• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.2
• /
• pp.786-799
• /
• 2021

Road damage detection is important for road maintenance. With the development of deep learning, more and more road damage detection methods have been proposed, such as Fast R-CNN, Faster R-CNN, Mask R-CNN and RetinaNet. However, because shallow and deep layers cannot be extracted at the same time, the existing methods do not perform well in detecting objects with fewer samples. In addition, these methods cannot obtain a highly accurate detecting bounding box. This paper presents a Multi-level Feature Pyramids method based on M2det. Because the feature layer has multi-scale and multi-level architecture, the feature layer containing more information and obvious features can be extracted. Moreover, an attention mechanism is used to improve the accuracy of local boundary boxes in the dataset. Experimental results show that the proposed method is better than the current state-of-the-art methods.

• Journal of the Optical Society of Korea
• /
• v.20 no.2
• /
• pp.245-250
• /
• 2016

In this paper, we demonstrate a self-imaging technique that can visualize longitudinal interference patterns behind periodically-structured objects, which is often referred to as Talbot carpet. Talbot carpet is of great interest due to ever-decreasing scale of interference features. We demonstrate experimentally that Talbot carpets can be imaged in a single exposure configuration revealing a broad spectrum of multi-scale features. We have performed rigorous diffraction simulations for showing that Talbot carpet print can produce ever-decreasing structures down to limits set by mask feature sizes. This demonstrates that large-scale pattern masks may be used for direct printing of features with substantially smaller scales. This approach is also useful for characterization of image sensors and recording media.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.12
• /
• pp.4439-4455
• /
• 2021

Compared with two-stage object detection algorithms, one-stage algorithms provide a better trade-off between real-time performance and accuracy. However, these methods treat the intermediate features equally, which lacks the flexibility to emphasize meaningful information for classification and location. Besides, they ignore the interaction of contextual information from different scales, which is important for medium and small objects detection. To tackle these problems, we propose an image pyramid network based on dual attention mechanism (DAIPNet), which builds an image pyramid to enrich the spatial information while emphasizing multi-scale informative features based on dual attention mechanisms for one-stage object detection. Our framework utilizes a pre-trained backbone as standard detection network, where the designed image pyramid network (IPN) is used as auxiliary network to provide complementary information. Here, the dual attention mechanism is composed of the adaptive feature fusion module (AFFM) and the progressive attention fusion module (PAFM). AFFM is designed to automatically pay attention to the feature maps with different importance from the backbone and auxiliary network, while PAFM is utilized to adaptively learn the channel attentive information in the context transfer process. Furthermore, in the IPN, we build an image pyramid to extract scale-wise features from downsampled images of different scales, where the features are further fused at different states to enrich scale-wise information and learn more comprehensive feature representations. Experimental results are shown on MS COCO dataset. Our proposed detector with a 300 × 300 input achieves superior performance of 32.6% mAP on the MS COCO test-dev compared with state-of-the-art methods.

• Korean Management Science Review
• /
• v.24 no.2
• /
• pp.57-72
• /
• 2007

Many Applications of scientific research have coupled with functional data signal clustering techniques to discover novel characteristics that can be used for the diagnoses of several issues. In this article we present an interpretable multi-scale cluster hierarchy framework for clustering functional data using its multi-aspect frequency information. The suggested method focuses on how to effectively select transformed features/variables in unsupervised manner so that finally reduce the data dimension and achieve the multi-purposed clustering. Specially, we apply our suggested method to mutual fund returns and make superior-performing funds group based on different aspects such as global patterns, seasonal variations, levels of noise, and their combinations. To promise our method producing a quality cluster hierarchy, we give some empirical results under the simulation study and a set of real life data. This research will contribute to financial market analysis and flexibly fit to other research fields with clustering purposes.

• Proceedings of the IEEK Conference
• /
• 2000.09a
• /
• pp.901-904
• /
• 2000

A direct authentication from gray-scale image, instead of the conventional multi-step preprocessing, is proposed using Gabor filter-based features from the gray-scale fingerprint around core point. The core point is located as a reference point for the translation invariant matching. And its principal symmetry axis is detected for the rotation invariant matching from its neighboring region centered at the core point. And then fingerprint is divided into non-overlapping blocks with respect to the core point and features are directly extracted form the blocked gray level fingerprint using Gabor filter. The proposed fingerprint authentication is based on the Euclidean distance between the corresponding Gabor features of the input and the template fingerprints. Experiments are conducted on 300${\times}$300 fingerprints obtained from a CMOS sensor with 500 dpi resolution, and the proposed method could lower the False Reject Rate(FRR) to 18.2% under False Acceptance Rate(FAR) of 0%.

• Journal of Electrical Engineering and Technology
• /
• v.13 no.4
• /
• pp.1494-1503
• /
• 2018

This paper proposes a novel probabilistic load flow model for power systems integrated with large-scale wind power, which considers the multi-time scale dispatching features. The ramp limitations of the units and the steady-state security constraints of the network have been comprehensively considered for the entire duration of the study period; thus, the coupling of the system operation states at different time sections has been taken into account. For each time section, the automatic generation control (AGC) strategy is considered, and all variations associated with the wind power and loads are compensated by all AGC units. Cumulants and the Gram-Charlier expansion are used to solve the proposed model. The effectiveness of the proposed method is validated using the modified IEEE RTS 24-bus system and the modified IEEE 118-bus system.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2020.11a
• /
• pp.25-28
• /
• 2020

Automatic segmentation of brain tissues such as WM, GM, and CSF from brain MRI scans is helpful for the diagnosis of many neurological disorders. Accurate segmentation of these brain structures is a very challenging task due to low tissue contrast, bias filed, and partial volume effects. With the aim to improve brain MRI segmentation accuracy, we propose an end-to-end convolutional based U-SegNet architecture designed with multi-scale kernels, which includes cascaded dilated convolutions for the task of brain MRI segmentation. The multi-scale convolution kernels are designed to extract abundant semantic features and capture context information at different scales. Further, the cascaded dilated convolution scheme helps to alleviate the vanishing gradient problem in the proposed model. Experimental outcomes indicate that the proposed architecture is superior to the traditional deep-learning methods such as Segnet, U-net, and U-Segnet and achieves high performance with an average DSC of 93% and 86% of JI value for brain MRI segmentation.

• Korean Journal of Remote Sensing
• /
• v.34 no.6_2
• /
• pp.1215-1227
• /
• 2018

Sea ice motion is an important factor for assessing change of sea ice because the motion affects to not only regional distribution of sea ice but also new ice growth and thickness of ice. This study presents an application of multi-temporal high-resolution optical satellites images obtained from Korea Multi-Purpose Satellite-2 (KOMPSAT-2) and Korea Multi-Purpose Satellite-3 (KOMPSAT-3) to measure sea ice motion using SIFT (Scale-Invariant Feature Transform), SURF (Speeded Up Robust Features) and ORB (Oriented FAST and Rotated BRIEF) feature tracking techniques. In order to use satellite images from two different sensors, spatial and radiometric resolution were adjusted during pre-processing steps, and then the feature tracking techniques were applied to the pre-processed images. The matched features extracted from the SIFT showed even distribution across whole image, however the matched features extracted from the SURF showed condensed distribution of features around boundary between ice and ocean, and this regionally biased distribution became more prominent in the matched features extracted from the ORB. The processing time of the feature tracking was decreased in order of SIFT, SURF and ORB techniques. Although number of the matched features from the ORB was decreased as 59.8% compared with the result from the SIFT, the processing time was decreased as 8.7% compared with the result from the SIFT, therefore the ORB technique is more suitable for fast measurement of sea ice motion.

• Journal of Advanced Navigation Technology
• /
• v.23 no.5
• /
• pp.400-407
• /
• 2019

In this paper, the shadow detection and reconstruction method are proposed using intrinsic image, which does not change the essential characteristics under the influence of various illuminance, and multi-scale gamma correction. The shadow detection was estimated by the pixel change information between a grayscale and an intrinsic image of the color image, and the brightness of the image were adjusted by gamma correction in the shadow restoration process. Multi-scale gamma correction is performed for each channel of a color image due to the fact that the saturation can be changed by nonlinear adjustment to individual pixel values. Multi-scale gamma values are estimated based on the information of the crossed edge between shadows and non-shadowed regions in the color image, as a result, the shadows are reconstructed by correcting different region features with multi-scale gamma values. Experimental results show that the proposed method effectively reconstructs shadows in a single natural image.

• Current Optics and Photonics
• /
• v.8 no.3
• /
• pp.215-224
• /
• 2024

In medium- and long-range optical imaging systems, atmospheric turbulence causes blurring and distortion of images, resulting in loss of image information. An image-restoration method based on an adaptive feature-fusion multi-input-multi-output (MIMO) dense U-shaped network (Unet) is proposed, to restore a single image degraded by atmospheric turbulence. The network's model is based on the MIMO-Unet framework and incorporates patch-embedding shallow-convolution modules. These modules help in extracting shallow features of images and facilitate the processing of the multi-input dense encoding modules that follow. The combination of these modules improves the model's ability to analyze and extract features effectively. An asymmetric feature-fusion module is utilized to combine encoded features at varying scales, facilitating the feature reconstruction of the subsequent multi-output decoding modules for restoration of turbulence-degraded images. Based on experimental results, the adaptive feature-fusion MIMO dense U-shaped network outperforms traditional restoration methods, CMFNet network models, and standard MIMO-Unet network models, in terms of image-quality restoration. It effectively minimizes geometric deformation and blurring of images.