• 반도체디스플레이기술학회지
• /
• 제19권2호
• /
• pp.88-91
• /
• 2020

Image segmentation is the task of partitioning an image into multiple sets of pixels based on some characteristics. The objective is to simplify the image into a representation that is more meaningful and easier to analyze. In this paper, we apply deep-learning to pre-train the learning model, and implement an algorithm that performs image segmentation in real time by extracting frames for the stream input from the Android device. Based on the open source of DeepLab-v3+ implemented in Tensorflow, some convolution filters are modified to improve real-time operation on the Android platform.

• 정보처리학회논문지:컴퓨터 및 통신 시스템
• /
• 제12권8호
• /
• pp.243-252
• /
• 2023

위성 이미지는 토지 표면 조사에서 매우 중요하다. 따라서 위성에서 지상국으로 이미지를 전송하기 위해 다양한 방법을 사용하고 있다. 그러나 전송 시스템의 품질 저하로 인해 이미지는 왜곡에 취약하고 올바른 데이터를 제공하지 못하고 있다. 그러한 이미지의 세그먼트 결과는 토지 표면 데이터를 올바르게 분류할 수 없다. 본 논문에서는 위성영상에 대한 자동인코더 기반의 영상 전처리 방법을 제안한다. 실험결과 사전 향상 기술을 사용하여 세그멘테이션 결과도 크게 향상될 수 있음을 보여주었다. 또한 본 논문에서 적용한 항공 이미지 향상기법은 토지 자원의 정확한 평가에 이바지할 수 있음을 확인하였다.

• 한국멀티미디어학회논문지
• /
• 제25권5호
• /
• pp.685-694
• /
• 2022

The goal of few-shot semantic segmentation is to build a network that quickly adapts to novel classes with extreme data shortage regimes. Most existing few-shot segmentation methods leverage single or multiple prototypes from extracted support features. Although there have been promising results for natural images, these methods are not directly applicable to the aerial image domain. A key factor in few-shot segmentation on aerial images is to effectively exploit information that is robust against extreme changes in background and object scales. In this paper, we propose a Mask-Guided Attention module to extract more comprehensive support features for few-shot segmentation in aerial images. Taking advantage of the support ground-truth masks, the area correlated to the foreground object is highlighted and enables the support encoder to extract comprehensive support features with contextual information. To facilitate reproducible studies of the task of few-shot semantic segmentation in aerial images, we further present the few-shot segmentation benchmark iSAID-, which is constructed from a large-scale iSAID dataset. Extensive experimental results including comparisons with the state-of-the-art methods and ablation studies demonstrate the effectiveness of the proposed method.

• 한국방송∙미디어공학회:학술대회논문집
• /
• 한국방송공학회 1999년도 KOBA 방송기술 워크샵 KOBA Broadcasting Technology Workshop
• /
• pp.159-164
• /
• 1999

Homogeneous but distinct visual objects having low-contrast boundaries are usually merged in most of the segmentation algorithms. To alleviate this problem, an efficient image segmentation algorithm based on a bottom-up approach is proposed by using spatial domain information only. For initial image segmentation, we adopt an efficient marker extraction algorithm conforming to the human visual system. Then, two region-merging algorithms are successively applied so that homogeneous visual objects can be represented as simple as possible without destroying low-contrast real boundaries among them. The resultant segmentation describes homogeneous visual objects with few regions while preserving semantic object shapes well. Finally, a size-based region decision procedure may be applied to represent complex visual objects simpler, if their precise semantic contents are not necessary. Experimental results show that the proposed image segmentation algorithm represents homogeneous visual objects with a few regions and describes complex visual objects with a marginal number of regions with well-preserved semantic object shapes.

• 인터넷정보학회논문지
• /
• 제20권3호
• /
• pp.33-41
• /
• 2019

본 논문에서는 실내 공간 이미지의 의미론적 영상 분할을 위해 배경과 물체로 재설계된 클래스를 학습하는 방법을 제안한다. 의미론적 영상 분할은 이미지의 벽이나 침대 등 의미를 갖는 부분들을 픽셀 단위로 나누는 기술이다. 기존 의미론적 영상 분할에 대한 연구들은 신경망을 통해 이미지의 다양한 객체 클래스들을 학습하는 방법들을 제시해왔고, 긴 학습 시간에 비해 정확도가 부족하다는 문제가 지적되었다. 그러나 물체와 배경을 분리하는 문제에서는, 다양한 객체 클래스를 학습할 필요가 없다. 따라서 우리는 이 문제에 집중해, 클래스를 단순화 후에 학습하는 방법을 제안한다. 학습 방법의 실험 결과로 기존 방법들보다 정확도가 약 5~12% 정도 높았다. 그리고 같은 환경에서 클래스를 달리 구성했을 때 학습 시간이 약 14 ~ 60분 정도 단축됐으며, 이에 따라 물체와 배경을 분리하는 문제에 대해 제안하는 방법이 효율적임을 보인다.

• 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.

• 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.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제17권12호
• /
• pp.3364-3382
• /
• 2023

Remote sensing image segmentation plays an important role in realizing intelligent city construction. The current mainstream segmentation networks effectively improve the segmentation effect of remote sensing images by deeply mining the rich texture and semantic features of images. But there are still some problems such as rough results of small target region segmentation and poor edge contour segmentation. To overcome these three challenges, we propose an improved semantic segmentation model, referred to as MRU-Net, which adopts the U-Net architecture as its backbone. Firstly, the convolutional layer is replaced by BasicBlock structure in U-Net network to extract features, then the activation function is replaced to reduce the computational load of model in the network. Secondly, a hybrid multi-scale recognition module is added in the encoder to improve the accuracy of image segmentation of small targets and edge parts. Finally, test on Massachusetts Buildings Dataset and WHU Dataset the experimental results show that compared with the original network the ACC, mIoU and F1 value are improved, and the imposed network shows good robustness and portability in different datasets.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제17권9호
• /
• pp.2458-2482
• /
• 2023

Medical image segmentation techniques based on convolution neural networks indulge in feature extraction triggering redundancy of parameters and unsatisfactory target localization, which outcomes in less accurate segmentation results to assist doctors in diagnosis. In this paper, we propose a multi-level semantic-rich encoding-decoding network, which consists of a Pooling-Conv-Former (PCFormer) module and a Cbam-Dilated-Transformer (CDT) module. In the PCFormer module, it is used to tackle the issue of parameter explosion in the conservative transformer and to compensate for the feature loss in the down-sampling process. In the CDT module, the Cbam attention module is adopted to highlight the feature regions by blending the intersection of attention mechanisms implicitly, and the Dilated convolution-Concat (DCC) module is designed as a parallel concatenation of multiple atrous convolution blocks to display the expanded perceptual field explicitly. In addition, MultiHead Attention-DwConv-Transformer (MDTransformer) module is utilized to evidently distinguish the target region from the background region. Extensive experiments on medical image segmentation from Glas, SIIM-ACR, ISIC and LGG demonstrated that our proposed network outperforms existing advanced methods in terms of both objective evaluation and subjective visual performance.

• 한국멀티미디어학회논문지
• /
• 제19권3호
• /
• pp.531-538
• /
• 2016

In this paper, we propose a novel post-processing method of semantic segmentation from indoor scenes with RGBD inputs. For accurate segmentation, various post-processing methods such as superpixel from color edges or Conditional Random Field (CRF) method considering neighborhood connectivity have been used, but these methods are not efficient due to high complexity and computational cost. To solve this problem, we maximize the efficiency of post processing by using depth superpixel extracted from disparity image to handle object silhouette. Our experimental results show reasonable performances compared to previous methods in the post processing of semantic segmentation.