• 한국컴퓨터정보학회:학술대회논문집
• /
• 한국컴퓨터정보학회 2021년도 제63차 동계학술대회논문집 29권1호
• /
• pp.37-39
• /
• 2021

본 논문에서는 간단한 아두이노 모듈을 이용하여 MATLAB에서 실행되는 semantic segmentation을 조작해보았다. 기존에는 단순히 센서를 통해 감지하거나, 입력을 받아 출력하는 등의 수동적으로 아두이노 모듈을 활용하였다. 하지만 직접 아두이노와 semantic segmentation을 연결하여 semantic segmentation 결과를 조작하여, 아두이노를 인공지능과 결합하여 능동적으로 사용할 수 있게 하였다.

• 한국멀티미디어학회논문지
• /
• 제22권9호
• /
• pp.1000-1010
• /
• 2019

Image semantic segmentation and dehazing are key tasks in the computer vision. In recent years, researches in both tasks have achieved substantial improvements in performance with the development of Convolutional Neural Network (CNN). However, most of the previous works for semantic segmentation assume the images are captured in clear weather and show degraded performance under hazy images with low contrast and faded color. Meanwhile, dehazing aims to recover clear image given observed hazy image, which is an ill-posed problem and can be alleviated with additional information about the image. In this work, we propose a deep multi-task network for simultaneous semantic segmentation and dehazing. The proposed network takes single haze image as input and predicts dense semantic segmentation map and clear image. The visual information getting refined during the dehazing process can help the recognition task of semantic segmentation. On the other hand, semantic features obtained during the semantic segmentation process can provide cues for color priors for objects, which can help dehazing process. Experimental results demonstrate the effectiveness of the proposed multi-task approach, showing improved performance compared to the separate networks.

• 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.

• 디지털융복합연구
• /
• 제19권6호
• /
• pp.251-258
• /
• 2021

본 논문에서는 U-Net 기반의 semantic segmentation 방법에서 정확도를 향상시키기 위해 residual learning을 활용한 인코더-디코더 구조의 모델을 제안하였다. U-Net은 딥러닝 기반의 semantic segmentation 방법이며 자율주행 자동차, 의료 영상 분석과 같은 응용 분야에서 주로 사용된다. 기존 U-Net은 인코더의 얕은 구조로 인해 특징 압축 과정에서 손실이 발생한다. 특징 손실은 객체의 클래스 분류에 필요한 context 정보 부족을 초래하고 segmentation 정확도를 감소시키는 문제가 있다. 이를 개선하기 위해 제안하는 방법은 기존 U-Net에 특징 손실과 기울기 소실 문제를 방지하는데 효과적인 residual learning을 활용한 인코더를 통해 context 정보를 효율적으로 추출하였다. 또한, 인코더에서 down-sampling 연산을 줄여 특징맵에 포함된 공간 정보의 손실을 개선하였다. 제안하는 방법은 Cityscapes 데이터셋 실험에서 기존 U-Net 방법에 비해 segmentation 결과가 약 12% 향상되었다.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 1998년도 하계종합학술대회논문집
• /
• pp.661-664
• /
• 1998

Since the region segmentation at high resolution contains most of viable semantic object contours in an image, the bottom-up approach for image segmentation is appropriate for the application such as MPEG-4 which needs to preserve semantic object contours. However, the conventioal region merging methods, that follow the region segmentation, have poor performance in keeping low-contrast semantic object contours. In this paper, we propose an image segmentation algorithm based on classified region merging. The algorithm pre-segments an image with a large number of small regions, and also classifies it into several classes having similar gradient characteristics. Then regions only in the same class are merged according to the boundary weakness or statisticsal similarity. The simulation result shows that the proposed image segmentation preserves semantic object contours very well even with a small number of regions.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2020년도 춘계학술발표대회
• /
• pp.468-471
• /
• 2020

본 논문은 ESRGAN(Enhanced Super Resolution GAN)과 Semantic Soft Segmentation을 이용한 객체 분할의 성능 개선에 관한 것이다. 본 논문의 연구진이 이미 제안한 Mask R-CNN과 Semantic Soft Segmentation을 이용한 객체 분할 방법은 전반적으로 객체 분할 성능이 양호한 반면, 객체의 크기가 상대적으로 작으면 분할 성능이 저조해지는 문제점이 있었다. 본 논문은 이러한 문제점을 해결하기 위한 것으로, Mask R-CNN을 통해 검출된 객체의 크기가 일정 기준치 이하인 경우, ESRGAN을 통해 초해상화를 수행한 후, Semantic Soft Segmentation을 수행함으로써 소형 객체의 분할 성능을 개선함에 그 목적이 있다. 제안된 방법에 따르면, 기존의 방볍에 비해 크기가 작은 객체의 분할 특성을 좀 더 효과적으로 개선할 수 있음을 확인할 수 있었다.

• Journal of Information Processing Systems
• /
• 제17권5호
• /
• pp.892-904
• /
• 2021

An image semantic segmentation model is proposed based on improved ENet network in order to achieve the low accuracy of image semantic segmentation in complex environment. Firstly, this paper performs pruning and convolution optimization operations on the ENet network. That is, the network structure is reasonably adjusted for better results in image segmentation by reducing the convolution operation in the decoder and proposing the bottleneck convolution structure. Squeeze-and-excitation (SE) module is then integrated into the optimized ENet network. Small-scale targets see improvement in segmentation accuracy via automatic learning of the importance of each feature channel. Finally, the experiment was verified on the public dataset. This method outperforms the existing comparison methods in mean pixel accuracy (MPA) and mean intersection over union (MIOU) values. And in a short running time, the accuracy of the segmentation and the efficiency of the operation are guaranteed.

• 한국멀티미디어학회논문지
• /
• 제24권1호
• /
• pp.1-12
• /
• 2021

In this paper, we present a new architecture for semantic segmentation. Semantic segmentation aims at a pixel-wise classification which is important to fully understand images. Previous semantic segmentation networks use features of multi-layers in the encoder to predict final results. However, they do not contain various receptive fields in the multi-layers features, which easily lead to inaccurate results for boundaries between different classes and small objects. To solve this problem, we propose a multi-path feature fusion module that allows for features of each layers to contain various receptive fields by use of a set of dilated convolutions with different dilatation rates. Various experiments demonstrate that our method outperforms previous methods in terms of mean intersection over unit (mIoU).

• 한국군사과학기술학회지
• /
• 제25권6호
• /
• pp.606-616
• /
• 2022

Semantic segmentation in autonomous driving for unstructured environments is challenging due to the presence of uneven terrains, unstructured class boundaries, irregular features and strong textures. Current off-road datasets exhibit difficulties like class imbalance and understanding of varying environmental topography. To overcome these issues, we propose a deep learning framework for semantic segmentation that involves a pooled class semantic segmentation with five classes. The evaluation of the framework is carried out on two off-road driving datasets, RUGD and TAS500. The results show that our proposed method achieves high accuracy and real-time performance.

• ETRI Journal
• /
• 제45권5호
• /
• pp.822-835
• /
• 2023

Recent semantic segmentation frameworks usually combine low-level and high-level context information to achieve improved performance. In addition, postlevel context information is also considered. In this study, we present a Context ReFinement Network (CRFNet) and its training method to improve the semantic predictions of segmentation models of the encoder-decoder structure. Our study is based on postprocessing, which directly considers the relationship between spatially neighboring pixels of a label map, such as Markov and conditional random fields. CRFNet comprises two modules: a refiner and a combiner that, respectively, refine the context information from the output features of the conventional semantic segmentation network model and combine the refined features with the intermediate features from the decoding process of the segmentation model to produce the final output. To train CRFNet to refine the semantic predictions more accurately, we proposed a sequential training scheme. Using various backbone networks (ENet, ERFNet, and HyperSeg), we extensively evaluated our model on three large-scale, real-world datasets to demonstrate the effectiveness of our approach.