• 한국정보통신학회논문지
• /
• 제10권4호
• /
• pp.674-679
• /
• 2006

본 논문에서는 3차원 손 특징 데이터를 이용한 동작 인식 시스템을 제안하고자 한다. 제안된 시스템은 3차원 센서에 의해 조밀한 범위의 영상을 생성하여 손 동작에 대한 3차원 특징을 추출하여 손 동작을 분류한다. 또한 다양한 조명과 배경하에서의 손을 견실하게 분할하고 색상 정보와 상관이 없어 수화와 같은 복잡한 손 동작에 대해서도 견실한 인식능력을 나타낼 수가 있다. 제안된 방법의 전체적인 순서는 3차원 영상 획득, 팔 분할, 손과 팔목 분할, 손 자세 추정, 3차원 특징 추출, 그리고 동작 분류로 구성되어 있고, 수화 자세에 대한 인식 실험으로 제안된 시스템의 효율성을 입증하였다.

• 한국멀티미디어학회논문지
• /
• 제14권5호
• /
• pp.607-613
• /
• 2011

본 논문에서는 조명과 배경에 강인한 동적임계값을 이용한 손 영상 분할방법을 제안한다. 먼저 시간단위 입력 차영상을 구하여 움직이는 물체에 대한 손의 실루엣을 추출한다 그 후, 추출된 손 실루엣에 해당하는 영상의 R,G,B 히스토그램 분석을 통하여 R,G,B 각각에 대한 임계구간을 동적으로 구한다. 마지막으로 획득된 동적 임계값을 이용하여 영상에서 손영역을 분할한 다음 모폴로지, 연결요소 분석, 플러드필 연산을 이용한 잡음 제거를 수행한다. 실험 결과 본 논문에서 제시하는 기법은 기존의 비전 기술을 통한 손 인식 기법들과 비교하여 별도의 고정임계값을 두지 않고 실행시간에 정확한 임계값을 추출 할 수 있으며, 다양한 배경과 조명에 대해서도 정확하게 손을 분할할 수 있다. 본 연구에서 제안한 기법은 혼합 현실 응용을 위한 사용자 인터페이스로 사용될 수 있다.

• 한국콘텐츠학회논문지
• /
• 제18권4호
• /
• pp.398-405
• /
• 2018

HCI 분야에서 대표적인 손 제스처 인식은 IT기기의 개발과 더불어 사용자와 기기 간의 상호작용 및 정보교환을 위한 방법으로 주목받고 있다. 영상 처리를 통한 손 제스처 인식에서 손바닥 영역 검출은 처리속도 및 인식률 향상에 기여하는 핵심 처리 과정이다. 본 논문에서는 손바닥 영역 검출(palm area detection)을 위해 손과 손목을 영상 분할(image segmentation) 하는 새로운 방법을 제안한다. 손의 해부학적 특성으로 가장 넓은 폭이 발생하는 엄지와 소지의 장골 간격을 손 영상의 수평 투사 히스토그램으로 계산 후 이 간격을 지름으로 하는 원을 그려 손바닥 영역을 검출한다. 이 방법의 우수성을 검증하기 위하여 다단 형판정합(multiple stage template matching)을 사용해 10가지 손 제스처에 대해 기존 방법 4가지와 인식 성능을 비교 평가한다. 손 제스처 인식에 관련한 연구가 다양하나 손바닥 영역 검출에 특화된 성능 비교 문헌이 저조함을 강조한다.

• 한국멀티미디어학회논문지
• /
• 제17권5호
• /
• pp.547-555
• /
• 2014

This paper presents a method for hand segmentation using depth information, and adaptive threshold by means of histogram analysis and color clustering in HSV color model. We consider hand area as a nearer object to the camera than background on depth information. And the threshold of hand color is adaptively determined by clustering using the matching of color values on the input image with one of the regions of hue histogram. Experimental results demonstrate 95% accuracy rate. Thus, we confirmed that the proposed method is effective for hand segmentation in variations of hand color, scale, rotation, pose, different lightning conditions and any colored background.

• 한국멀티미디어학회논문지
• /
• 제22권9호
• /
• pp.1000-1010
• /
• 2019

Image semantic segmentation and dehazing are key tasks in the computer vision. In recent years, researches in both tasks have achieved substantial improvements in performance with the development of Convolutional Neural Network (CNN). However, most of the previous works for semantic segmentation assume the images are captured in clear weather and show degraded performance under hazy images with low contrast and faded color. Meanwhile, dehazing aims to recover clear image given observed hazy image, which is an ill-posed problem and can be alleviated with additional information about the image. In this work, we propose a deep multi-task network for simultaneous semantic segmentation and dehazing. The proposed network takes single haze image as input and predicts dense semantic segmentation map and clear image. The visual information getting refined during the dehazing process can help the recognition task of semantic segmentation. On the other hand, semantic features obtained during the semantic segmentation process can provide cues for color priors for objects, which can help dehazing process. Experimental results demonstrate the effectiveness of the proposed multi-task approach, showing improved performance compared to the separate networks.

• JSTS:Journal of Semiconductor Technology and Science
• /
• 제17권3호
• /
• pp.473-482
• /
• 2017

Hand gesture recognition is regarded as new Human Computer Interaction (HCI) technologies for the next generation of mobile devices. Previous hand gesture implementation requires a large memory and computation power for hand segmentation, which fails to give real-time interaction with mobile devices to users. Therefore, in this paper, we presents a low latency and memory-efficient hand segmentation architecture for natural hand gesture recognition. To obtain both high memory-efficiency and low latency, we propose a streaming hand contour tracing unit and a fast contour filling unit. As a result, it achieves 7.14 ms latency with only 34.8 KB on-chip memory, which are 1.65 times less latency and 1.68 times less on-chip memory, respectively, compare to the best-in-class.

• 융복합기술연구소 논문집
• /
• 제11권1호
• /
• pp.1-5
• /
• 2021

Deep learning based methods achieve state-of-the-art accuracy, however, they typically rely on supervised training with large labeled datasets. It is known in many medical applications that labeling medical images requires significant expertise and much time, and typical hand-tuned approaches for data augmentation fail to capture the complex variations in such images. This paper proposes a 3D image augmentation method to overcome these difficulties. It allows us to enrich diversity of training data samples that is essential in medical image segmentation tasks, thus reducing the data overfitting problem caused by the fact the scale of medical image dataset is typically smaller. Our numerical experiments demonstrate that the proposed approach provides significant improvements over state-of-the-art methods for 3D medical image segmentation.

• Computers and Concrete
• /
• 제5권1호
• /
• pp.61-74
• /
• 2008

Digital image processing algorithms for the analysis and characterization of grains and voids in cemented materials were developed using toolbox functions of a mathematical software package. Utilization of grayscale, color and watershed segmentation algorithms and their performances were demonstrated on artificially prepared self-compacting concrete (SCC) samples. It has been found that color segmentation was more advantageous over the gray scale segmentation for the detection of voids whereas the latter method provided satisfying results for the aggregate grains due to the sharp contrast between their colors and the cohesive matrix. The watershed segmentation method, on the other hand, appeared to be very efficient while separating touching objects in digital images.

• 대한임베디드공학회논문지
• /
• 제16권5호
• /
• pp.209-214
• /
• 2021

Panoptic segmentation, which is now widely used in computer vision such as medical image analysis, and autonomous driving, helps understanding an image with holistic view. It identifies each pixel by assigning a unique class ID, and an instance ID. Specifically, it can classify 'thing' from 'stuff', and provide pixel-wise results of semantic prediction and object detection. As a result, it can solve both semantic segmentation and instance segmentation tasks through a unified single model, producing two different contexts for two segmentation tasks. Semantic segmentation task focuses on how to obtain multi-scale features from large receptive field, without losing low-level features. On the other hand, instance segmentation task focuses on how to separate 'thing' from 'stuff' and how to produce the representation of detected objects. With the advances of both segmentation techniques, several panoptic segmentation models have been proposed. Many researchers try to solve discrepancy problems between results of two segmentation branches that can be caused on the boundary of the object. In this survey paper, we will introduce the concept of panoptic segmentation, categorize the existing method into two representative methods and explain how it is operated on two methods: top-down method and bottom-up method. Then, we will analyze the performance of various methods with experimental results.

• 한국측량학회:학술대회논문집
• /
• 한국측량학회 2003년도 춘계학술발표회 논문집
• /
• pp.229-236
• /
• 2003

In this study, for efficient replacemen of sensor modelling of high-resolution satellite imagery, image segmentation method is applied to the test area of the SPOT-3 satellite imagery. After that, a third-order polynomial model in the sectioned area is compared with the RFM which is to the entire in the test area. As results, plane error of the third-order polynomial model is lower(approximately 0.8m) than that of RFM. On the other hand, height error of RFM is lower(approximately 1.0m).