• Journal of Institute of Control, Robotics and Systems
• /
• v.21 no.8
• /
• pp.788-793
• /
• 2015

This paper proposes a path planning algorithm to reduce the inspection time of AOI (Automatic Optical Inspection) machines for SMT (Surface Mount Technology) in-line system. Since the field-of-view of the camera attached at the machine is much less than the entire inspection region of board, the inspection region should be clustered to many groups. The image acquisition time depends on the number of groups, and camera moving time depends on the sequence of visiting the groups. The acquired image is processed while the camera moves to the next position, but it may be delayed if the group includes many components to be inspected. The inspection delay has influence on the overall job time of the machine. In this paper, we newly considers the inspection delay time for path planning of the inspection machine. The unified approach using genetic algorithm is applied to generates the groups and visiting sequence simultaneously. The chromosome, crossover operator, and mutation operator is proposed to develop the genetic algorithm. The experimental results are presented to verify the usefulness of the proposed method.

• Journal of Advanced Navigation Technology
• /
• v.16 no.5
• /
• pp.831-838
• /
• 2012

In the transmission system, the transmission efficiency can be increased by applying the proper character coding method. This paper is to show the character coding rule in computer and information equipment etc to improve the transmission efficiency in datacommunications. The character coding rule showing in this paper was suggested by considering the two view points. First one is FLAG bits in HDLC and PPP protocol on datalink layer in OSI 7 layer. Second one is one of the scrambling method, HDB-3, on physical layer in OSI 7 layer. The former is to prevent the sequence of over 5bits of "1" in the character codes. The latter is to prevent the sequence of over 4bits of "0" in the character codes.

• Transactions of the Korean Society for Noise and Vibration Engineering
• /
• v.19 no.12
• /
• pp.1260-1268
• /
• 2009

Three methods(the stepped sine method, the statistical method(random excitation method) and the maximum-length sequence(MLS) method) for head-related transfer functions(HRTFs) are experimentally compared in view point of accuracy and efficiency. First, the stepped sine method has high signal-to-noise ratio, but low efficiency. Second, the statistical method is fast measurement speed, but weak to noise than the other methods. Finally, the MLS method shows both good efficiency and high signal-to-noise ratio, but it needs additional software or equipment such as MLS signal generator. For comparison of measurement accuracy, HRTFs of KEMAR dummy are measured for various azimuths and elevations. Error norms for magnitude and phase of HRTFs are defined and calculated for the measured HRTFs. The calculated error norms show that the methods give similar results in magnitude and phase except a little phase difference in the MLS method.

• The KIPS Transactions:PartB
• /
• v.10B no.2
• /
• pp.127-134
• /
• 2003

This paper is intended to develop an algorithm for automatic detection of traffic accidents using image sequences. This algorithm is designed for detecting stopped vehicles traffic accidents, break down, illegal stop in the road shoulder - on the range of camera view. Virtual traps are set on accident-prone spots. We analyze the changes in gray levels of pixels on the virtual traps which represent the motion of vehicles on the corresponding spots. We verify the proposed algorithm by simulating some situations and checking if it detect them correctly.

• Proceedings of the Korean Information Science Society Conference
• /
• 2007.06c
• /
• pp.477-481
• /
• 2007

A background is a part where do not vary too much or frequently change in an image sequence. Using this assumption, it is presented a background acquisition algorithm for not only static but also dynamic view in this paper. For generating background, we detect a region, where has high correlation rate compared within selected region in the prior pyramid image, from the searching region in the current image. Between a detected region in the current image and a selected region in the prior image, we calculate movement vector for each regions in time sequence. After we calculate whole movement vectors for two successive images, vector histogram is used to determine the camera movement. The vector which has the highest density in the histogram is determined a camera movement. Using determined camera movement, we classify clusters based on pixel intensities which pixels are matched with prior pixels following camera movement. Finally we eliminate clusters which have lower weight than threshold, and combine remained clusters for each pixel to generate multiple background clusters. Experimental results show that we can automatically detect background whether camera move or not.

• Transactions of Materials Processing
• /
• v.11 no.5
• /
• pp.405-413
• /
• 2002

A process planning system for cold forging of non-axisymmetric parts of comparatively simple shape was developed in this study. Programs for the system have been written with Visual LISP in AutoCAD. Shape of the product must be drawn with the solid line and the hidden line, and with the plane and front view, as well. At the plane, the system recognizes the external shape of non-axisymmetric portions - the number of the sides of the regular polygons and the radii of circles inscribing and circumscribing the polygon. At the front view, the system cognizes the diameter of axisymmetric portions and the height of the primitive geometries such as polygon, cylinder, cone, concave, convex, etc. The system perceives that the list developed from the solid line must be formed by the operation of forward extrusion or upsetting, and that the list developed from the hidden line must be formed by the operation of backward extrusion. The system designs the intermediate geometries again by considering clearance between workpiece and die, and then finally the billet diameter, in reverse order from the finished product, on the basis of volume constancy and using the operations, the forming sequence, the number of operations and the intermediate geometries which were already designed. The design rules and knowledges for the system were extracted from the plasticity theories, handbook, relevant reference and empirical knowledge of field experts. Suitability of the process planning was analyzed using SuperForge of FVM simulation package. The results of analysis showed good formability.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.6 no.4
• /
• pp.1128-1139
• /
• 2012

With the development of three-dimensional display and related technologies, depth video coding becomes a new topic and attracts great attention from industries and research institutes. Because (1) the depth video is not a sequence of images for final viewing by end users but an aid for rendering, and (2) depth video is simpler than the corresponding color video, fast algorithm for depth video is necessary and possible to reduce the computational burden of the encoder. This paper proposes a fast mode decision algorithm for depth video coding based on depth segmentation. Firstly, based on depth perception, the depth video is segmented into three regions: edge, foreground and background. Then, different mode candidates are searched to decide the encoding macroblock mode. Finally, encoding time, bit rate and video quality of virtual view of the proposed algorithm are tested. Experimental results show that the proposed algorithm save encoding time ranging from 82.49% to 93.21% with negligible quality degradation of rendered virtual view image and bit rate increment.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 1998.06b
• /
• pp.147-153
• /
• 1998

This paper provides a method for video augmentation using image interpolation. In computer graphics or augmented reality, 3D information of a model object is necessary to generate 2D views of the model, which are then inserted into or overlayed on environmental views or real video frames. However, we do not require any three dimensional model but images of the model object at some locations to render views according to the motion of video camera which is calculated by an SFM algorithm using point matches under weak-perspective (scaled-orthographic) projection model. Thus, a linear view interpolation algorithm is applied rather than a 3D ray-tracing method to get a view of the model at different viewpoints from model views. In order to get novel views in a way that agrees with the camera motion the camera coordinate system is embedded into model coordinate system at initialization time on the basis of 3D information recovered from video images and model views, respectively. During the sequence, motion parameters from video frames are used to compute interpolation parameters, and rendered model views are overlayed on corresponding video frames. Experimental results for real video frames and model views are given. Finally, discussion on the limitations of the method and subjects for future research are provided.

• International Journal of Contents
• /
• v.15 no.4
• /
• pp.8-15
• /
• 2019

This paper presents a solution of the 'Quick, Draw! Doodle Recognition Challenge' hosted by Google. Doodles are drawings comprised of concrete representational meaning or abstract lines creatively expressed by individuals. In this challenge, a doodle is presented as a sequence of sketches. From the view of at the sketch level, to learn the pattern of strokes representing a doodle, we propose a sequential model stacked with multiple convolution layers and Long Short-Term Memory (LSTM) cells following the attention mechanism [15]. From the view at the image level, we use multiple models pre-trained on ImageNet to recognize the doodle. Finally, an ensemble and a post-processing method using the minimum cost flow algorithm are introduced to combine multiple models in achieving better results. In this challenge, our solutions garnered 11th place among 1,316 teams. Our performance was 0.95037 MAP@3, only 0.4% lower than the winner. It demonstrates that our method is very competitive. The source code for this competition is published at: https://github.com/ngxbac/Kaggle-QuickDraw.

• Molecules and Cells
• /
• v.37 no.5
• /
• pp.372-382
• /
• 2014

In this study, the chloroplast (cp) genome sequences from three early diverged leptosporangiate ferns were completed and analyzed in order to understand the evolution of the genome of the fern lineages. The complete cp genome sequence of Osmunda cinnamomea (Osmundales) was 142,812 base pairs (bp). The cp genome structure was similar to that of eusporangiate ferns. The gene/intron losses that frequently occurred in the cp genome of leptosporangiate ferns were not found in the cp genome of O. cinnamomea. In addition, putative RNA editing sites in the cp genome were rare in O. cinnamomea, even though the sites were frequently predicted to be present in leptosporangiate ferns. The complete cp genome sequence of Diplopterygium glaucum (Gleicheniales) was 151,007 bp and has a 9.7 kb inversion between the trnL-CAA and trnV-GCA genes when compared to O. cinnamomea. Several repeated sequences were detected around the inversion break points. The complete cp genome sequence of Lygodium japonicum (Schizaeales) was 157,142 bp and a deletion of the rpoC1 intron was detected. This intron loss was shared by all of the studied species of the genus Lygodium. The GC contents and the effective numbers of codons (ENCs) in ferns varied significantly when compared to seed plants. The ENC values of the early diverged leptosporangiate ferns showed intermediate levels between eusporangiate and core leptosporangiate ferns. However, our phylogenetic tree based on all of the cp gene sequences clearly indicated that the cp genome similarity between O. cinnamomea (Osmundales) and eusporangiate ferns are symplesiomorphies, rather than synapomorphies. Therefore, our data is in agreement with the view that Osmundales is a distinct early diverged lineage in the leptosporangiate ferns.