• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2011년도 춘계학술발표대회
• /
• pp.447-450
• /
• 2011

This paper shows the application of P-N Learning [4] method in the soccer ball detection and improvement for increasing the speed of processing. In the P-N learning, the learning process is guided by positive (P) and negative (N) constraints which restrict the labeling of the unlabeled data, identify examples that have been classified in contradiction with structural constraints and augment the training set with the corrected samples in an iterative process. But for the long-view in the soccer game, P-N learning will produce so many ferns that more time is spent than other methods. We propose that color histogram of each frame is constructed to delete the unnecessary details in order to decreasing the number of feature points. We use the mask to eliminate the gallery region and Line Hough Transform to remove the line and adjust the P-N learning's parameters to optimize accurate and speed.

• 디지털콘텐츠학회 논문지
• /
• 제19권1호
• /
• pp.165-171
• /
• 2018

그림자는 자연 영상에서 관찰되는 물리적인 현상으로 지능형 비디오 감시, 교통 감시 및 항공 영상 분석 등과 같은 다양한 영상처리 시스템에 부정적인 영향을 미치는 요소이다. 따라서 그림자의 검출은 컴퓨터 비전의 전 분야에서 전처리 과정으로 고려되어야 한다. 본 논문에서는 참조 영상이 필요 없는 단일 자연 영상에서 그림자 검출을 위한 다양한 특징 요소들을 정의하고 분석하였다. 그림자 요소들은 영상의 밝기, 색도, 조도불변, 색상불변 및 정보의 불확실성을 의미하는 엔트로피 영상 등을 기술하였으며, 분석 결과 색도와 조도불변 영상이 그림자 검출 및 복원에 효과적임을 알 수 있었다. 향후 다양한 그림자 특징 요소들의 퓨전 맵을 정의하고, 다양한 조명 수준에 적응 가능한 그림자 검출 및 색도와 조도불변 영상을 이용한 그림자 제거 연구를 계속하고자 한다.

• 한국콘텐츠학회:학술대회논문집
• /
• 한국콘텐츠학회 2009년도 춘계 종합학술대회 논문집
• /
• pp.889-894
• /
• 2009

Accompanied by the rapid development of Computer Vision, Visual surveillance has achieved great evolution with more and more complicated processing. However there are still many problems to be resolved for robust and reliable visual surveillance, and the cast shadow occurring in motion detection process is one of them. Shadow pixels are often misclassified as object pixels so that they cause errors in localization, segmentation, tracking and classification of objects. This paper proposes a novel cast shadow removal method. As opposed to previous conventional methods, which considers pixel properties like intensity properties, color distortion, HSV color system, and etc., the proposed method utilizes observations about edge patterns in the shadow region in the current frame and the corresponding region in the background scene, and applies Laplacian edge detector to the blob regions in the current frame and the background scene. Then, the product of the outcomes of application determines whether the blob pixels in the foreground mask comes from object blob regions or shadow regions. The proposed method is simple but turns out practically very effective for Gaussian Mixture Model, which is verified through experiments.

• 한국멀티미디어학회논문지
• /
• 제20권11호
• /
• pp.1729-1740
• /
• 2017

This paper describes a vision-based method that effectively recognize a traffic light. The method consists of two steps of traffic light detection and discrimination. Many related studies have used color information to detect traffic light, but color information is not robust to the varying illumination environment. This paper proposes a new method of traffic light detection based on intensity and saturation. When a traffic light is turned on, the light region usually shows values with high saturation and high intensity. However, when the light region is oversaturated, the region shows values of low saturation and high intensity. So this study proposes a method to be able to detect a traffic light under these conditions. After detecting a traffic light, it estimates the size of the body region including the traffic light and extracts the body region. The body region is compared with five models which represent specific traffic signals, then the region is discriminated as one of the five models or rejected as none of them. Experimental results show the performance of traffic light detection reporting the precision of 97.2%, the recall of 95.8%, and correct recognition rate of 94.3%. These results shows that the proposed method is effective.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제4권4호
• /
• pp.618-632
• /
• 2010

This paper presents a novel approach to control the augmented reality (AR) objects robustly in a marker-less AR system by fingertip tracking and hand pattern recognition. It is known that one of the promising ways to develop a marker-less AR system is using human's body such as hand or face for replacing traditional fiducial markers. This paper introduces a real-time method to manipulate the overlaid virtual objects dynamically in a marker-less AR system using both hands with a single camera. The left bare hand is considered as a virtual marker in the marker-less AR system and the right hand is used as a hand mouse. To build the marker-less system, we utilize a skin-color model for hand shape detection and curvature-based fingertip detection from an input video image. Using the detected fingertips the camera pose are estimated to overlay virtual objects on the hand coordinate system. In order to manipulate the virtual objects rendered on the marker-less AR system dynamically, a vision-based hand control interface, which exploits the fingertip tracking for the movement of the objects and pattern matching for the hand command initiation, is developed. From the experiments, we can prove that the proposed and developed system can control the objects dynamically in a convenient fashion.

• 한국게임학회 논문지
• /
• 제14권5호
• /
• pp.79-86
• /
• 2014

증강현실 기술을 게임에 접목하려는 시도가 많이 이루어지고 있다. 본 논문에서는 실시간으로 스마트 기기의 카메라로부터 손동작 2차원 영상을 획득하고 HSV 컬러 영역을 활용하여 해당 색상의 물체 또는 신체를 실시간으로 검출해, 게임의 요소로 활용하여 즐길 수 있는 2D 퍼즐게임을 개발하였다. 이는 스마트 기기에 컴퓨터 비전을 접목한 형태의 게임으로, 교육 및 엔터테인먼트 환경에서 스마트 기기의 휴대성과 가상현실 체험의 현장감을 접목시킨 새로운 인터랙티브 기술이 될 것이다.

• 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.

• 한국정보통신학회논문지
• /
• 제15권7호
• /
• pp.1564-1572
• /
• 2011

본 논문에서는 증강현실을 위한 히스토그램 기반의 손 인식 기법을 제안한다. 손동작 인식은 사용자와 컴퓨터 사이의 친숙한 상호작용을 가능하게 한다. 하지만, 비젼 기반의 손동작 인식은 복잡한 손의 형태로 인한 관찰 방향 변화에 따른 입력 영상의 다양함으로 인식에 어려움이 따른다. 따라서 본 논문에서는 손의 형태적인 특징을 이용한 새로운 모델을 제안한다. 제안하는 기법에서 손 인식은 카메라로부터 획득한 영상에서 손 영역을 분리하는 부분과 인식하는 부분으로 구성된다. 카메라로부터 획득한 영상에서 배정을 제거하고 피부색 정보를 이용하여 손 영역을 분리한다. 다음으로 히스토그램을 이용하여 손의 특징점을 구하여 손의 형태를 계산한다. 마지막으로 판별된 손인식 정보를 이용하여 3차원 객체를 제어하는 증강현실 시스템을 구현하였다. 실험을 통해 제안한 기법의 구현 속도가 빠르고 인식률도 91.7%로 비교적 높음을 확인하였다.

• 한국정보통신학회:학술대회논문집
• /
• 한국해양정보통신학회 2009년도 춘계학술대회
• /
• pp.396-399
• /
• 2009

스테레오 비전 시스템(stereo vision system)은 2차원 영상정보를 이용하여 3차원 깊이 정보를 획득하는 데 유용한 방법으로, 그동안 많은 연구가 진행되었다. 3차원 깊이 정보를 획득하기 위해서는 영상의 대응점을 찾아야 하는데, 속도와 정확성을 동시에 만족시키기가 어렵다. 이러한 문제를 해결하기 위해, 본 논문에서는 적응적 가중치(weight)를 적용한 cost aggregation 기반의 스테레오 정합 기법을 제안한다. 이 방법은 스테레오 영상의 특징을 이용하여 가중치를 획득하고, 색상정보, 밝기정보, 거리정보에 가중치를 적용한 후, 이를 이용하여 대응점을 찾아 깊이 정보를 추출한다. 제안된 방법의 성능을 평가하기 위하여 ground truth가 존재하는 다양한 스테레오 영상을 이용하여 실험하였으며, 실험 결과 다양한 영상에서도 향상된 결과를 보였다.

• 한국농공학회논문집
• /
• 제66권4호
• /
• pp.27-39
• /
• 2024

Soil texture is determined by the proportions of sand, silt, and clay within the soil, which influence characteristics such as porosity, water retention capacity, electrical conductivity (EC), and pH. Traditional classification of soil texture requires significant sample preparation including oven drying to remove organic matter and moisture, a process that is both time-consuming and costly. This study aims to explore an alternative method by developing an AI model capable of predicting soil texture from images of pre-sorted soil samples using computer vision and deep learning technologies. Soil samples collected from agricultural fields were pre-processed using sieve analysis and the images of each sample were acquired in a controlled studio environment using a smartphone camera. Color distribution ratios based on RGB values of the images were analyzed using the OpenCV library in Python. A convolutional neural network (CNN) model, built on PyTorch, was enhanced using Digital Image Processing (DIP) techniques and then trained across nine distinct conditions to evaluate its robustness and accuracy. The model has achieved an accuracy of over 80% in classifying the images of pre-sorted soil samples, as validated by the components of the confusion matrix and measurements of the F1 score, demonstrating its potential to replace traditional experimental methods for soil texture classification. By utilizing an easily accessible tool, significant time and cost savings can be expected compared to traditional methods.