• ETRI Journal
• /
• v.33 no.4
• /
• pp.569-579
• /
• 2011

This paper presents a novel approach for human activity recognition (HAR) using the joint angles from a 3D model of a human body. Unlike conventional approaches in which the joint angles are computed from inverse kinematic analysis of the optical marker positions captured with multiple cameras, our approach utilizes the body joint angles estimated directly from time-series activity images acquired with a single stereo camera by co-registering a 3D body model to the stereo information. The estimated joint-angle features are then mapped into codewords to generate discrete symbols for a hidden Markov model (HMM) of each activity. With these symbols, each activity is trained through the HMM, and later, all the trained HMMs are used for activity recognition. The performance of our joint-angle-based HAR has been compared to that of a conventional binary and depth silhouette-based HAR, producing significantly better results in the recognition rate, especially for the activities that are not discernible with the conventional approaches.

• Computers and Concrete
• /
• v.13 no.6
• /
• pp.781-798
• /
• 2014

Estimating the workability of self-compacting concrete (SCC) is very important both in laboratories and on construction site. A method using visual information during the mixing process was proposed in this paper to estimate the workability of SCC. First, fourteen specimens of concrete were produced by a single-shaft mixer. A digital camera was used to record all the mixing processes. Second, employing the digital image processing, the visual information from mixing process images was extracted. The concrete pushed by the rotating blades forms two boundaries in the images. The shape of the upper boundary and the vertical distance between the upper and lower boundaries were used as two visual features. Thirdly, slump flow test and V-funnel test were carried out to estimate the workability of each SCC. Finally, the vertical distance between the upper and lower boundaries andthe shape of the upper boundary were used as indicators to estimate the workability of SCC. The vertical distance between the upper and lower boundaries was related to the slump flow, the shape of the upper boundary was related to the V-funnel flow time. Based on these relationships, the workability of SCC could be estimated using the mixing process images. This estimating method was verified by three more experiments. The experimental results indicate that the proposed method could be used to automatically estimate SCC workability.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.31 no.4
• /
• pp.517-524
• /
• 2007

This paper presents a global localization method using circular correlation of an omni-directional image. The localization of a mobile robot, especially in indoor conditions, is a key component in the development of useful service robots. Though stereo vision is widely used for localization, its performance is limited due to computational complexity and its narrow view angle. To compensate for these shortcomings, we utilize a single omni-directional camera which can capture instantaneous $360^{\circ}$ panoramic images around a robot. Nodes around a robot are extracted by the correlation coefficients of CHL (Circular Horizontal Line) between the landmark and the current captured image. After finding possible near nodes, the robot moves to the nearest node based on the correlation values and the positions of these nodes. To accelerate computation, correlation values are calculated based on Fast Fourier Transforms. Experimental results and performance in a real home environment have shown the feasibility of the method.

• Proceedings of the KSME Conference
• /
• 2008.11b
• /
• pp.3019-3025
• /
• 2008

An experimental study was performed to assess the effect of diesel and JP-8 aviation fuel on the spray characteristics, performance and emissions in a single cylinder optical diesel engine. Both fuels were injected via an 8-hole solenoid-driven injector in a common-rail injection system. For better understanding of spray development, the macroscopic images were captured with high speed camera, offered evidences for the results of performance and emissions. From macroscopic spray images, the spray tip penetration of JP-8 shorter than that of diesel while spray angle of JP-8 was wider than that of diesel. It indicates that the vaporization of JP-8 is superior to that of diesel. The lower cetane number of JP-8 resulted in increased portion of premixed combustion. The IMEP with JP-8 is lower than that of diesel-fueled engine. Especially, using JP-8 has a potential for reducing soot.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2014.07a
• /
• pp.51-52
• /
• 2014

본 논문에서는 경량화 설계가 반영된 차량의 내구성 및 안전성을 증가시키기 위해 사용되는 구조용 접착제의 비균일적, 미도포 된 부분을 검사하기 위한 방법에 대해 제안한다. 이 방법은 차량이 조립되기 전 구조용 접착체가 균일하게 도포되지 않은 부분을 사전에 알려줌으로써 차량의 전체적인 강성을 높일 수 있어, 차량의 조립에 있어 의무화되어 가는 추세이다. 이 방법은 머신전용 카메라와 보드 기반으로 간단하게 구성이 가능하다.

• ETRI Journal
• /
• v.37 no.4
• /
• pp.752-765
• /
• 2015

We propose a novel post-processing algorithm and its very-large-scale integration architecture that simultaneously uses the passive and active stereo vision information to improve the reliability of the three-dimensional disparity in a hybrid stereo vision system. The proposed architecture consists of four steps - left-right consistency checking, semi-2D hole filling, a tiny adaptive variance checking, and a 2D weighted median filter. The experimental results show that the error rate of the proposed algorithm (5.77%) is less than that of a raw disparity (10.12%) for a real-world camera image having a $1,280{\times}720$ resolution and maximum disparity of 256. Moreover, for the famous Middlebury stereo image sets, the proposed algorithm's error rate (8.30%) is also less than that of the raw disparity (13.7%). The proposed architecture is implemented on a single commercial field-programmable gate array using only 13.01% of slice resources, which achieves a rate of 60 fps for $1,280{\times}720$ stereo images with a disparity range of 256.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.6 no.3
• /
• pp.457-463
• /
• 2011

As computer related technologies are developed, interests in augmented reality technologies are greatly increasing. Augmented reality is a technology that composes digital contents from the real input images through camera and it enables interaction with users. This study designed a directional marker using LED light that emits infrared ray, then, provided a detection algorithm and a marker information extraction method that can realize various virtual objects as augmented reality from one marker. The newly designed method provides a solution to settle the problems in existing marker technologies such as decrease of immersiveness and read rate and single information expression, and at the same time it can minimize the cost or time consumption in marker information storage.

• Journal of Biosystems Engineering
• /
• v.25 no.5
• /
• pp.409-414
• /
• 2000

A machine vision system was built to obtain single stationary image from an egg. This system includes a CCD camera, an image processing board and a lighting system. A computer program was written to acquire, enhance and get histogram from an image. To minimize the evaluation time, the artificial neural network with the histogram of the image was used for eggshell evaluation. Various artificial neural networks with different parameters were trained and tested. The best network(64-50-1 and 128-10-1) showed an accuracy of 87.5% in evaluating eggshell. The comparison test for the elapsed processing time per an egg spent by this method(image processing and artificial neural network) and by the processing time per an egg spent by this method(image processing and artificial neural network) and by the previous method(image processing only) revealed that it was reduced to about a half(5.5s from 10.6s) in case of cracked eggs and was reduced to about one-fifth(5.5s from 21.1s) in case of normal eggs. This indicates that a fast eggshell evaluation system can be developed by using machine vision and artificial neural network.

• Transactions of the Korean Society of Automotive Engineers
• /
• v.22 no.7
• /
• pp.107-116
• /
• 2014

This paper presents camera-based road surface marking detection methods suited to sensor fusion-based positioning system that consists of low-cost GPS (Global Positioning System), INS (Inertial Navigation System), EDM (Extended Digital Map), and vision system. The proposed vision system consists of two parts: lane marking detection and RSM (Road Surface Marking) detection. The lane marking detection provides ROIs (Region of Interest) that are highly likely to contain RSM. The RSM detection generates candidates in the regions and classifies their types. The proposed system focuses on detecting RSM without false detections and performing real time operation. In order to ensure real time operation, the gating varies for lane marking detection and changes detection methods according to the FSM (Finite State Machine) about the driving situation. Also, a single template matching is used to extract features for both lane marking detection and RSM detection, and it is efficiently implemented by horizontal integral image. Further, multiple step verification is performed to minimize false detections.

• International Journal of Automotive Technology
• /
• v.6 no.2
• /
• pp.125-131
• /
• 2005

This article reports the experimental and numerical results for free sprays under ultra-high injection pressure conditions to give us better understandings of spray characteristics and also to make clear a limit pressure condition in diesel sprays. The high pressure injection system developed in this work is devised to reach ultra-high pressure conditions in the range from 150 MPa to 355 MPa. The free spray injected from a single nozzle injector is visualized by the Schlieren technique and the high speed camera. In particular, it is found that the shock waves are present and propagated along the edge of spray in the downstream direction. The measured spray penetration length increases gradually with the injection pressure, but its increasing rate is decreased as the injection pressure increases. The Sauter mean diameter is also no longer augmented for the injection pressures higher than 300 MPa. In addition, the three­dimensional numerical simulations are conducted for comparing the measurements with the predictions based on two different breakup models. The TAB model results show better agreements with experimental data than the WAVE model under ultra-high injection pressure conductions. Moreover, the simulation results show that the gas-phase pressure increases substantially in the vicinity of the spray tip region. It supports the experimental observation that the shock waves are formed at the front of spray tip and are propagated downstream.