http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
MRU-Net: A remote sensing image segmentation network for enhanced edge contour Detection
Jing Han,Weiyu Wang,Yuqi Lin,Xueqiang LYU 한국인터넷정보학회 2023 KSII Transactions on Internet and Information Syst Vol.17 No.12
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.
Attention-based for Multiscale Fusion Underwater Image Enhancement
Zhixiong Huang,Jinjiang Li,Zhen Hua 한국인터넷정보학회 2022 KSII Transactions on Internet and Information Syst Vol.16 No.2
Underwater images often suffer from color distortion, blurring and low contrast, which is caused by the propagation of light in the underwater environment being affected by the two processes: absorption and scattering. To cope with the poor quality of underwater images, this paper proposes a multiscale fusion underwater image enhancement method based on channel attention mechanism and local binary pattern (LBP). The network consists of three modules: feature aggregation, image reconstruction and LBP enhancement. The feature aggregation module aggregates feature information at different scales of the image, and the image reconstruction module restores the output features to high-quality underwater images. The network also introduces channel attention mechanism to make the network pay more attention to the channels containing important information. The detail information is protected by real-time superposition with feature information. Experimental results demonstrate that the method in this paper produces results with correct colors and complete details, and outperforms existing methods in quantitative metrics.
LIU QIAN,Zhang Zhiyao,GUO PENG,WANG YIFAN,Liang Junxin 한국CDE학회 2024 Journal of computational design and engineering Vol.11 No.1
Predicting the remaining useful life (RUL) of the aircraft engine based on historical data plays a pivotal role in formulating maintenance strategies and mitigating the risk of critical failures. None the less, attaining precise RUL predictions often encounters challenges due to the scarcity of historical condition monitoring data. This paper introduces a multiscale deep transfer learning framework via integrating domain adaptation principles. The framework encompasses three integral components: a feature extraction module, an encoding module, and an RUL prediction module. During pre-training phase, the framework leverages a multiscale convolutional neural network to extract distinctive features from data across varying scales. The ensuing parameter transfer adopts a domain adaptation strategy centered around maximum mean discrepancy. This method efficiently facilitates the acquisition of domain-invariant features from the source and target domains. The refined domain adaptation Transformer-based multiscale convolutional neural network model exhibits enhanced suitability for predicting RUL in the target domain under the condition of limited samples. Experiments on the C-MAPSS dataset have shown that the proposed method significantly outperforms state-of-the-art methods.
Automatic Segmentation Method of Phalange Regions Based on Residual U-Net and MSGVF Snakes
Kohei KAWAGOE,Kazuhiro HATANO,Seiichi MURAKAMI,Huimin LU,Hyoungseop KIM,Takatoshi AOKI 제어로봇시스템학회 2019 제어로봇시스템학회 국제학술대회 논문집 Vol.2019 No.10
Bone diseases include rheumatoid arthritis and osteoporosis. Although visual screening using computed radiography (CR) images is an effective method for diagnosing osteoporosis, there are some similar diseases that exhibit low bone mass status. To this end, we aim to develop a computer-aided diagnostic (CAD) system to support the automatic diagnosis of osteoporosis from CR images. In this paper, we use convolutional neural network (CNN) and multiscale gradient vector flow snakes (MSGVF Snakes) algorithms to segment each finger bone regions from the CR image. The proposed method is applied to 15 cases, 92.95 [%] of the true positive rates, 2.21 [%] of the false positive rates, 7.05 [%] of the false negative rates are obtained respectively.
Zhao Yao,Zhao Zhibo,Lin Shunfu,Yang Fan,Li Dongdong 대한전기학회 2024 Journal of Electrical Engineering & Technology Vol.19 No.4
Variable fl ux reluctance machines can be adopted in the fi eld of built-in starter generator for aero-engine. It is critical to achieve reliable protection of the power generation system in harsh environments. The single signal makes it diffi cult to identify the initial fault accurately due to the little impact by a small-turn short-circuit on the electromagnetic fi eld. Thus, this paper proposes a novel framework for multi-source information fusion fault diagnosis in VFRMs by extracted current signals manually and vibration signals automatically. Firstly, the armature winding short-circuit fault characteristics of the current and vibration signals in the VFRM are analyzed. Secondly, a multi-source fusion framework based on a kernel extreme learning machine combined with a multiscale convolutional neural network is presented according to the structural characteristics of the VFRM. Then, the Dempster-Shafer evidence theory is applied for achieving decision-level fusion. Finally, a four-phase 8/10-pole VFRM prototype with diff erent AWSC faults is used to validate the proposed method. The results indicate that the fault diagnosis rate of the proposed method is 97.28%, which is 10.37% and 3.7% higher than vibration and current signals, respectively. It is more reliable and eff ective to identify diff erent AWSC faults accurately in the early stages.