• Proceedings of the Korea Institute of Convergence Signal Processing
• /
• 2000.12a
• /
• pp.101-104
• /
• 2000

본 논문에서는 곡률 근사화를 이용한 3차원 영상의 표면 분할 알고리즘을 제안한다. 제안한 알고리즘은 기하학적인 접근방법으로 곡률 근사화 이용한 간략화 된 처리 과정의 적용과 곡률의 불연속 정도를 결정하는데 보다 용이한 방법을 제시한다. 이러한 효율적인 에지 검출을 기반으로 여러 가지 3차원 영상의 표면 분할 실험을 통하여 제안한 방법의 성능이 기존의 방법보다 우수함을 확인하였다.

• Proceedings of the Korea Institute of Convergence Signal Processing
• /
• 2000.08a
• /
• pp.317-320
• /
• 2000

동영상 분할은 컴퓨터 비전 분야에서 중요한 단계로 많이 연구되고 있다 그러나 동영상 분할은 계산 복잡도에 의해 제약을 받는다. 이를 해결하기 위해, 본 논문은 분산 유전자 알고리즘에 기반한 계산 효율을 높일 수 있는 새로운 동영상 분할 방법을 제안한다. 일반적으로 동영상에서 연속한 두 프레임은 높은 상관관계를 가진다. 따라서, 한 프레임의 분할 결과는 이전 프레임의 분할 결과를 사용해서 연속적으로 얻어진다. 그리고 중복된 계산을 제거하기 위해 움직이는 객체에 대응되는 염색체만을 진화시킨다. 실험 결과는 제안한 방법의 효율성을 보여준다.

• Proceedings of the Korea Institute of Convergence Signal Processing
• /
• 2000.08a
• /
• pp.193-196
• /
• 2000

최근 컴퓨터를 이용한 CAD 디자인 시스템이 날염디자인제도(textile printing design trace)에 널리 사용되고 있다 CAD를 이용한 날염디자인은 기존의 수작업에 비해 공정을 간편하게 하고, 상당히 많은 시간과 경비의 단축을 가능하게 하였다. 그러나 CAD를 이용한 날염디자인제도 역시 상당부분 숙련자들의 수작업을 요구하고 있다. 본 논문에서는 날염디자인제도에서의 컬러 분할 전처리 과정으로 원 이미지를 저주파 통과 필터링하고 컬러분할을 수행하였다. 이렇게 분할된 이미지의 윤곽선을 추출하고 스플라인(Spline)기법을 사용, 더 부드럽고 완만한 곡선을 생성하도록 하였다. 모든 과정은 Matlab을 사용하여 구현하였으며 분할된 이미지를 날염제도공정으로의 적용 가능성에 대해 검토하였다.

• Korean Journal of Radiology
• /
• v.20 no.8
• /
• pp.1275-1284
• /
• 2019

Objective: To develop algorithms using convolutional neural networks (CNNs) for automatic segmentation of acute ischemic lesions on diffusion-weighted imaging (DWI) and compare them with conventional algorithms, including a thresholding-based segmentation. Materials and Methods: Between September 2005 and August 2015, 429 patients presenting with acute cerebral ischemia (training:validation:test set = 246:89:94) were retrospectively enrolled in this study, which was performed under Institutional Review Board approval. Ground truth segmentations for acute ischemic lesions on DWI were manually drawn under the consensus of two expert radiologists. CNN algorithms were developed using two-dimensional U-Net with squeeze-and-excitation blocks (U-Net) and a DenseNet with squeeze-and-excitation blocks (DenseNet) with squeeze-and-excitation operations for automatic segmentation of acute ischemic lesions on DWI. The CNN algorithms were compared with conventional algorithms based on DWI and the apparent diffusion coefficient (ADC) signal intensity. The performances of the algorithms were assessed using the Dice index with 5-fold cross-validation. The Dice indices were analyzed according to infarct volumes (< 10 mL, ≥ 10 mL), number of infarcts (≤ 5, 6-10, ≥ 11), and b-value of 1000 (b1000) signal intensities (< 50, 50-100, > 100), time intervals to DWI, and DWI protocols. Results: The CNN algorithms were significantly superior to conventional algorithms (p < 0.001). Dice indices for the CNN algorithms were 0.85 for U-Net and DenseNet and 0.86 for an ensemble of U-Net and DenseNet, while the indices were 0.58 for ADC-b1000 and b1000-ADC and 0.52 for the commercial ADC algorithm. The Dice indices for small and large lesions, respectively, were 0.81 and 0.88 with U-Net, 0.80 and 0.88 with DenseNet, and 0.82 and 0.89 with the ensemble of U-Net and DenseNet. The CNN algorithms showed significant differences in Dice indices according to infarct volumes (p < 0.001). Conclusion: The CNN algorithm for automatic segmentation of acute ischemic lesions on DWI achieved Dice indices greater than or equal to 0.85 and showed superior performance to conventional algorithms.

• Journal of Institute of Control, Robotics and Systems
• /
• v.12 no.4
• /
• pp.353-357
• /
• 2006

The vehicle detection method using pulse radar has the advantage of maintenance in comparison with loop detection method. We propose the pulse radar signal processing algorithm in which we devide the trace. data from pulse radar into segments by using SSC concept, and then construct the sectors in accordance with period and amplitude of segments, and finally decide the vehicle detection probability by applying the SSC parameters of each sectors into the discriminant function. We also improve the signal processing time by reducing the quantities of processing data and processing routines.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.12 no.1
• /
• pp.22-28
• /
• 2019

This paper presents a method for detection of an emergency signal expressed by arm gestures based on motion segmentation and face area detection in the surveillance system. The important indicators of emergency can be arm gestures and voice. We define an emergency signal as the 'Help Me' arm gestures in a rectangle around the face. The 'Help Me' arm gestures are detected by tracking changes in the direction of the horizontal motion vectors of left and right arms. The experimental results show that the proposed method successfully detects 'Help Me' emergency signal for a single person and distinguishes it from other similar arm gestures such as hand waving for 'Bye' and stretching. The proposed method can be used effectively in situations where people can't speak, and there is a language or voice disability.

• Journal of Korea Multimedia Society
• /
• v.15 no.11
• /
• pp.1305-1318
• /
• 2012

Image segmentation is one of the difficult research problems in machine vision and pattern recognition field. A commonly used segmentation method is the Otsu method. It is simpler and easier to implement but it fails if the histogram is unimodal or similar to unimodal. And if some target area is smaller than background object, then its histogram has the distribution close to unimodal. In this paper, we proposed an improved image segmentation method based on 1D Otsu method for a small target detection. To overcome drawbacks by unimodal histogram effect, we depressed the background histogram using a logarithm function. And to improve a signal to noise ratio, we used a local average value by the neighbor window for thresholding using 1D Otsu method. The experimental results show that our proposed algorithm performs better segmentation result than a traditional 1D Otsu method, and needs much less computational time than that of the 2D Otsu method.

• Journal of the Semiconductor & Display Technology
• /
• v.21 no.4
• /
• pp.92-98
• /
• 2022

This paper proposes a new method of the traffic signal detection and the recognition in an HSI color model. The proposed method firstly converts a ROI image in the RGB model to in the HSI model to segment the color of a traffic signal. Secondly, the segmented colors are dilated by the morphological processing to connect the traffic signal light and the signal light case and finally, it extracts the traffic signal light and the case by the aspect ratio using the connected component analysis. The extracted components show the detection and the recognition of the traffic signal lights. The proposed method is implemented using C language in Raspberry Pi 4 system with a camera module for a real-time image processing. The system was fixedly installed in a moving vehicle, and it recorded a video like a vehicle black box. Each frame of the recorded video was extracted, and then the proposed method was tested. The results show that the proposed method is successful for the detection and the recognition of traffic signals.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2007.10a
• /
• pp.473-476
• /
• 2007

Location determination of mobile user via RSSI approach has received ample attention from researchers lately. However, it remains a challenging issue due to the complexities of RSSI signal propagation characteristics, which are easily exacerbated by the mobility of user. Hence, a segmentation-based linear spline interpolation method is proposed to cater for the dynamic fluctuation pattern of radio signal in complex environment. This optimization algorithm is proposed in addition to the current radiolocation's (CC2431, Chipcon, Norway) algorithm, which runs on IEEE802.15.4 standard. The enhancement algorithm involves four phases. First phase consists of calibration model in which RSSI values at different static locations are collected and processed to obtain the mean and standard deviation value for the predefined distance. RSSI smoothing algorithm is proposed to minimize the dynamic fluctuation of radio signal received from each reference node when the user is moving. Distances are computed using the segmentation formula obtain in the first phase. In situation where RSSI value falls in more than one segment, the ambiguity of distance is solved by probability approach. The distance probability distribution function(pdf) for each distances are computed and distance with the highest pdf at a particular RSSI is the estimated distance. Finally, with the distances obtained from each reference node, an iterative trilateration algorithm is used for position estimation. Experiment results obtained position the proposed algorithm as a viable alternative for location tracking.

• Proceedings of the Korea Institute of Convergence Signal Processing
• /
• 2000.12a
• /
• pp.93-96
• /
• 2000

In this paper, we suggest a feature points selection method using block-based watershed segmentation and polygon approximation for preprocessing of MPEG-4 mesh generation. 2D natural image is segmented by 8$\times$8 or 4$\times$4 block classification method and watershed algorithm. As this result, pixels on the watershed lines represent scene's interior feature and this lines are shapes of closed contour. Continuous pixels on the watershed lines are selected out feature points using Polygon approximation and post processing.