• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.11
• /
• pp.3493-3506
• /
• 2022

In the field of scene segmentation, the precise segmentation of object boundaries in sports movement scene images is a great challenge. The geometric information and spatial information of the image are very important, but in many models, they are usually easy to be lost, which has a big influence on the performance of the model. To alleviate this problem, a parallel dense dilated convolution merging Network (termed PDDCM-Net) was proposed. The proposed PDDCMNet consists of a feature extractor, parallel dilated convolutions, and dense dilated convolutions merged with different dilation rates. We utilize different combinations of dilated convolutions that expand the receptive field of the model with fewer parameters than other advanced methods. Importantly, PDDCM-Net fuses both low-level and high-level information, in effect alleviating the problem of accurately segmenting the edge of the object and positioning the object position accurately. Experimental results validate that the proposed PDDCM-Net achieves a great improvement compared to several representative models on the COCO-Stuff data set.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.45 no.1
• /
• pp.75-83
• /
• 2008

We propose a welfare interface using multiple fecial features tracking, which can efficiently implement various mouse operations. The proposed system consist of five modules: face detection, eye detection, mouth detection, facial feature tracking, and mouse control. The facial region is first obtained using skin-color model and connected-component analysis(CCs). Thereafter the eye regions are localized using neutral network(NN)-based texture classifier that discriminates the facial region into eye class and non-eye class, and then mouth region is localized using edge detector. Once eye and mouth regions are localized they are continuously and correctly tracking by mean-shift algorithm and template matching, respectively. Based on the tracking results, mouse operations such as movement or click are implemented. To assess the validity of the proposed system, it was applied to the interface system for web browser and was tested on a group of 25 users. The results show that our system have the accuracy of 99% and process more than 21 frame/sec on PC for the $320{\times}240$ size input image, as such it can supply a user-friendly and convenient access to a computer in real-time operation.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2001.10a
• /
• pp.587-591
• /
• 2001

This paper deals with inspect algorithm using visual system. One of the major problems that arise during polymer production is the estimation of the noise of the color product.(bad pallets) An erroneous output can cause a lot of losses (production and financial losses). Therefore new methods for real-time inspection of the noise are demanded. For this reason, we have presented a development of vision system algorithm for the defect inspection of PE color pallets. First of all, in order to detect the edge of object, the differential filter is used. And we apply to the labelling algorithm for feature extraction. This algorithm is designed for the defect inspection of pallets. The labelling algorithm permits to separate all of the connected components appearing on the pallets. Labelling the connected regions of a image is a fundamental computation in image analysis and machine vision, with a large number of application. Also, we suggested vision processing program in window environment. Simulations and experimental results demonstrate the performance of the proposal algorithm.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2002.11a
• /
• pp.755-758
• /
• 2002

스테레오스코픽 영상은 스테레오스코픽 카메라를 이용하여 좌 영상(left image)과 우 영상(right image)을 동시에 획득하는 것으로 사람의 눈으로 보는 것과 같은 입체감을 얻을 수 있는 것을 특징으로 한다. 스테레오스코픽 영상에서 객체의 깊이값을 구하기 위해서는 영상의 정합점을 찾는 것이 중요한데, 본 논문에서는 일반화 대칭변환(generalized symmetry transform) 알고리즘을 적용하여 스테레오스코픽(stereoscopic) 영상의 정합점(correspond points)을 찾는 방법을 제안한다. 본 논문에서 제안하는 방법은 먼저 좌 영상과 우 영상에 대해 에지(edge), 코너 검출 방법을 통해 특징점(feature point)을 검출하고 각 특징점들을 중심으로 사각 영역을 설정하고 이 범위내의 에지들이 갖는 대칭도(symmetry magnitude)를 특징점의 위치에 누적 시킨다. 좌영상의 대칭도를 구한 결과를 우 영상의 에지들의 대칭도와 비교를 수행해 임계치(threshold) 이하의 값을 가진 점들을 정합 후보로 선택한다. 이 정합 후보들을 영역내의 반지름 단위의 대칭도 비교를 통해 더욱 세분화된 비교를 수행하고 만약 이와 같은 과정을 통해서도 정합점을 찾지 못한다면 정합 후보들에 대해 칼라 정합도를 측정하여 최종적으로 정합점을 검출한다. 제안한 알고리즘을 이용한다면 특징점만을 이용하여 검색을 수행했을 때보다 더욱 정확한 정합점을 구할 수 있다.

• Journal of Korea Multimedia Society
• /
• v.16 no.6
• /
• pp.756-763
• /
• 2013

Bilateral filter (BF), functioning by two Gaussian filters, domain and range filter is a nonlinear filter for sharpness enhancement and noise removal. In infrared (IR) small target detection field, the BF is designed by background predictor for predicting background not including small target. For this, the standard deviations of the two Gaussian filters need to be changed adaptively in background and target region of an infrared image. In this paper, the proposed bilateral filter make the standard deviations changed adaptively, using variance feature of mean values of surrounding block neighboring local filter window. And, in case the variance of mean values for surrounding blocks is low for any processed pixel, the pixel is classified to flat background and target region for enhancing background prediction. On the other hand, any pixel with high variance for surrounding blocks is classified to edge region. Small target can be detected by subtracting predicted background from original image. In experimental results, we confirmed that the proposed bilateral filter has superior target detection rate, compared with existing methods.

• Journal of the Korean Institute of Telematics and Electronics S
• /
• v.35S no.12
• /
• pp.55-62
• /
• 1998

Matching two images is an essential step for many computer vision applications. A new approach to the scale and rotation invariant scene matching, using linear features, is presented. Scene or model images are described by a set of linear features approximating edge information, which can be obtained by the conventional edge detection, thinning, and piecewise linear approximation. A set of candidate parameters are hypothesized by mapping the angular difference and a new distance measure to the Hough space and by detecting maximally consistent points. These hypotheses are verified by a fast linear feature matching algorithm composed of a single-step relaxation and a Hough technique. The proposed method is shown to be much faster than the conventional one where the relaxation process is repeated until convergence, while providing matching performance robust to the random alteration of the linear features, without a priori information on the geometrical transformation parameters.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.47 no.3
• /
• pp.11-22
• /
• 2010

This paper is a study on implementation of intelligent image surveillance system using context information and supplements temporal-spatial constraint, the weak point in which it is hard to process it in real time. In this paper, we propose scene analysis algorithm which can be processed in real time in various environments at low resolution video(320*240) comprised of 30 frames per second. The proposed algorithm gets rid of background and meaningless frame among continuous frames. And, this paper uses wavelet transform and edge histogram to detect shot boundary. Next, representative key-frame in shot boundary is selected by key-frame selection parameter and edge histogram, mathematical morphology are used to detect only motion region. We define each four basic contexts in accordance with angles of feature points by applying vertical and horizontal ratio for the motion region of detected object. These are standing, laying, seating and walking. Finally, we carry out scene analysis by defining simple context model composed with general context and emergency context through estimating each context's connection status and configure a system in order to check real time processing possibility. The proposed system shows the performance of 92.5% in terms of recognition rate for a video of low resolution and processing speed is 0.74 second in average per frame, so that we can check real time processing is possible.

• Journal of KIISE:Databases
• /
• v.36 no.4
• /
• pp.263-279
• /
• 2009

Shape features in a content-based image retrieval (CBIR) system are divided into two classes: contour-based and region-based. Contour-based shape features are simple but they are not as efficient as region-based shape features. Most systems using the region-based shape feature have to extract the region firs t. The prior works on region-based systems still have shortcomings. They are complex to implement, particularly with respect to region extraction, and do not sufficiently use the spatial relationship between regions in the distance model In this paper, a region extraction method that is the combination of an edge-based method and a region growing method is proposed to accurately extract regions inside an object. Edges inside an object are accurately detected based on the Canny edge detector and the Hough transform. And the modified Integrated Region Matching (IRM) scheme which includes the adjacency relationship of regions is also proposed. It is used to compute the distance between images for the similarity search using shape features. The experimental results show the effectiveness of our region extraction method as well as the modified IRM. In comparison with other works, it is shown that the new region extraction method outperforms others.

• Journal of the Korea Society of Computer and Information
• /
• v.17 no.1
• /
• pp.71-80
• /
• 2012

This paper proposes vehicle detection and tracking algorithm using a CCD camera. The proposed algorithm uses Haar-like wavelet edge detector to detect features of vehicle and estimates vehicle's location using calibration information of an image. After that, extract accumulated vehicle information in continuous k images to improve reliability. Finally, obtained vehicle region becomes a template image to find same object in the next continuous image using SURF(Speeded Up Robust Features). The template image is updated in the every frame. In order to reduce SURF processing time, ROI(Region of Interesting) region is limited on expended area of detected vehicle location in the previous frame image. This algorithm repeats detection and tracking progress until no corresponding points are found. The experimental result shows efficiency of proposed algorithm using images obtained on the road.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2013.10a
• /
• pp.83-86
• /
• 2013

In this paper, by using the Morphing, if the size of the eyes of both sides are not the same, we propose a method to correct the size of eyes area. First, by using the Haar-like feature from a input image that is input, to detect the shape of the eyes and face. After inverting the left and right eye region of one of the shape of the eyes detected sets the correspondence between the second with a line to control the shape of the eyes detected using eyes that is detected with canny edge, in the previous step. To the Warping to match the correspondence was then set in the previous step, an area of each eye. Then, I merge the image which merged in the eye area is detected from the original image. As a result, a system result of the experiment in the test image and face image seen from the front, the proposed, prove to be more efficient than a method of keying the size of the eye only.