• 제어로봇시스템학회:학술대회논문집
• /
• 2002.10a
• /
• pp.100.3-100
• /
• 2002

This paper presents the method for detection and tracking of multiple humans robustly in mobile platform. The perception of human is performed in real time through the processing of images acquired from a moving stereo vision system. We performed multi-cue integration such as human shape, skin color and depth information to detect and track each human in moving background scene. Human shape is measured by edge-based template matching on distance transformed image. Improving robustness for human detection, we apply the human face skin color in HSV color space. And we could increase the accuracy and the robustness in both detection and tracking by applying random sampling stochastic estimati...

• 제어로봇시스템학회:학술대회논문집
• /
• 2002.10a
• /
• pp.98.3-98
• /
• 2002

Vision-based systems for finding road lanes have to operate robustly under a wide variety of environ-mental conditions including large amount of scene clutters. This paper presents a method for finding the lane boundaries by combining a local line extraction method and dynamic programming as a search tool. The line extractor obtains an initial position estimation of road lane boundaries from the noisy edge fragments. Dynamic programming then improves the initial approximation to an accurate configuration of lane boundaries. Input image frame is divided into a few sub-regions along the vertical direction. The local line extractor then performs to extract candidate lines of road lanes in the...

• Transactions of the Korean Society of Mechanical Engineers
• /
• v.8 no.6
• /
• pp.576-583
• /
• 1984

This paper presents an algorithm for recognition of simple curved two dimensional objects. The algorithm is divided into four steps, determining threshold, edge finding, feature extracting and model matching. To evaluate the performance of this algorithm some experiments were conducted for various objects and illuminations. The results shows that the proposed algorithm can be effectively used for part recognition and quality inspection.

• Journal of IKEEE
• /
• v.15 no.3
• /
• pp.255-260
• /
• 2011

In this paper, we propose a parallelization technique in lane detection by using Hough transform. Hough transform has a weakness that it has a lot computation quantity, because it has to compute ${\rho}$ value in all candidate ${\Theta}$ to be detected in an image. We propose an architecture of parallel processing for this transform in a multi-core environment. The parallel processing has application to Hough transform as well as noise reduction and edge detection. This proposed architecture has 5.17 times improvement in performance compare to the existing algorithm.

• Journal of Institute of Control, Robotics and Systems
• /
• v.8 no.6
• /
• pp.462-467
• /
• 2002

A new approach for reducing the blocking artifact is proposed in this paper. This method can be applied to conventional transform coding, without introducing additional information or significant blurring. Main drawbacks of the Discrete Cosine Transform(DCT) are visible block boundaries due to coarse quantization of the coefficients. Therefore, restoration techniques result in unnecessary blurring of the image. The proposed deblocking algorithm is based on the heuristic approach for edge detection. All edges of the standard still images are categorized, and the best edges are selected. Several images are used fer experiments, and several other previous algorithms are compared with the proposed approach. The results show that the proposed algorithm works better than those of other previous researches. This algorithm can be used for JPEG, MPEG, and H.261 standard images.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.32B no.3
• /
• pp.66-76
• /
• 1995

In this research, a mesh connected VLSI structure is proposed for the real time computation of the generalized Hough transform(GHT). The purpose of the research is to design a generalized Hough transformer that can be realized as a single chip processor. The GHT has been modified to yield a highly parallel structure consisting of simple processing elements(PEs) and communication networks. In the proposed structure, the GHT can be computed by first assigning an image pixel to a PE and performing shift and add operations. The result of the CAD circuit simulation shows that it can be computed in the time proportional to the number of pixels in the pattern. In addition to the Hough transformer, the peak detector has been designed to reduce 1)the number of the I/O operations between the transformer and the host computer and 2) the host computer's burden for peak detection by transmitting only the local peaks detected from the transformed accumulator. It is expected that the proposed single chip Hough transformer with peak detector makes a fast and inexpensive edge based object recognition systems possible for many industrial and military applications.

• Journal of the Korean Institute of Telematics and Electronics A
• /
• v.31A no.7
• /
• pp.69-75
• /
• 1994

A very fine pattern formation process using double exposure is investigated, which can overcome the resolution limit of optical wafer stepper. The very fine pattern can be obtained by moving the edge profile of large pattern by means of moving the stepper stage. The simulation results show that the light transmittance decrease bellow 9%, and the contrast increase to 16.6% for the 0.3$\mu$m photoresist pattern exposeed by the double exposure using i-line wafer stepper. And the experimental results show that fine photoresist pattern as short as 0.2$\mu$m can be obtained without a loss of photoresist thickness. Also, it proves that the depth of focus for 0.3$\mu$m pattern is longer than $1.5\mu$m. And, the very fine negative photoresist pattern was formmed by using the double exposure technique and the image reversal process.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2011.01a
• /
• pp.51-53
• /
• 2011

최근에는 텍스트정보 보다 동영상정보를 다루는 일이 많아졌고 그에 따라 동영상 데이터의 분할, 색인, 검색 등을 위해 장면 전환 검출이 필요하게 되었다. 장면 전환 검출 기술은 비디오 데이터의 장면 변화가 발생하는 경계를 검출하는 기술이다. 본 논문에서는 에지 이미지를 이용한 장면전환 검출과 이를 위한 임계값 설정, 그리고 결과에서 중복된 이미지와 오 검출 된 이미지를 줄여줄 수 있는 구현에 대하여 실험결과를 바탕으로 설명한다.

• Journal of Institute of Control, Robotics and Systems
• /
• v.4 no.6
• /
• pp.795-801
• /
• 1998

In this paper, we propose a machine vision algorithm for inspecting inserts which are used for milling and turning operations. Major defects of the inserts are breakage and crack on insert surfaces. Among the defects, breakages on the face of the inserts can be detected through three stages of the algorithm developed in this paper. In the first stage, a multi-layer perceptron is used to recognize the inserts being inspected. Edge detection of the insert image is performed in the second stage. Finally, in the third stage breakages on the insert face are identified using Hough transform. The overall algorithm is tested on real specimens and the results show that the algorithm works fairly well.

• Journal of Institute of Control, Robotics and Systems
• /
• v.21 no.1
• /
• pp.52-58
• /
• 2015

In this paper, The ET-MBEF algorithm is presented for CCD imaging seeker. At the imaging seeker, target size information is important factor for accurate tracking. The MBEF algorithm was proposed to estimate target size at IIR seeker. However, the MBEF algorithm can't be applied at CCD imaginary target size estimation. In order to overcome the problem, we propose ET-MBEF algorithm which based on ET (Edge Template) and MBEF algorithm. The performance of proposed method is tested at target intercept scenario. The experiment results show that the proposed algorithm has the accurate target intercept performance.