• Korean Journal of Remote Sensing
• /
• v.37 no.5_1
• /
• pp.1149-1161
• /
• 2021

With a trend of the utilization of computer vision for satellite images, cloud detection using deep learning also attracts attention recently. In this study, we conducted a U-Net cloud detection modeling using SPARCS (Spatial Procedures for Automated Removal of Cloud and Shadow) Cloud Dataset with the image data augmentation and carried out 10-fold cross-validation for an objective assessment of the model. Asthe result of the blind test for 1800 datasets with 512 by 512 pixels, relatively high performance with the accuracy of 0.821, the precision of 0.847, the recall of 0.821, the F1-score of 0.831, and the IoU (Intersection over Union) of 0.723. Although 14.5% of actual cloud shadows were misclassified as land, and 19.7% of actual clouds were misidentified as land, this can be overcome by increasing the quality and quantity of label datasets. Moreover, a state-of-the-art DeepLab V3+ model and the NAS (Neural Architecture Search) optimization technique can help the cloud detection for CAS500 (Compact Advanced Satellite 500) in South Korea.

• The Journal of the Acoustical Society of Korea
• /
• v.42 no.2
• /
• pp.94-101
• /
• 2023

A deep neural network composed of encoders and decoders, such as U-Net, used for speech enhancement, concatenates the encoder to the decoder through skip-connection. Skip-connection helps reconstruct the enhanced spectrum and complement the lost information. The features of the encoder and the decoder connected by the skip-connection are incompatible with each other. In this paper, for complex-valued spectrum based speech enhancement, Self-Attention (SA) method is applied to skip-connection to transform the feature of encoder to be compatible with the features of decoder. SA is a technique in which when generating an output sequence in a sequence-to-sequence tasks the weighted average of input is used to put attention on subsets of input, showing that noise can be effectively eliminated by being applied in speech enhancement. The three models using encoder and decoder features to apply SA to skip-connection are studied. As experimental results using TIMIT database, the proposed methods show improvements in all evaluation metrics compared to the Deep Complex U-Net (DCUNET) with skip-connection only.

• International Journal of Computer Science & Network Security
• /
• v.22 no.3
• /
• pp.273-275
• /
• 2022

Deep Learning is used nowadays in Nuclei segmentation. While recent developments in theory and open-source software have made these tools easier to implement, expert knowledge is still required to choose the exemplary model architecture and training setup. We compare two popular segmentation frameworks, U-Net and Mask-RCNN, in the nuclei segmentation task and find that they have different strengths and failures. we compared both models aiming for the best nuclei segmentation performance. Experimental Results of Nuclei Medical Images Segmentation using U-NET algorithm Outperform Mask R-CNN Algorithm.

• Journal of Korea Multimedia Society
• /
• v.24 no.10
• /
• pp.1319-1325
• /
• 2021

It is important to remove fog for accurate object recognition and detection during preprocessing because images taken in foggy adverse weather suffer from poor quality of images due to scattering and absorption of light, resulting in poor performance of various vision-based applications. This paper proposes an end-to-end deep learning-based single image de-fogging method using U-Net architecture. The loss function used in the algorithm is a loss function based on Mahalanobis distance with fog features, which solves the problem of domain shifts, and demonstrates superior performance by comparing qualitative and quantitative numerical evaluations with conventional methods. We also design it to generate fog through the VGG19 loss function and use it as the next training dataset.

• Smart Media Journal
• /
• v.9 no.1
• /
• pp.16-22
• /
• 2020

In this study, a neural network method performing both Detection and Classification of diseases and insects in paprika is proposed with Multi-Tasking U-net. Paprika on farms does not have a wide variety of diseases in this study, only two classes such as powdery mildew and mite, which occur relatively frequently are made as the targets. Aiming to this, a U-net is used as a backbone network, and the last layers of the encoder and the decoder of the U-net are utilized for classification and segmentation, respectively. As the result, the encoder of the U-net is shared for both of detection and classification. The training data are composed of 680 normal leaves, 450 mite-damaged leaves, and 370 powdery mildews. The test data are 130 normal leaves, 100 mite-damaged leaves, and 90 powdery mildews. Its test results shows 89% of recognition accuracy.

• Journal of the Korea Society of Computer and Information
• /
• v.25 no.10
• /
• pp.15-22
• /
• 2020

In this study, we propose an improvement method that can create U-Net model which detect fine concrete cracks by applying a weighted loss function. Because cracks in concrete are a factor that threatens safety, it is important to periodically check the condition and take prompt initial measures. However, currently, the visual inspection is mainly used in which the inspector directly inspects and evaluates with naked eyes. This has limitations not only in terms of accuracy, but also in terms of cost, time and safety. Accordingly, technologies using deep learning is being researched so that minute cracks generated in concrete structures can be detected quickly and accurately. As a result of attempting crack detection using U-Net in this study, it was confirmed that it could not detect minute cracks. Accordingly, as a result of verifying the performance of the model trained by applying the suggested weighted loss function, a highly reliable value (Accuracy) of 99% or higher and a harmonic average (F1_Score) of 89% to 92% was derived. The performance of the learning improvement plan was verified through the results of accurately and clearly detecting cracks.

• Journal of KIISE
• /
• v.45 no.1
• /
• pp.94-98
• /
• 2018

We propose Wide Inception ResNet (WIR Net) an optimized neural network architecture as a real-time semantic segmentation method for autonomous driving. The neural network architecture consists of an encoder that extracts features by applying a residual connection and inception module, and a decoder that increases the resolution by using transposed convolution and a low layer feature map. We also improved the performance by applying an ELU activation function and optimized the neural network by reducing the number of layers and increasing the number of filters. The performance evaluations used an NVIDIA Geforce GTX 1080 and TX1 boards to assess the class and category IoU for cityscapes data in the driving environment. The experimental results show that the accuracy of class IoU 53.4, category IoU 81.8 and the execution speed of $640{\times}360$, $720{\times}480$ resolution image processing 17.8fps and 13.0fps on TX1 board.

• Korean Journal of Remote Sensing
• /
• v.36 no.6_2
• /
• pp.1579-1590
• /
• 2020

In this paper, spatially-adaptive denormalization (SPADE) based U-Net is proposed to detect changes by using high-resolution satellite images. The proposed network is to preserve spatial information using SPADE. Change detection methods using high-resolution satellite images can be used to resolve various urban problems such as city planning and forecasting. For using pixel-based change detection, which is a conventional method such as Iteratively Reweighted-Multivariate Alteration Detection (IR-MAD), unchanged areas will be detected as changing areas because changes in pixels are sensitive to the state of the environment such as seasonal changes between images. Therefore, in this paper, to precisely detect the changes of the objects that consist of the city in time-series satellite images, the semantic spatial objects that consist of the city are defined, extracted through deep learning based image segmentation, and then analyzed the changes between areas to carry out change detection. The semantic objects for analyzing changes were defined as six classes: building, road, farmland, vinyl house, forest area, and waterside area. Each network model learned with KOMPSAT-3A satellite images performs a change detection for the time-series KOMPSAT-3 satellite images. For objective assessments for change detection, we use F1-score, kappa. We found that the proposed method gives a better performance compared to U-Net and UNet++ by achieving an average F1-score of 0.77, kappa of 77.29.

• Ecology and Resilient Infrastructure
• /
• v.8 no.4
• /
• pp.253-265
• /
• 2021

In this study, crop cultivation filed was extracted by using Unmanned Aerial Vehicle (UAV) imagery and deep learning models to overcome the limitations of satellite imagery and to contribute to the technological development of understanding the status of crop cultivation field. The study area was set around Chungbuk Goesan-gun Gammul-myeon Yidam-li and orthogonal images of the area were acquired by using UAV images. In addition, study data for deep learning models was collected by using Farm Map that modified by fieldwork. The Attention U-Net was used as a deep learning model to extract feature of UAV in this study. After the model learning process, the performance evaluation of the model for corn cultivation extraction was performed using non-learning data. We present the model's performance using precision, recall, and F1-score; the metrics show 0.94, 0.96, and 0.92, respectively. This study proved that the method is an effective methodology of extracting corn cultivation field, also presented the potential applicability for other crops.

• Korean Journal of Remote Sensing
• /
• v.38 no.6_4
• /
• pp.1925-1934
• /
• 2022

Monitoring nuclear activity for inaccessible areas using remote sensing technology is essential for nuclear non-proliferation. In recent years, deep learning has been actively used to detect nuclear-activity-related small objects. However, high-resolution satellite imagery containing small objects can result in class imbalance. As a result, there is a performance degradation problem in detecting small objects. Therefore, this study aims to improve detection accuracy by analyzing the effect of the ratio of small objects related to nuclear activity in the input data for the performance of the deep learning model. To this end, six case datasets with different ratios of small object pixels were generated and a U-Net model was trained for each case. Following that, each trained model was evaluated quantitatively and qualitatively using a test dataset containing various types of small object classes. The results of this study confirm that when the ratio of object pixels in the input image is adjusted, small objects related to nuclear activity can be detected efficiently. This study suggests that the performance of deep learning can be improved by adjusting the object pixel ratio of input data in the training dataset.