• International Journal of Internet, Broadcasting and Communication
• /
• 제11권1호
• /
• pp.39-46
• /
• 2019

This paper proposes an adaptive threshold watershed algorithm, which is the method used for image segmentation and boundary detection, which extends the region on the basis of regional minimum point. First, apply adaptive thresholds to determine regional minimum points. Second, it extends the region by applying adaptive thresholds based on determined regional minimum points. Traditional watershed algorithms create over-segmentation, resulting in the disadvantages of breaking boundaries between regions. These segmentation results mainly from the boundary of the object, creating an inaccurate region. To solve these problems, this paper applies an improved watershed algorithm applied with adaptive threshold in regional minimum point search and region expansion in order to reduce over-segmentation and breaking the boundary of region. This resulted in over-segmentation suppression and the result of having the boundary of precisely divided regions. The experimental results show that the proposed algorithm can apply adaptive thresholds to reduce the number of segmented regions and see that the segmented boundary parts are correct.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제7권11호
• /
• pp.2839-2852
• /
• 2013

Context-awareness is an essential part of ubiquitous computing, and over the past decade video based activity recognition (VAR) has emerged as an important component to identify user's context for automatic service delivery in context-aware applications. The accuracy of VAR significantly depends on the performance of the employed human body segmentation algorithm. Previous human body segmentation algorithms often engage modeling of the human body that normally requires bulky amount of training data and cannot competently handle changes over time. Recently, active contours have emerged as a successful segmentation technique in still images. In this paper, an active contour model with the integration of Chan Vese (CV) energy and Bhattacharya distance functions are adapted for automatic human body segmentation using depth cameras for VAR. The proposed technique not only outperforms existing segmentation methods in normal scenarios but it is also more robust to noise. Moreover, it is unsupervised, i.e., no prior human body model is needed. The performance of the proposed segmentation technique is compared against conventional CV Active Contour (AC) model using a depth-camera and obtained much better performance over it.

• Smart Structures and Systems
• /
• 제31권4호
• /
• pp.335-349
• /
• 2023

Bridges constantly undergo deterioration and damage, the most common ones being concrete damage and exposed rebar. Periodic inspection of bridges to identify damages can aid in their quick remediation. Likewise, identifying components can provide context for damage assessment and help gauge a bridge's state of interaction with its surroundings. Current inspection techniques rely on manual site visits, which can be time-consuming and costly. More recently, robotic inspection assisted by autonomous data analytics based on Computer Vision (CV) and Artificial Intelligence (AI) has been viewed as a suitable alternative to manual inspection because of its efficiency and accuracy. To aid research in this avenue, this study performs a comparative assessment of different architectures, loss functions, and ensembling strategies for the autonomous segmentation of bridge components and damages. The experiments lead to several interesting discoveries. Nested Reg-UNet architecture is found to outperform five other state-of-the-art architectures in both damage and component segmentation tasks. The architecture is built by combining a Nested UNet style dense configuration with a pretrained RegNet encoder. In terms of the mean Intersection over Union (mIoU) metric, the Nested Reg-UNet architecture provides an improvement of 2.86% on the damage segmentation task and 1.66% on the component segmentation task compared to the state-of-the-art UNet architecture. Furthermore, it is demonstrated that incorporating the Lovasz-Softmax loss function to counter class imbalance can boost performance by 3.44% in the component segmentation task over the most employed alternative, weighted Cross Entropy (wCE). Finally, weighted softmax ensembling is found to be quite effective when used synchronously with the Nested Reg-UNet architecture by providing mIoU improvement of 0.74% in the component segmentation task and 1.14% in the damage segmentation task over a single-architecture baseline. Overall, the best mIoU of 92.50% for the component segmentation task and 84.19% for the damage segmentation task validate the feasibility of these techniques for autonomous bridge component and damage segmentation using RGB images.

• 한국측량학회지
• /
• 제25권6_1호
• /
• pp.575-583
• /
• 2007

Surface segmentation aims to represent the terrain as a set of bounded and analytically defined surface patches. Many previous segmentation methods have been developed to extract planar patches from LIDAR data for building extraction. However, most of them were not fully satisfactory for more general applications in terms of the degree of automation and the quality of the segmentation results. This is mainly caused from the limited information derived from LIDAR data. The purpose of this study is thus to develop an automatic method to perform surface segmentation by combining not only LIDAR data but also images. A region-based method is proposed to generate a set of planar patches by grouping LIDAR points. The grouping criteria are based on both the coordinates of the points and the corresponding intensity values computed from the images. This method has been applied to urban data and the segmentation results are compared with the reference data acquired by manual segmentation. 76% of the test area is correctly segmented. Under-segmentation is rarely founded but over-segmentation still exists. If the over-segmentation is mitigated by merging adjacent patches with similar properties as a post-process, the proposed segmentation method can be effectively utilized for a reliable intermediate process toward automatic extraction of 3D model of the real world.

• 대한전자공학회논문지SP
• /
• 제44권3호
• /
• pp.42-47
• /
• 2007

영상 분할은 주어진 영상에서 관심 영역을 추출하거나 압축을 위한 비디오 처리 분야에서 중요한 부분이며 특히 영역 기반 비디오 코딩에서는 필수적인 부분이다. 영역 기반의 수리형태학적 영상분할에서는 영상을 단순화한 후 추출된 경사 영상을 가지고 영역 경계를 결정하는 워터쉐이드 기법을 이용하는 방법이 주로 제안되고 있다. 이 방법은 병합될 대상 영역의 수가 많아질수록 병합하는 과정에 필요한 계산량이 지수적으로 증가하고, 영상 내의 잡음이 직접 국부적 최소 점들로 표현되어 영역들의 경계에 대한 기울기에 영향을 주어 영상의 과분할을 초래하게 된다. 따라서 본 논문에서는 이러한 영상의 과분할 문제를 해결할 수 있는 ATM 필터를 제안하였다. 모의실험 결과 제안된 ATM 필터가 전체적인 잡음제거의 향상과 함께 잡음 비율이 20% 이상일 경우의 영상의 선명도 훼손의 정도가 줄어들었음을 확인하였다.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2014년도 춘계학술발표대회
• /
• pp.826-829
• /
• 2014

본 연구에서는 야외 지형 영상 및 항공 영상 등에 대하여 각각의 영역들의 속성을 분할 및 인식 하기 위해 minimum entropy clustering 기반의 군집화 기법과 over-segmentation을 반복 적용하여 군집화 하는 두 방법을 융합한 기법을 제안하였다. 이 기법들을 기반으로 각 군집의 대표 영역을 추출한 후에 학습 데이터를 기반으로 만들어진 텍스톤 사전과 학습 데이터 각각의 텍스톤 모델을 이용하여 텍스톤 히스토그램 매칭을 통해 매칭 포인트를 얻어내고 얻어낸 매칭 포인트를 기반으로 영역의 카테고리를 결정한다. 본 논문에서는 인터넷에서 얻은 일반 야외 영상들로부터 자체적으로 제작한 지형 데이터 셋을 통해 제안한 기법의 우수성을 검증하였으며, 본 실험에서는 영역을 토양, 수풀 그리고 물 지형으로 하여 영상내의 영역을 분류 및 인식하였다.

• 한국멀티미디어학회논문지
• /
• 제22권1호
• /
• pp.27-34
• /
• 2019

In this paper, a new type of lip feature is proposed as distance metric in CIELUV color system. The performance of the proposed feature was tested on face image database, Helen dataset from University of Illinois. The test processes consists of three steps. The first step is feature extraction and second step is principal component analysis for the optimal projection of a feature vector. The final step is Otsu's threshold for a two-class problem. The performance of the proposed feature was better than conventional features. Performance metrics for the evaluation are OverLap and Segmentation Error. Best performance for the proposed feature was OverLap of 65% and 59 % of segmentation error. Conventional methods shows 80~95% for OverLap and 5~15% of segmentation error usually. In conventional cases, the face database is well calibrated and adjusted with the same background and illumination for the scene. The Helen dataset used in this paper is not calibrated or adjusted at all. These images are gathered from internet and therefore, there are no calibration and adjustment.

• International journal of advanced smart convergence
• /
• 제11권4호
• /
• pp.81-87
• /
• 2022

In this paper, we propose a watershed algorithm that applies a high-frequency enhancement filter to emphasize the boundary and a local adaptive threshold to search for minimum points. The previous method causes the problem of over-segmentation, and over- segmentation appears around the boundary of the object, creating an inaccurate boundary of the region. The proposed method applies a high-frequency enhancement filter that emphasizes the high-frequency region while preserving the low-frequency region, and performs a minimum point search to consider local characteristics. When merging regions, a fixed threshold is applied. As a result of the experiment, the proposed method reduced the number of segmented regions by about 58% while preserving the boundaries of the regions compared to when high frequency emphasis filters were not used.

• 한국정보과학회논문지:소프트웨어및응용
• /
• 제32권6호
• /
• pp.523-531
• /
• 2005

확산(Diffusion)을 이용한 기존의 칼라영상 분할은 확산의 횟수가 반복될수록 경계선 정보가 적절히 유지되지 못하거나 잡음을 제거하지 못함으로써 워터쉐드(Watershed) 알고리즘을 적용하는 경우, 과분할을 피할 수 없다는 단점을 갖고 있다. 본 논문에서는 수리 형태학(Mathematical Morphology)과 비선형 확산(Non-Linear Diffusion)을 함께 적용하여 과분할의 문제점을 제거한 워터쉐드 결과를 얻을 수 있는 칼라영상 분할방법을 제안한다. 임의의 칼라 영상을 LUV 색상공간으로 변환하여, 그 각각의 색상공간에 수리 형태학을 응용한 재구성에 의한 닫힘(Reconstruction) 연산과 비선형 확산을 함께 적용하여 경계선을 적절히 유지하면서 잡음을 제거한 단순 영상을 획득할 수 있다. 이 영상에서 칼라 영상의 기울기(Gradient) 정보를 획득하고, 워터쉐드 알고리즘을 적용하여 영상을 분할한다. 실험 결과, 기존의 방법보다 과분할이 현저히 제거되고, 칼라 영상이 매우 효과적으로 분할됨을 확인하였다

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2000년도 ITC-CSCC -1
• /
• pp.482-485
• /
• 2000

A modified watershed transform is proposed which is context-free marker-controlled and minima imposition-free to reduce the over-segmentation and to speedup the transform. In contrast to the conventional methods in which a priori knowledge, such as flat zones, zones of homogeneous texture, and morphological distance, is required for marker extraction, context-free marker extraction is proposed by using the attention operator based on the GST (generalized symmetry transform). By using the context-free marker, the proposed watershed transform exploit marker-constrained labeling to speedup the computation and to reduce the over-segmentation by eliminating the unnecessary geodesic reconstruction such as the minima imposition and thereby eliminating the necessity of the post-processing of region merging. The simulation results show that the proposed method can extract context-free markers inside the objects from the complex background that includes multiple objects and efficiently reduces over-segmentation and computation time.