• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2009.10a
• /
• pp.713-716
• /
• 2009

In this paper, we propose a vision-based detection of container hole for container location measuring. We use a method for container position using detection of diagonal container holes, because containers have holes that are linked to spreader headblocks. First, we extract images from spreader and detect straight lines to detect container in images using hough transform. Next, proposed method finds positions of cross at the right angles and set candidates of the corner that is linked to spreader headblocks. Finally, this method performs template matching to detect a right corner of containers. Experimental results show that proposed method performed well at detection of container position.

• Journal of Positioning, Navigation, and Timing
• /
• v.6 no.1
• /
• pp.27-33
• /
• 2017

GPS provides the positioning solution in most areas of the world. However, the position error largely occurs in the urban area due to signal attenuation, signal blockage, and multipath. Although many studies have been carried out to solve this problem, a definite solution has not yet been proposed. Therefore, research is being conducted to solve the vehicle localization problem in the urban environment by converging sensors such as cameras and Light Detection and Ranging (LIDAR). In this paper, the precise vehicle localization using 3D LIDAR (Velodyne HDL-32E) is performed in the urban area. As there are many tall buildings in the urban area and the outer walls of urban buildings consist of planes generally perpendicular to the earth's surface, the outer wall of the building meets at a vertical corner and this vertical corner can be accurately extracted using 3D LIDAR. In this paper, we describe the vertical corner extraction method using 3D LIDAR and perform the precise localization by combining the extracted corner position and GPS/DR information. The driving test was carried out in an about 4.5 km-long section near Teheran-ro, Gangnam. The lateral and longitudinal RMS position errors were 0.146 m and 0.286 m, respectively and showed very accurate localization performance.

• Journal of the Institute of Convergence Signal Processing
• /
• v.13 no.4
• /
• pp.173-179
• /
• 2012

In this paper, we presents a new method for vehicle number plate detection. Our method is basically the method extracting a rectangles from a car image because the shape of a vehicle number plate is a rectangle. For detecting the vehicle number plate, firstly, the contrast of the input image is enhanced. Then, the lines in the image are obtained by using LSD(line segment detector), and rectangles in the image are detected from the line data. These rectangles are the candidates of the car plate, from which the car plate is selected. In this procedure, the method of detecting rectangles is our proposed method, which consists of three stages: (1) extracting corners from the line segments by LSD; (2) extracting diagonal lines from the corner data; and (3) detecting rectangles from diagonal line information. And finally the vehicle number plate is selected from these rectangles by using the feature of the vehicle number plate and the inside information of rectangles. In the experiments with the 100 images captured by our digital camera, we have achieved a detection rate of 94%.

• The Transactions of the Korea Information Processing Society
• /
• v.5 no.3
• /
• pp.824-832
• /
• 1998

In this paper, wc proposed new method for corner point detection on digital contours using directional angle and area dcviation_ First of all, dircctional angle was detccted according to contours by lookup table, then corner point was detected using arca deviation aftcr the pixels over standard value had selected as a candidate point. This method has the advantage the rcduction of processing time for real time processing and the reduction of round-off error on digital image reprcsentation. For vcrification of the proposed method simulation results which applied on various tcst pattern were compared with existing methods.

• Proceedings of the IEEK Conference
• /
• 2002.06d
• /
• pp.339-342
• /
• 2002

The feature points in the uncalibrated stereo vision should represent all the characteristics of an image in multiple resolution, have high precision, and have the robustness against mismatching. This paper proposed an algorithm which detects the corner points in multi-resolution for stereo computer vision. The algorithm has sub-pixel precision, rejects the mismatched points, and corrects the lens distortion. We show the performance of the algorithm by estimating the homography with it.

• Journal of Digital Contents Society
• /
• v.15 no.2
• /
• pp.209-217
• /
• 2014

It is very important to classify a lot of table-form documents into the same type of classes or to extract information filled in the template automatically. For these, it is necessary to accurately analyze table-form structure. This paper proposes an algorithm to extract corner points based on line edge segments and to classify the type of junction from table-form images. The algorithm preprocesses image through binarization, skew correction, deletion of isolated small area of black color because that they are probably generated by noises.. And then, it processes detections of edge block, line edges from a edge block, corner points. The extracted corner points are classified as 9 types of junction based on the combination of horizontal/vertical line edge segments in a block. The proposed method is applied to the several unconstraint document images such as tax form, transaction receipt, ordinary document containing tables, etc. The experimental results show that the performance of point detection is over 99%. Considering that almost corner points make a correspondence pair in the table, the information of type of corner and width of line may be useful to analyse the structure of table-form document.

• Journal of the Optical Society of Korea
• /
• v.15 no.2
• /
• pp.152-154
• /
• 2011

We propose a novel method which detects convex and concave corners using radial projection. The sum of two neighbors' differences at the local maxima or minima of the radial projection is compared with the angle threshold for detecting corners. In addition, the use of oriented bounding box trees and partial circles makes it possible to detect the corners of complex shapes. The experimental results show that the proposed method can separately detect the convex and concave corners, and that this method is scale invariant.

• Proceedings of the Optical Society of Korea Conference
• /
• 2007.07a
• /
• pp.339-340
• /
• 2007

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.31B no.3
• /
• pp.80-90
• /
• 1994

In this paper, a high-resolution algorithm for detecting the orientation and position of the SMD and an algorithm for compensating the position and skew angle of the PCB are proposed. The proposed algorithm for the first topic consists of two parts. Its first part is a preprocessing step. in which corner points of the SMD are detected and they are grouped. Then the coarse angle of the principal axis is obtained by line fitting. The second part is a main processing step, in which the fuzzy Hough transform over the limited range of angles is applied to the corner points to detect precisely the orientation of the SMD. The position of the SMD is determined by using its four corner points. The proposed algorithm for the second topic is the one which detects a rotation angle and translation parameters of the PCB using a template matching method. The computer simulation shows that the parametes obtained by proposed algorithms are more precise than those by the several conventional methods considered. The proposed algorithms can be applied to the fast and accurate automatic inspection systems.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.8 no.1
• /
• pp.127-135
• /
• 2009

This paper presents a new technique for corner shape based object retrieval from a database. The proposed feature matrix consists of values obtained through a neighborhood operation of detected corners. This results in a significant small size feature matrix compared to the algorithms using color features and thus is computationally very efficient. The corners have been extracted by finding the intersections of the detected lines found using Hough transform. As the affine transformations preserve the co-linearity of points on a line and their intersection properties, the resulting corner features for image retrieval are robust to affine transformations. Furthermore, the corner features are invariant to noise. It is considered that the proposed algorithm will produce good results in combination with other algorithms in a way of incremental verification for similarity.