• Title/Summary/Keyword: Grab

Search Result 217, Processing Time 0.024 seconds

Window Production Method based on Low-Frequency Detection for Automatic Object Extraction of GrabCut (GrabCut의 자동 객체 추출을 위한 저주파 영역 탐지 기반의 윈도우 생성 기법)

  • Yoo, Tae-Hoon;Lee, Gang-Seong;Lee, Sang-Hun
    • Journal of Digital Convergence
    • /
    • v.10 no.8
    • /
    • pp.211-217
    • /
    • 2012
  • Conventional GrabCut algorithm is semi-automatic algorithm that user must be set rectangle window surrounds the object. This paper studied automatic object detection to solve these problem by detecting salient region based on Human Visual System. Saliency map is computed using Lab color space which is based on color opposing theory of 'red-green' and 'blue-yellow'. Then Saliency Points are computed from the boundaries of Low-Frequency region that are extracted from Saliency Map. Finally, Rectangle windows are obtained from coordinate value of Saliency Points and these windows are used in GrabCut algorithm to extract objects. Through various experiments, the proposed algorithm computing rectangle windows of salient region and extracting objects has been proved.

IR Image Segmentation using GrabCut (GrabCut을 이용한 IR 영상 분할)

  • Lee, Hee-Yul;Lee, Eun-Young;Gu, Eun-Hye;Choi, Il;Choi, Byung-Jae;Ryu, Gang-Soo;Park, Kil-Houm
    • Journal of the Korean Institute of Intelligent Systems
    • /
    • v.21 no.2
    • /
    • pp.260-267
    • /
    • 2011
  • This paper proposes a method for segmenting objects from the background in IR(Infrared) images based on GrabCut algorithm. The GrabCut algorithm needs the window encompassing the interesting known object. This procedure is processed by user. However, to apply it for object recognition problems in image sequences. the location of window should be determined automatically. For this, we adopted the Otsu' algorithm for segmenting the interesting but unknown objects in an image coarsely. After applying the Otsu' algorithm, the window is located automatically by blob analysis. The GrabCut algorithm needs the probability distributions of both the candidate object region and the background region surrounding closely the object for estimating the Gaussian mixture models(GMMs) of the object and the background. The probability distribution of the background is computed from the background window, which has the same number of pixels within the candidate object region. Experiments for various IR images show that the proposed method is proper to segment out the interesting object in IR image sequences. To evaluate performance of proposed segmentation method, we compare other segmentation methods.

A Design of a Selective Multi Sink GRAdient Broadcast Scheme in Large Scale Wireless Sensor Network (대규모 무선 센서 네트워크 환경을 위한 다중 Sink 브로드캐스팅 기법 설계)

  • Lee, Ho-Sun;Cho, Ik-Lae;Lee, Kyoon-Ha
    • Journal of the Korea Society of Computer and Information
    • /
    • v.10 no.4 s.36
    • /
    • pp.239-248
    • /
    • 2005
  • The reliability and efficiency of network must be considered in the large scale wireless sensor networks. Broadcast method must be used rather than unicast method to enhance the reliability of networks. In recently proposed GRAB (GRAdient Broadcast) can certainly enhance reliability of networks fy using broadcast but its efficiency regarding using energy of network is low due to using only one sink. Hence, the lifetime of networks is reduced. In the paper we propose the scheme of SMSGB (Selective Multi Sink Gradient Broadcast) which uses single sink of multi-sink networks. The broadcast based SMSGB can secure reliability of large scale wireless sensor networks. The SMSGB can also use the network's energy evenly via multi sink distribution. Our experiments show that using SMSGB was reliable as GRAB and it increased the network's lifetime by 18% than using GRAB.

  • PDF

A Comparison of Sit-to-Stand Performance Based on Toilet Grab Bar Positions (화장실 안전손잡이 위치에 따른 앉은 자세에서 일어서기 비교)

  • Chung, Hyun-Ae;Son, Yu-Na;Lee, Ji-Hun;Kim, Hee-Dong
    • PNF and Movement
    • /
    • v.17 no.2
    • /
    • pp.275-282
    • /
    • 2019
  • Purpose: This study aimed to investigate the optimal positions of safety grab bars for effective sit-to-stand (STS) movement by comparing the results of the STS movement while using a safety grab bar installed under two different conditions: the height of the grab bar installation was determined by (1) the Building Act and (2) the principle of proprioceptive neuromuscular facilitation (PNF). Methods: A total of 50 undergraduate students participated in this study, and they were required to perform an STS movement twice under each condition. A baropodometric platform for sitting and a Biorescue (RM Ingenierie, France) were used to collect and analyze changes in the center of pressure (COP) on the left and right sides before and after performing the STS movement. The average completion time for the STS movement was also measured for analysis. Moreover, the participants were asked to express their individual subjective preferences regarding the two positions of the grab bars. Results: The COP changes were significantly smaller when performing the STS movement with the grab bar installed at the height determined by the PNF principle than the Building Act (p<0.01), and the difference in the completion time of the STS movement was not statistically significant between the two conditions. Conclusion: The findings of this study suggest that the principle of PNF can be useful for planning therapeutic exercise as well as for proposing the optimal grab bar position for older adults and those with health-related issues when performing the STS movement. In addition, this may serve as a basic rehabilitation technique for maintaining remaining functions and providing functional efficiency.

Automatic Segmentation of Product Bottle Label Based on GrabCut Algorithm

  • Na, In Seop;Chen, Yan Juan;Kim, Soo Hyung
    • International Journal of Contents
    • /
    • v.10 no.4
    • /
    • pp.1-10
    • /
    • 2014
  • In this paper, we propose a method to build an accurate initial trimap for the GrabCut algorithm without the need for human interaction. First, we identify a rough candidate for the label region of a bottle by applying a saliency map to find a salient area from the image. Then, the Hough Transformation method is used to detect the left and right borders of the label region, and the k-means algorithm is used to localize the upper and lower borders of the label of the bottle. These four borders are used to build an initial trimap for the GrabCut method. Finally, GrabCut segments accurate regions for the label. The experimental results for 130 wine bottle images demonstrated that the saliency map extracted a rough label region with an accuracy of 97.69% while also removing the complex background. The Hough transform and projection method accurately drew the outline of the label from the saliency area, and then the outline was used to build an initial trimap for GrabCut. Finally, the GrabCut algorithm successfully segmented the bottle label with an average accuracy of 92.31%. Therefore, we believe that our method is suitable for product label recognition systems that automatically segment product labels. Although our method achieved encouraging results, it has some limitations in that unreliable results are produced under conditions with varying illumination and reflections. Therefore, we are in the process of developing preprocessing algorithms to improve the proposed method to take into account variations in illumination and reflections.

Evaluation and management of work process in dredger using ECDIS (ECDIS에 의한 준설선의 작업공정 관리 및 평가)

  • Lee, Dae-Jae
    • Journal of the Korean Society of Fisheries and Ocean Technology
    • /
    • v.43 no.3
    • /
    • pp.212-221
    • /
    • 2007
  • This paper describes on the evaluation and management of work process in suction hopper dredger and grab bucket dredger as an application of a PC-based ECDIS system. The dynamic tracking of dredging bucket and the data logging of grab dredging information were performed by using the grab dredging vessel "Kunwoong G-18". The position and route tracking of the dredger moving toward the ocean dumping site of dredged material was performed by using the hopper dredging vessel "Samyang-7". The evaluation of wok process in the dredging field, for grab dredger, was continuously carried out on January to May, 2006, in Incheon Hang and for hopper dredger, on July to December, 2003, in Busan Hang, Korea. The dredging information, such as dredger's position, heading, dredging depth and route track which was individually time stamped during the dredging operation, was automatically processed in real-time on the ECDIS and displayed simultaneously on the S-57 ENC chart. From these results, we conclude that the ECDIS system can be applied as a tool in order to manage the work process during the dredging operation, and also in order to generate the factual record of the dredging activities that is sufficient for dredging inspector to accurately evaluate the contract performance even in the absence of a full-time onboard inspector.

Unconstrained Object Segmentation Using GrabCut Based on Automatic Generation of Initial Boundary

  • Na, In-Seop;Oh, Kang-Han;Kim, Soo-Hyung
    • International Journal of Contents
    • /
    • v.9 no.1
    • /
    • 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.

Generation of Active Stromotion Images using Kernel-based Tracking and Grab-Cut Algorithm (커널 기반 객체 추적 및 Grab-Cut 알고리즘을 이용한 액티브 스트로모션 영상 생성)

  • Oh, Kyeong-Seok;Choi, Yoo-Joo
    • Proceedings of the Korean Society of Broadcast Engineers Conference
    • /
    • 2016.11a
    • /
    • pp.131-133
    • /
    • 2016
  • 본 논문은 연속적인 비디오 시퀀스에서 움직이는 객체의 영역을 효율적으로 분할하기 위하여 커널 기반 객체 추적과 Grab-Cut 알고리즘을 결합한 비디오 영역 분할 방법을 제안한다. 제안 방법에서는 추적 목표 객체의 초기 위치를 사각영역으로 선택하면, 사각의 외부 영역을 배경색상으로 인지하고, 배경 색상을 고려한 목표 객체의 주요 색상을 분석한다. 이를 기반으로 커널기반 객체 추적 기법을 적용하여 빠르게 객체의 영역을 추출한다. 추적한 각 객체의 영역에서 중앙 객체 영역과 배경 영역의 색 정보를 초기값으로 하여 Grab-Cut 알고리즘을 수행하고 사각형 형태가 아닌 객체의 실루엣 최적화된 영역으로 분할한다. 제안 방법을 스포츠 방송, 광고, 영화 등의 특수 효과로 활용되고 있는 stromotion 영상 생성에 적용하기 위하여 프레임별 추출된 객체의 영상을 새로운 프레임 영상에 합성하는 작업을 수행하여, 초당 10 프레임의 처리 속도에서 원하는 스트로모션 효과 영상을 생성하였다.

  • PDF

Improvement of Background Subtraction Algorithm using GrabCut (GrabCut 을 이용한 배경 분리 알고리즘의 정확도 개선)

  • Lee, Sang-Hoon;Kim, Gibak;Cho, Nam Ik
    • Proceedings of the Korean Society of Broadcast Engineers Conference
    • /
    • 2015.07a
    • /
    • pp.129-132
    • /
    • 2015
  • 본 논문에서는 기존의 배경 분리 알고리즘 결과에 GrabCut 알고리즘을 도입하여 보다 정확한 배경 분리를 수행하고자 한다. 기존의 알고리즘은 동영상의 프레임 간 정보만을 이용하여 배경 확률 모델을 만들고 배경과 전경을 분리한다. 제안하는 알고리즘에서는 먼저 프레임 간의 정보를 이용하여 간단하게 배경과 전경을 분리하는 기존의 배경 분리 알고리즘을 적용한다. 분리된 결과의 정확도를 향상시키기 위해 프레임 내의 정보를 이용하는 GrabCut 알고리즘을 적용한다. 즉, 본 연구에서는 동영상의 프레임 간 정보와 프레임 내 정보를 모두 이용하여 배경과 전경을 분리하고자 한다. 실험결과에서 Change Detection Workshop dataset 에 포함된 몇 가지 영상에 대해 실험 한 후 결과 영상 비교 및 F-measure 를 통해 개선된 결과를 확인할 수 있다.

  • PDF