• 한국방송∙미디어공학회:학술대회논문집
• /
• 한국방송공학회 1995년도 학술대회
• /
• pp.143-148
• /
• 1995

In this paper, we describe a fast 3D video segmentation method using mathematical morphology. The proposed 3D video segmentation algorithm is composed of intra-frame segmentation step and inter-frame segmentation step. In the intra-frame segmentation step, the first frame is segmented using the fast hierarchical segmentation method. Then, in the inter-frame segmentation step, the next frames are segmented using markers that are extracted from the difference of previous segmentation result and simplified present image. Experimental results show that the proposed method has more fast structure and is suitable for video segmentation.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제16권1호
• /
• pp.60-79
• /
• 2022

The U-Net architecture-based segmentation models attained remarkable performance in numerous medical image segmentation missions like skin lesion segmentation. Nevertheless, the resolution gradually decreases and the loss of spatial information increases with deeper network. The fusion of adjacent layers is not enough to make up for the lost spatial information, thus resulting in errors of segmentation boundary so as to decline the accuracy of segmentation. To tackle the issue, we propose a new deep learning-based segmentation model. In the decoding stage, the feature channels of each decoding unit are concatenated with all the feature channels of the upper coding unit. Which is done in order to ensure the segmentation effect by integrating spatial and semantic information, and promotes the robustness and generalization of our model by combining the atrous spatial pyramid pooling (ASPP) module and channel attention module (CAM). Extensive experiments on ISIC2016 and ISIC2017 common datasets proved that our model implements well and outperforms compared segmentation models for skin lesion segmentation.

• 사물인터넷융복합논문지
• /
• 제9권1호
• /
• pp.97-104
• /
• 2023

본 논문은 ESRGAN(Enhanced Super Resolution GAN)과 SSS(Semantic Soft Segmentation)을 이용한 객체 분할에 관한 것이다. 본 논문의 연구진이 앞서 제안한 Mask R-CNN과 SSS를 이용한 객체 분할 방법의 분할 성능은 전반적으로 양호하지만 객체의 크기가 상대적으로 작은 경우 분할 성능이 저조해지는 문제점이 있었다. 본 논문은 이러한 문제점을 해소하기 위한 것이다. 제안된 방법은 Mask R-CNN을 통해 검출된 객체의 크기가 일정 기준치 이하인 경우, ESRGAN을 통해 초해상화를 수행한 후, SSS을 수행함으로써 소형 객체의 분할 성능을 개선하고자 한다. 제안된 방법에 따르면, 기존의 방법에 비해 크기가 작은 객체의 분할 특성을 좀 더 효과적으로 개선할 수 있음을 확인할 수 있었다.

• 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
• /
• 제42권6호
• /
• pp.43-54
• /
• 2005

이본 논문에서는 Bayesian 영상 분할법과 SOM(Self Organization feature Map)을 이용한 텍스쳐(Texture) 분할 방법을 제안한다. SOM의 입력으로 다중 스케일에서의 웨이블릿 계수를 사용하고, 훈련된 SOM으로부터 관측 데이터에 대한 우도(尤度, likelihood)와 사후확률을 구하는 방법을 제시한다. 훈련된 SOM들로부터 구한 사후확률과 MAP(Maximum A Posterior) 분류법을 이용하여 텍스쳐 분할을 얻는다. 그리고 문맥 정보를 이용하여 텍스쳐 분할 결과를 개선하였다. 제안 방법은 HMT(Hidden Markov Tree)을 이용한 텍스쳐 분할보다 더 우수한 결과를 보여준다. 또한 SOM과 HMTseg라고 불리는 다중스케일 Bayesian 영상 분할 기법을 이용한 텍스쳐 분할 결과는 HMT와 HMTseg을 이용한 결과보다 더 우수한 성능을 보여준다.

• 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.

• 전자공학회논문지CI
• /
• 제41권4호
• /
• pp.9-21
• /
• 2004

본 논문은 동영상내의 객체를 자동으로 추출하고 추적할 수 있는 유전자 알고리즘 기반의 분할 방법을 제안한다. 제안된 방법은 시간 분할과 공간 분할로 이루어진다. 공간 분할은 각 프레임을 정확한 경계를 가진 영역으로 나누고 시간 분할은 각 프레임을 전경 영역과 배경 영역으로 나눈다. 공간 분할은 분산 유전자 알고리즘을 이용하여 수행된다. 그러나, 일반적인 유전자 알고리즘과는 달리, 염색체는 이전 프레임의 분할 결과로부터 초기화되고, 동적인 객체 부분에 대응하는 불안정 염색체만이 진화연산자에 의해 진화된다. 시간 분할은 두 개의 연속적인 프레임의 밝기 차이에 기반을 둔 적응적 임계치 방법에 의해 수행한다. 얻어진 공간과 시간 분할 결과의 결합을 통해서 객체를 추출하고, 이 객체들은 natural correspondence에 의해 전체 동영상을 통해 정확히 추적된다. 제안된 방법은 다음의 두 가지 장점을 가진다. 1) 제안된 비디오 분할 방법은 사전 정보를 필요로 하지 않는 자동 동영상 분할 방법이다. 2) 제안된 공간 분할방법은 기존의 유전자 알고리즘보다 해공간의 효율적인 탐색을 제공할 수 있을 뿐만 아니라, 정확한 객체 추적 메커니즘을 포함하고 있는 새로운 진화 알고리즘이다. 이러한 장점들은 제안된 방법이 잘 알려진 동영상과 실제 동영상에 성공적으로 적용됨을 통해 검증된다.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2003년도 Proceedings of ACRS 2003 ISRS
• /
• pp.1323-1325
• /
• 2003

As to many conventional segmentation approaches , spatial autocorrelation, perhaps being the first law of geography, is always overlooked. Thus, the corresponding segmentation results are always not so satisfying, which will further affect the subsequent image processing or analyses. In order to improve segmentation results, a geostatistic based segmentation approach with the consideration of spatial autocorrelation hidden in remote-sensing images is proposed in this article. First, by calculating the mean variance between each pair of pixels at given different lag distances, information like the size of typical targets in the scene can be obtained, and segmentation thresholds are calculated accordingly. Second, an initial region growing segmentation approach is implemented. Finally, based on the segmentation thresholds obtained at the first step and the initial segmentation results, the final segmentation results are obtained using the same region growing approach by taking the local mutual best fitting strategy. From the experiment results, we found the approach is rather promising. However, there still exists some problems to be settled, and further researches should be conducted in the future.

• International Journal of Computer Science & Network Security
• /
• 제23권7호
• /
• pp.61-70
• /
• 2023

Image segmentation is a very crucial step in effective digital image processing. In the past decade, several research contributions were given related to this field. However, a general segmentation algorithm suitable for various applications is still challenging. Among several image segmentation approaches, graph-based approach has gained popularity due to its basic ability which reflects global image properties. This paper proposes a methodology to partition the image with its pixel, region and texture along with its intensity. To make segmentation faster in large images, it is processed in parallel among several CPUs. A way to achieve this is to split images into tiles that are independently processed. However, regions overlapping the tile border are split or lost when the minimum size requirements of the segmentation algorithm are not met. Here the contributions are made to segment the image on the basis of its pixel using min-cut/max-flow algorithm along with edge-based segmentation of the image. To segment on the basis of the region using a homogenous optimum cut algorithm with boundary segmentation. On the basis of texture, the object type using spectral partitioning technique is identified which also minimizes the graph cut value.

• Investigative Magnetic Resonance Imaging
• /
• 제24권3호
• /
• pp.123-131
• /
• 2020

Purpose: Joint label fusion (JLF) is a popular multi-atlas-based segmentation algorithm, which compensates for dependent errors that may exist between atlases. However, in order to get good segmentation results, it is very important to set the several free parameters of the algorithm to optimal values. In this study, we first investigate the feasibility of a JLF algorithm for prostate segmentation in MR images, and then suggest the optimal set of parameters for the automatic prostate segmentation by validating the results of each parameter combination. Materials and Methods: We acquired T2-weighted prostate MR images from 20 normal heathy volunteers and did a series of cross validations for every set of parameters of JLF. In each case, the atlases were rigidly registered for the target image. Then, we calculated their voting weights for label fusion from each combination of JLF's parameters (r_pxy, r_pz, r_sxy, r_sz, β). We evaluated the segmentation performances by five validation metrics of the Prostate MR Image Segmentation challenge. Results: As the number of voxels participating in the voting weight calculation and the number of referenced atlases is increased, the overall segmentation performance is gradually improved. The JLF algorithm showed the best results for dice similarity coefficient, 0.8495 ± 0.0392; relative volume difference, 15.2353 ± 17.2350; absolute relative volume difference, 18.8710 ± 13.1546; 95% Hausdorff distance, 7.2366 ± 1.8502; and average boundary distance, 2.2107 ± 0.4972; in parameters of r_pxy = 10, r_pz = 1, r_sxy = 3, r_sz = 1, and β = 3. Conclusion: The evaluated results showed the feasibility of the JLF algorithm for automatic segmentation of prostate MRI. This empirical analysis of segmentation results by label fusion allows for the appropriate setting of parameters.