• IEIE Transactions on Smart Processing and Computing
• /
• 제1권3호
• /
• pp.125-132
• /
• 2012

This paper proposes an automatic object segmentation and background composition method for video communication over consumer mobile phones. The object regions were extracted based on the motion and color variance of the first two frames. To combine the motion and variance information, the Euclidean distance between the motion boundary pixel and the neighboring color variance edge pixels was calculated, and the nearest edge pixel was labeled to the object boundary. The labeling results were refined using the morphology for a more accurate and natural-looking boundary. The grow-cut segmentation algorithm begins in the expanded label map, where the inner and outer boundary belongs to the foreground and background, respectively. The segmented object region and a new background image stored a priori in the mobile phone was then composed. In the background composition process, the background motion was measured using the optical-flow, and the final result was synthesized by accurately locating the object region according to the motion information. This study can be considered an extended, improved version of the existing background composition algorithm by considering motion information in a video. The proposed segmentation algorithm reduces the computational complexity significantly by choosing the minimum resolution at each segmentation step. The experimental results showed that the proposed algorithm can generate a fast, accurate and natural-looking background composition.

• 대한전기학회논문지:전력기술부문A
• /
• 제48권3호
• /
• pp.321-329
• /
• 1999

Moving Object segmentation extracts an interested moving object on a consecutive image frames, and has been used for factory automation, autonomous navigation, video surveillance, and VOP(Video Object Plane) detection in a MPEG-4 method. This paper proposes new segmentation method using difference images are calculated with three consecutive input image frames, and used to calculate both coarse object area(AI) and it's movement area(OI). An AI is extracted by removing background using background area projection(BAP). Missing parts in the AI is recovered with help of the OI. Boundary information of the OI confines missing parts of the object and gives inital curves for active contour optimization. The optimized contours in addition to the AI make the boundaries of the moving object. Experimental results of a fast moving object on a complex background scene are included.

• 디지털융복합연구
• /
• 제10권3호
• /
• pp.167-172
• /
• 2012

본 논문에서는 단일 프레임 영상에 존재하는 객체를 Active Contour 기반의 영역 분할 과정을 거쳐 분할하였다. Active Contour는 영상에서 객체의 윤곽 형태를 검출해내는 것으로 다중 객체 분할을 위해 각 객체의 윤곽 형태를 검출해 낼 수 있도록 다중 탐색 시작점을 갖도록 하였다. 생성된 객체 별 윤곽 정보를 기반으로 이진화하여 초기 객체 영역을 생성하였다. 초기 객체 영역 내부의 홀 영역과 픽셀 값의 변화로 인한 내부 분할을 hole filling을 수행하여 보정함으로써 최종 객체 영역을 생성하였다. 제안한 기법은 기존 영역 기반 분할의 문제점인 잡음이나 경계선 부근에서 객체 분할이 정확히 이루어지지 않는 부분을 보완하였다. 제안 방법을 비교하기 위해 실제 영상에 기존에 제안된 객체 분할 방법과 제안한 방법을 각각 적용하여 비교하였다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제7권12호
• /
• pp.3180-3199
• /
• 2013

While non-predefined object segmentation (NDOS) distinguishes an arbitrary self-assumed object from its background, predefined object segmentation (DOS) pre-specifies the target object. In this paper, a new and novel method to segment predefined objects is presented, by globally optimizing an orientation-based objective function that measures the fitness of the object boundary, in a discretized parameter space. A specific object is explicitly described by normalized discrete sets of boundary points and corresponding normal vectors with respect to its plane shape. The orientation factor provides robust distinctness for target objects. By considering the order of transformation elements, and their dependency on the derived over-segmentation outcome, the domain of translations and scales is efficiently discretized. A branch and bound algorithm is used to determine the transformation parameters of a shape model corresponding to a target object in an image. The results tested on the PASCAL dataset show a considerable achievement in solving complex backgrounds and unclear boundary images.

• International Journal of Contents
• /
• 제9권1호
• /
• pp.6-10
• /
• 2013

Foreground estimation in object segmentation has been an important issue for last few decades. In this paper we propose a GrabCut based automatic foreground estimation method using block clustering. GrabCut is one of popular algorithms for image segmentation in 2D image. However GrabCut is semi-automatic algorithm. So it requires the user input a rough boundary for foreground and background. Typically, the user draws a rectangle around the object of interest manually. The goal of proposed method is to generate an initial rectangle automatically. In order to create initial rectangle, we use Gabor filter and Saliency map and then we use 4 features (amount of area, variance, amount of class with boundary area, amount of class with saliency map) to categorize foreground and background. From the experimental results, our proposed algorithm can achieve satisfactory accuracy in object segmentation without any prior information by the user.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제15권9호
• /
• pp.3204-3220
• /
• 2021

We perform the task of video object segmentation by incorporating a conditional random field (CRF) and convolutional neural networks (CNNs). Most methods employ a CRF to refine a coarse output from fully convolutional networks. Others treat the inference process of the CRF as a recurrent neural network and then combine CNNs and the CRF into an end-to-end model for video object segmentation. In contrast to these methods, we propose a novel higher-order CRF model to solve the problem of video object segmentation. Specifically, we use CNNs to establish a higher-order dependence among pixels, and this dependence can provide critical global information for a segmentation model to enhance the global consistency of segmentation. In general, the optimization of the higher-order energy is extremely difficult. To make the problem tractable, we decompose the higher-order energy into two parts by utilizing auxiliary variables and then solve it by using an iterative process. We conduct quantitative and qualitative analyses on multiple datasets, and the proposed method achieves competitive results.

• 방송공학회논문지
• /
• 제21권5호
• /
• pp.782-791
• /
• 2016

영상에서 배경으로부터 객체를 추출하는 영상 segmentation 알고리즘은 물체 인식 및 추적 등 다양한 응용분야에서 활용될 수 있다. 본 논문에서는 고정된 카메라에서 다수의 초기 프레임을 참조하여 실시간 객체 segmentation 방법을 제안한다. 먼저 객체와 배경을 분류하는 확률모델을 제안하였으며 초기 프레임 동안에 카메라의 color consistency와 focus 특성을 분석하여 안정적인 segmentation 성능을 증가시켰다. 또한 분류된 객체에서 human의 skeleton 특성을 이용하여 추출 결과를 보정하는 방법을 제안한다. 마지막으로 제안된 알고리즘은 객체 segmentation 실시간 처리를 위하여 복잡도를 최소화하므로 다양한 mobile 단말에 확대 적용 가능하다.

• 방송공학회논문지
• /
• 제25권7호
• /
• pp.1081-1094
• /
• 2020

With the recent development of deep learning, most computer vision-related tasks are being solved with deep learning-based network technologies such as CNN and RNN. Computer vision tasks such as object detection or object segmentation use intermediate features extracted from the same backbone such as Resnet or FPN for training and inference for object detection and segmentation. In this paper, an experiment was conducted to find out the compression efficiency and the effect of encoding on task inference performance when the features extracted in the intermediate stage of CNN are encoded. The feature map that combines the features of 256 channels into one image and the original image were encoded in HEVC to compare and analyze the inference performance for object detection and segmentation. Since the intermediate feature map encodes the five levels of feature maps (P2 to P6), the image size and resolution are increased compared to the original image. However, when the degree of compression is weakened, the use of feature maps yields similar or better inference results to the inference performance of the original image.

• JSTS:Journal of Semiconductor Technology and Science
• /
• 제12권2호
• /
• pp.175-185
• /
• 2012

Predictive watershed transform is a popular object segmentation algorithm which achieves a speed-up by identifying image regions that are different from the previous frame and performing object segmentation only for those regions. However, incorrect segmentation is often generated by the predictive watershed transform which uses only local information in merge-split decision on boundary regions. This paper improves the predictive watershed transform to increase the accuracy of segmentation results by using the additional information about the root of boundary regions. Furthermore, the proposed algorithm is processed in a block-based manner such that an image frame is decomposed into blocks and each block is processed independently of the other blocks. The block-based approach makes it easy to implement the algorithm in hardware and also permits an extension for parallel execution. Experimental results show that the proposed watershed transform produces more accurate segmentation results than the predictive watershed transform.

• 대한전자공학회논문지SP
• /
• 제40권1호
• /
• pp.51-62
• /
• 2003

본 논문에서는 분할기반 영상 부호화를 위한 새로운 영상 분할 알고리즘을 제안한다. 제안된 방법은 움직임과 밝기 정보에 기반한 새로운 유사성 척도를 사용한다. 그리고 하나의 분할 단계 내에 밝기와 움직임 정보가 함께 결합된다. 영상 분할은 분수령 알고리즘에 기반한 영역 확장법을 통해 이루처지며, 연속된 프레임에 대한 분할은 분할결과가 시간축으로 일관성을 유지하도록 추적방법을 통해 이루어진다. 모의실험결과, 제안된 방법이 통계적 척도만을 사용한 방법과는 달리, 물체의 경계를 결정하는데 효과적임을 보였다.