications

A chessboard image can be used as a pattern for camera calibration and pose estimation. We propose an algorithm for the automatic detection of a chessboard using one circle as a probe. We first generate candidates using the Lucas-Kanade feature detector algorithm. Finally, we find control points on the chessboard using properties inherent on a chessboard pattern. We suggest that a distinct edge along the border line and black and white sequence on the chessboard can be used as constraints. A circle is used as a probe for checking those properties. We show that the proposed algorithm can be used successfully in camera calibration and pose estimation. Experimental results using images acquired under the variation of scale, pose, and illumination shows the robustness of proposed algorithm.

Fast object recognition using dynamic programming from combination of salient line groups

This paper presents a new method of grouping and matching line segments to recognize objects. We propose a dynamic programming-based formulation extracting salient line patterns by defining a robust and stable geometric representation that is based on perceptual organizations. As the endpoint proximity, we detect several junctions from image lines. We then search for junction groups by using the collinear constraint between the junctions. Junction groups similar to the model are searched in the scene, based on a local comparison. A DP-based search algorithm reduces the time complexity for the search of the model lines in the scene. The system is able to find reasonable line groups in a short time.

Specimen alignment in an axial tensile test of thin films using direct imaging and its influence on the mechanical properties of BeCu

This paper proposes a new system for verification of the alignment of loading fixtures and test specimens during tensile testing of thin film with a micrometer size through direct imaging. The novel and reliable image recognition system to evaluate the misalignment between the load train and the specimen axes during tensile test of thin film was developed using digital image processing technology with CCD. The decision of whether alignment of the tensile specimen is acceptable or not is based on a probabilistic analysis through the edge feature extraction of digital imaging. In order to verify the performance of the proposed system and investigate the effect of the misalignment of the specimen on tensile properties, the tensile tests were performed as displacement control in air and at room temperature for metal thin film, the beryllium copper (BeCu) alloys. In the case of the metal thin films, bending stresses caused by misalignment are insignificant because the films are easily bent during tensile tests to eliminate the bending stresses. And it was observed that little effects and scatters on tensile properties occur by stress gradient caused by twisting at in-plane misalignment, and the effects and scatters on tensile properties are insignificant at out-of-plane misalignment, in the case of the BeCu thin film.

New strain measurement method at axial tensile test of thin films through direct imaging

This paper proposes a new method for measuring strain during a tensile test of the specimen with micrometre size through direct imaging. A specimen was newly designed for adoption of direct imaging which was the main contribution of the proposed system. The structure of the specimen has eight indicators that make it possible to adopt direct imaging and it is fabricated using the same process of microelectromechanical system (MEMS) devices to guarantee the feasibility of the tensile test. We implemented a system for non-contact in situ measurement of strain with the specimen, the image-based displacement measurement system. Extension of the gauge length in the specimen could be found robustly by computing the positions of the eight rectangular-shape indicators on the image. Also, for an easy setup procedure, the region of interest was found automatically through the analysis of the edge projection profile along the horizontal direction. To gain confidence in the reliability of the system, the tensile test for the Al–3%Ti thin film was performed, which is widely used as a material in MEMS devices. Tensile tests were performed and displacements were measured using the proposed method and also the capacitance type displacement sensor for comparison. It is demonstrated that the new strain measurement system can be effectively used in the tensile test of the specimen at microscale with easy setup and better accuracy.

Automatic detection of calibration markers on a chessboard

The calibration of a camera is an essential step for the metric reconstruction of the world. Intrinsic and extrinsic parameters of the camera are computed using a one-to-one correspondence between 3-D and 2-D coordinates of control points on the calibration target. Three-dimensional coordinates of control points are given in advance, and 2-D coordinates are detected on the image. The calibration target uses cross lines, circles, and a chessboard pattern to improve detection of the control points on the image. We propose an algorithm to automatically detect the control points on an image, especially for a chessboard pattern. Two symmetric properties of a chessboard pattern related to geometric and brightness distribution are used, and two concentric circles are used as probes for the effective use of the two properties. The two symmetric properties of the chessboard generate the candidates of control points. Finally, a cross-ratio of four points on a line is used for verification. The experimental results using images that vary in scale, pose, and illumination demonstrate the robustness of the proposed algorithm.

A detection cell using multiple points of a rotating triangle to find local planar regions from stereo depth data

This paper presents a method to recognize plane regions for unobstructed motion of mobile robots. When an autonomous agency, using a stereo camera or a laser scanning sensor, is in an unknown 3D environment, the mobile agency must detect the plane regions so that it can independently decide its direction of movement in order to perform assigned tasks. In this paper, a fast method of plane detection is proposed, wherein the normal vector of a triangle is inscribed in a small circular region such that the normal vector passes through the circumcenter area of the triangle. To reduce the effects of noise and outliers, the triangle is rotationally sampled with respect to the center position of the circular region, and a series of inscribed triangles having different normal vectors is generated. The direction vectors of these generated triangles are normalized and the median direction of the normal vectors is then used to test the planarity of the circular region. A pose finding procedure is introduced from range data of a surface to decide the scale and rotation angle of the circular region superimposed on range image data. The method of plane detection is very fast as computation of local information about the plane typically requires sub-ms duration, and the performance of the algorithm for real range data obtained from a stereo camera system has been verified.

Initialization method for self-calibration using 2-views

Recently, 3D structure recovery through self-calibration of camera has been actively researched. Traditional calibration algorithm requires known 3D coordinates of the control points while self-calibration only requires the corresponding points of images, thus it has more flexibility in real application. In general, self-calibration algorithm results in the nonlinear optimization problem using constraints from the intrinsic parameters of the camera. Thus, it requires initial value for the nonlinear minimization. Traditional approaches get the initial values assuming they have the same intrinsic parameters while they are dealing with the situation where the intrinsic parameters of the camera may change. In this paper, we propose new initialization method using the minimum 2 images. Proposed method is based on the assumption that the least violation of the cameras intrinsic parameter gives more stable initial value. Synthetic and real experiment shows this result.

Calibration of structured light stripe system using plane with slits

Abstract. Structured light stripe systems are widely used in industrial applications for acquiring three-dimensional (3-D) information. Calibration is the first necessary step and traditional algorithms compute the 4×3 transformation matrix from image to world. Therefore, 3-D information can be obtained with respect to the camera’s coordinate system, and it cannot be transformed into the laser coordinate system. We propose a new calibration algorithm of a structured light system that can compute the relative pose of the laser coordinate system with respect to the camera coordinate system. We can convert 3-D information either to the laser coordinate system or to the camera coordinate system. The proposed algorithm uses two planes where one plane with multiple slits is set perpendicular to the other plane. We can easily compute the position and rotation of the laser coordinate system using proposed calibration structure. Also, we can solve the extrinsic calibration using just one shot of an image while conventional algorithms require more than two images under different poses. Experiments under various configurations show the feasibility of proposed algorithm.

Automatic context analysis for image classification and retrieval

This paper describes a method for image classification and retrieval for natural and urban scenes. The proposed algorithm is based on hierarchical image contents analysis. First image is classified as urban or natural according to color and edge distribution properties. Additionally scene is classified according to its conditions: illumination, weather, season and daytime based on contrast, saturation and color properties of the image. Then image content is analyzed in order to detect specific object classes: buildings, cars, trees, sky, road etc. To do so, image recursively divided into rectangular blocks. For each block probabilities of membership in the specific class is computed. This probability computed as a distance in a feature space defined by optimal feature subset selected on the training step. Blocks which can not be assigned to any class using computed features are separated into 4 sub-blocks which analyzed recursively. Process stopped then all blocks are classified or size of block is smaller then predefined value. Training process is used to select optimal feature subset for object classification. Training set contains images with manually labeled objects of different classes. Each image additionally tagged with scene parameters (illumination, weather etc).