• 한국멀티미디어학회논문지
• /
• 제25권11호
• /
• pp.1582-1590
• /
• 2022

Due to the situation of the widespread of the coronavirus, which causes the problem of lack of face image data occluded by masks at recent time, in order to solve the related problems, this paper proposes a method to generate face images with masks using a combination of generative adversarial networks and spatial transformation networks based on CNN model. The system we proposed in this paper is based on the GAN, combined with multi-scale convolution kernels to extract features at different details of the human face images, and used Wasserstein divergence as the measure of the distance between real samples and synthetic samples in order to optimize Generator performance. Experiments show that the proposed method can effectively put masks on face images with high efficiency and fast reaction time and the synthesized human face images are pretty natural and real.

• Journal of Information Processing Systems
• /
• 제17권2호
• /
• pp.385-398
• /
• 2021

The complexity of deep learning models affects the real-time performance of gesture recognition, thereby limiting the application of gesture recognition algorithms in actual scenarios. Hence, a residual learning neural network based on a deep convolutional neural network is proposed. First, small convolution kernels are used to extract the local details of gesture images. Subsequently, a shallow residual structure is built to share weights, thereby avoiding gradient disappearance or gradient explosion as the network layer deepens; consequently, the difficulty of model optimisation is simplified. Additional convolutional neural networks are used to accelerate the refinement of deep abstract features based on the spatial importance of the gesture feature distribution. Finally, a fully connected cascade softmax classifier is used to complete the gesture recognition. Compared with the dense connection multiplexing feature information network, the proposed algorithm is optimised in feature multiplexing to avoid performance fluctuations caused by feature redundancy. Experimental results from the ISOGD gesture dataset and Gesture dataset prove that the proposed algorithm affords a fast convergence speed and high accuracy.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제16권11호
• /
• pp.3493-3506
• /
• 2022

In the field of scene segmentation, the precise segmentation of object boundaries in sports movement scene images is a great challenge. The geometric information and spatial information of the image are very important, but in many models, they are usually easy to be lost, which has a big influence on the performance of the model. To alleviate this problem, a parallel dense dilated convolution merging Network (termed PDDCM-Net) was proposed. The proposed PDDCMNet consists of a feature extractor, parallel dilated convolutions, and dense dilated convolutions merged with different dilation rates. We utilize different combinations of dilated convolutions that expand the receptive field of the model with fewer parameters than other advanced methods. Importantly, PDDCM-Net fuses both low-level and high-level information, in effect alleviating the problem of accurately segmenting the edge of the object and positioning the object position accurately. Experimental results validate that the proposed PDDCM-Net achieves a great improvement compared to several representative models on the COCO-Stuff data set.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제17권3호
• /
• pp.861-880
• /
• 2023

Semantic segmentation of road scene is the key technology of autonomous driving, and the improvement of convolutional neural network architecture promotes the improvement of model segmentation performance. The existing convolutional neural network has the simplification of learning knowledge and the complexity of the model. To address this issue, we proposed a road scene semantic segmentation algorithm based on multi-task collaborative learning. Firstly, a depthwise separable convolution atrous spatial pyramid pooling is proposed to reduce model complexity. Secondly, a collaborative learning framework is proposed involved with saliency detection, and the joint loss function is defined using homoscedastic uncertainty to meet the new learning model. Experiments are conducted on the road and nature scenes datasets. The proposed method achieves 70.94% and 64.90% mIoU on Cityscapes and PASCAL VOC 2012 datasets, respectively. Qualitatively, Compared to methods with excellent performance, the method proposed in this paper has significant advantages in the segmentation of fine targets and boundaries.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2022년도 추계학술발표대회
• /
• pp.399-401
• /
• 2022

POI (Point-of-Interest) 추천은 다양한 위치 기반 서비스에서 중요한 역할을 있다. 기존 연구에서는 사용자의 모바일 선호도를 모델링하기 위해 과거의 체크인의 공간-시간적 관계를 추출한다. 그러나 사용자 궤적에 숨겨진 개인 방문 경향을 반영할 수 있는 structured feature 는 잘 활용되지 않는다. 이 논문에서는 궤적 그래프를 결합한 시공간 인식 attention 네트워크를 제안한다. 개인의 선호도가 시간이 지남에 따라 변할 수 있다는 점을 고려하면 Dynamic GCN (Graph Convolution Network) 모듈은 POI 들의 공간적 상관관계를 동적으로 집계할 수 있다. LBSN (Location-Based Social Networks) 데이터 세트에서 검증된 새 모델은 기존 모델보다 약 9.0% 성능이 뛰어나다.

• 한국조경학회지
• /
• 제33권4호
• /
• pp.71-78
• /
• 2005

The purpose of this study is the practical application of landscape ecological indices to establishment of eco-village planning methodology. Planning an eco-village has to be carried out in the boundary of a small watershed that is defined by homogeneous ecological character. Because the small watershed is a landscape unit it can have unique ecological character. On this viewpoint, the spatial structure is analyzed by the ecological attributes of form, distribution arrangement and composition of the sub-landscape units. Among all of the sub-landscape units, a green tract of land is the main subject of the analyzing entity. Woodland or forest as a green tract of land is a source of biological species and materials. Therefore the ecological attributes of green patches are especially analyzed by landscape ecological indices. The selected landscape ecological indices are elongation, lobes, interior area ratio, convolution of perimeter and proximity of the green patches. These indices represent the state of ecological conditions and they will be the evaluation factors of the landscape ecological planning. These frameworks for landscape ecological planning apply to Obok and Ganggeum villages in Wanju-gun, Korea. A proposed planning was evaluated by the selected landscape ecological indices. Among the selected landscape ecological indices of green patches, perimeter convolution and proximity were increased. It means that the ecological condition of peen paches will be mon sound and green areas of the village will be expanded naturally. In addition to this connectivities among green patches will also be improved.

• 한국음향학회지
• /
• 제39권4호
• /
• pp.279-285
• /
• 2020

항행 선박의 시·공간적 모니터링 기술 연구는 연안 해양공간에서 해양 생태계 보호 및 효율적인 관리를 위해서 중요하다. 본 연구에서는 실험해역에서 측정된 선박 소음 특징인 광대역 줄무늬 패턴 자료에 인공지능 기술을 적용하여 항행하는 선박을 자동 탐지하는 연구를 수행하였다. 소음 스펙트럼 이미지와 선박의 항행정보를 수집하기 위한 해상시험은 2016년 7월 15일부터 26일까지 제주 남부 해역에서 실시되었고, 컨볼루션 신경망 모델은 수집된 이미지를 기반으로 학습, 교차검증 과정을 거쳐 최적화되었다. 선박 소음 자동 탐지 기법의 성능은 정밀도(0.936), 재현율(0.830), 평균 정밀도(0.824) 그리고 정확도(0.949)로 평가되었다. 결론적으로 인공지능 기법을 활용하여 선박 소음의 자동 탐지 가능성을 확인하였다. 본 연구의 결과로부터 성능을 향상시킬 수 있는 방안 및 향후 연구에 대하여 제안하였다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제17권8호
• /
• pp.2068-2082
• /
• 2023

With the rapid development of deep learning, Depth Map Super-Resolution (DMSR) method has achieved more advanced performances. However, when the upsampling rate is very large, it is difficult to capture the structural consistency between color features and depth features by these DMSR methods. Therefore, we propose a color-image guided DMSR method based on iterative depth feature enhancement. Considering the feature difference between high-quality color features and low-quality depth features, we propose to decompose the depth features into High-Frequency (HF) and Low-Frequency (LF) components. Due to structural homogeneity of depth HF components and HF color features, only HF color features are used to enhance the depth HF features without using the LF color features. Before the HF and LF depth feature decomposition, the LF component of the previous depth decomposition and the updated HF component are combined together. After decomposing and reorganizing recursively-updated features, we combine all the depth LF features with the final updated depth HF features to obtain the enhanced-depth features. Next, the enhanced-depth features are input into the multistage depth map fusion reconstruction block, in which the cross enhancement module is introduced into the reconstruction block to fully mine the spatial correlation of depth map by interleaving various features between different convolution groups. Experimental results can show that the two objective assessments of root mean square error and mean absolute deviation of the proposed method are superior to those of many latest DMSR methods.

• 한국수자원학회논문집
• /
• 제36권6호
• /
• pp.961-969
• /
• 2003

토양수분 분포의 시공간적인 예측을 위하여 유사 동력학 상태의 습윤지수 계산과정을 정리하였고, 우량 자료를 회귀적분한 동력학적 습윤지수의 계산 알고리즘을 개발하였다. 설마천 유역의 수치고도 모형과 2년간의 우량자료를 활용하여 동력학적 상태의 습윤지수의 시ㆍ공간적인 거동을 분석하였다. 공간적인 거동은 동력학적인 습윤지수가 유사 동력학적 상태나 정적인 습윤지수와 비교하여 흐름분산 특성이 강조된 분포특성을 보여주었다. 통계적인 특성으로는 시간이 경과함에 따라 유사동력학적 습윤지수나 동력학적 습윤지수 모두 정상상태 습윤지수에 근접하나, 동력학적 습윤지수의 경우 두 개의 상이한 분포특성이 나타났다.

• 전기전자학회논문지
• /
• 제24권4호
• /
• pp.1141-1147
• /
• 2020

말벌 종은 모양이 매우 유사하기 때문에 비전문가가 분류하기 어렵고, 객체의 크기가 작고 빠르게 움직이기 때문에 실시간으로 탐지하여 종을 분류하는 것은 더욱 어렵다. 본 논문에서는 바운딩 박스를 이용한 딥러닝 알고리즘을 기반으로 말벌 종을 실시간으로 분류하는 시스템을 개발하였다. 훈련 영상의 레이블링 작업 시 바운딩 박스 안에 포함되는 배경 영역을 최소화하기 위하여 말벌의 머리와 몸통 부분만을 선택하는 방법을 제안한다. 또한 실시간으로 말벌을 탐지하고 그 종을 분류할 수 있는 최선의 알고리즘을 찾기 위하여 기존의 바운딩 박스 기반 객체 인식 알고리즘들을 실험을 통하여 비교한다. 실험 결과 컨볼루션 레이어의 활성함수로 mish 함수를 적용하고, 객체 검출 블록 전에 공간집중모듈(Spatial Attention Module, SAM)을 적용한 YOLOv4 모델을 사용하여 말벌 영상을 테스트한 경우 평균 97.89%의 정밀도(Precision)와 98.69%의 재현율(Recall)을 나타내었다.