• 한국정밀공학회지
• /
• 제15권11호
• /
• pp.189-198
• /
• 1998

Recently, monitoring of tool life is a matter of common interesting because tool life affects precision, productivity and cost in machining process. Especially flank wear has a direct effect on cutting mechanism, so the various pattern of cutting force is obtained experimentally according to variation of wear condition. By investigating cutting force signal, AR(Autoregressive) modeling and correlation dimension analysis is conducted in turning operation. In this modeling and analysis, we extract features through 6th AR model, correlation integral and normalized correlation integral. After the back-propagation model of the neural network is utilized to monitor tool life according to flank wear. As a result. a very reliable classification of tool life was obtained.

• 대한전자공학회논문지SD
• /
• 제48권4호
• /
• pp.6-13
• /
• 2011

정규상호상관 기반의 이미지 유사도 비교방법은 조명차 등에 강인한 특성이 있어 널리 사용되어 왔으나, 비효율적인 연산구조로 인해 실시간 연산을 요구하는 임베디드 시스템과 같은 응용분야에서는 적용하는 데 한계가 있었다. 본 논문에서는 효율적 연산방법을 통해 실시간 이미지 유사도 비교가 가능한 정규상호상관 기반의 하드웨어 연산구조를 제안한다. 제안된 구조는 적분이미지 기반의 윈도우 연산 방법을 사용하여 정규상호상관 함수의 윈도우 영역의 합 연산과정을 효율적으로 처리한다. 이를 위해 화소 입력과 동시에 적분이미지 생성이 가능한 구조와 메모리 효율적인 부분화 적분이미지 방법을 적용하여 적분이미지 생성과정에서의 부담을 최소화 한다.

• Journal of the Optical Society of Korea
• /
• 제14권4호
• /
• pp.388-394
• /
• 2010

In this paper the object recognition performance of a photon counting integral imaging system is quantitatively compared with that of a conventional gray scale imaging system. For 3D imaging of objects with a small number of photons, the elemental image set of a 3D scene is obtained using the integral imaging set up. We assume that the elemental image detection follows a Poisson distribution. Computational geometrical ray back propagation algorithm and parametric maximum likelihood estimator are applied to the photon counting elemental image set in order to reconstruct the original 3D scene. To evaluate the photon counting object recognition performance, the normalized correlation peaks between the reconstructed 3D scenes are calculated for the varied and fixed total number of photons in the reconstructed sectional image changing the total number of image channels in the integral imaging system. It is quantitatively illustrated that the recognition performance of the photon counting integral imaging system can be similar to that of a conventional gray scale imaging system as the number of image viewing channels in the photon counting integral imaging (PCII) system is increased up to the threshold point. Also, we present experiments to find the threshold point on the total number of image channels in the PCII system which can guarantee a comparable recognition performance with a gray scale imaging system. To the best of our knowledge, this is the first report on comparisons of object recognition performance with 3D photon counting & gray scale images.

• 한국측량학회지
• /
• 제38권2호
• /
• pp.165-172
• /
• 2020

There is growing interest in Vision-based video image matching owing to the constantly developing technology of unmanned-based systems. The purpose of this paper is the development of a fast and effective matching technique for the UAV oblique video image. We first extracted initial matching points using NCC (Normalized Cross-Correlation) algorithm and improved the computational efficiency of NCC algorithm using integral image. Furthermore, we developed a triangulation-based outlier removal algorithm to extract more robust matching points among the initial matching points. In order to evaluate the performance of the propose method, our method was quantitatively compared with existing image matching approaches. Experimental results demonstrated that the proposed method can process 2.57 frames per second for video image matching and is up to 4 times faster than existing methods. The proposed method therefore has a good potential for the various video-based applications that requires image matching as a pre-processing.

• 한국통신학회논문지
• /
• 제37권2A호
• /
• pp.128-134
• /
• 2012

본 논문에서는 커브형 집적영상 시스템에서 부분적으로 가려진 먼 거리 3차원 물체의 인식 향상을 위한 새로운 direct pixel-mapping (DPM)방법을 제안한다. 제안 방법은 커브형 집적영상 시스템에서 DPM 방법에 의해 먼 거리에 위치한 3차원 물체로부터 픽업된 요소영상배열 (elemental image array, EIA)은 가시적으로 가까운 거리에서 픽업한 것과 같은 새로운 요소영상배열을 생성한다. 이러한 특성은 재생한 3차원 물체 영상의 해상도를 향상 시킬 수 있고, 이로 인하여 먼 거리에 위치한 3차원 물체에 대한 인식 성능을 향상 시킬 수 있다. 컴퓨터적 실험결과와 기존 방법과의 비교를 통하여 제안방법으로 재생한 물체의 PSNR과 NCC의 값이 평균 1.75dB와 4.56% 향상됨을 확인할 수 있었다.