• Journal of Korea Multimedia Society
• /
• v.22 no.2
• /
• pp.136-145
• /
• 2019

The crowded environment of a domestic pig farm is highly vulnerable to the spread of infectious diseases such as foot-and-mouth disease, and studies have been conducted to automatically analyze behavior of pigs in a crowded pig farm through a video surveillance system using a camera. Although it is required to correctly separate occluding pigs for tracking each individual pigs, extracting the boundaries of the occluding pigs fast and accurately is a challenging issue due to the complicated occlusion patterns such as X shape and T shape. In this study, we propose a fast and accurate method to separate occluding pigs not only by exploiting the characteristics (i.e., one of the fast deep learning-based object detectors) of You Only Look Once, YOLO, but also by overcoming the limitation (i.e., the bounding box-based object detector) of YOLO with the test-time data augmentation of rotation. Experimental results with two-pigs occlusion patterns show that the proposed method can provide better accuracy and processing speed than one of the state-of-the-art widely used deep learning-based segmentation techniques such as Mask R-CNN (i.e., the performance improvement over Mask R-CNN was about 11 times, in terms of the accuracy/processing speed performance metrics).

• International Journal of Internet, Broadcasting and Communication
• /
• v.14 no.3
• /
• pp.149-154
• /
• 2022

In recent years, the application of deep learning method to computer vision has shown to achieve great performances. Thus, many research projects have also applied deep learning technology to railroad defect detection. In this paper, we have reviewed the researches that applied computer vision based deep learning method to railroad defect detection and inspection, and have discussed the current trend and the direction of those researches. Many research projects were targeted to operate automatically without visual inspection of human and to work in real-time. Therefore, methods to speed up the computation were also investigated. The reduction of the number of learning parameters was considered important to improve computation efficiency. In addition to computation speed issue, the problem of annotation was also discussed in some research projects. To alleviate the problem of time consuming annotation, some kinds of automatic segmentation of the railroad defect or self-supervised methods have been suggested.

• Investigative Magnetic Resonance Imaging
• /
• v.23 no.2
• /
• pp.81-99
• /
• 2019

Recently, deep learning methods have shown great potential in various tasks that involve handling large amounts of digital data. In the field of MR imaging research, deep learning methods are also rapidly being applied in a wide range of areas to complement or replace traditional model-based methods. Deep learning methods have shown remarkable improvements in several MR image processing areas such as image reconstruction, image quality improvement, parameter mapping, image contrast conversion, and image segmentation. With the current rapid development of deep learning technologies, the importance of the role of deep learning in MR imaging research appears to be growing. In this article, we introduce the basic concepts of deep learning and review recent studies on various MR image processing applications.

• Korean Journal of Remote Sensing
• /
• v.36 no.2_1
• /
• pp.199-215
• /
• 2020

A seagrass that is marine vascular plants plays an important role in the marine ecosystem, so periodic monitoring ofseagrass habitatsis being performed. Recently, the use of dronesthat can easily acquire very high-resolution imagery is increasing to efficiently monitor seagrass habitats. And deep learning based on a convolutional neural network has shown excellent performance in semantic segmentation. So, studies applied to deep learning models have been actively conducted in remote sensing. However, the segmentation accuracy was different due to the hyperparameter, various deep learning models and imagery. And the normalization of the image and the tile and batch size are also not standardized. So,seagrass habitats were segmented from drone-borne imagery using a deep learning that shows excellent performance in this study. And it compared and analyzed the results focused on normalization and tile size. For comparison of the results according to the normalization, tile and batch size, a grayscale image and grayscale imagery converted to Z-score and Min-Max normalization methods were used. And the tile size isincreased at a specific interval while the batch size is allowed the memory size to be used as much as possible. As a result, IoU was 0.26 ~ 0.4 higher than that of Z-score normalized imagery than other imagery. Also, it wasfound that the difference to 0.09 depending on the tile and batch size. The results were different according to the normalization, tile and batch. Therefore, this experiment found that these factors should have a suitable decision process.

• Imaging Science in Dentistry
• /
• v.54 no.1
• /
• pp.81-91
• /
• 2024

Purpose: The objective of this study was to propose a deep-learning model for the detection of the mandibular canal on dental panoramic radiographs. Materials and Methods: A total of 2,100 panoramic radiographs (PANs) were collected from 3 different machines: RAYSCAN Alpha (n=700, PAN A), OP-100 (n=700, PAN B), and CS8100 (n=700, PAN C). Initially, an oral and maxillofacial radiologist coarsely annotated the mandibular canals. For deep learning analysis, convolutional neural networks (CNNs) utilizing U-Net architecture were employed for automated canal segmentation. Seven independent networks were trained using training sets representing all possible combinations of the 3 groups. These networks were then assessed using a hold-out test dataset. Results: Among the 7 networks evaluated, the network trained with all 3 available groups achieved an average precision of 90.6%, a recall of 87.4%, and a Dice similarity coefficient (DSC) of 88.9%. The 3 networks trained using each of the 3 possible 2-group combinations also demonstrated reliable performance for mandibular canal segmentation, as follows: 1) PAN A and B exhibited a mean DSC of 87.9%, 2) PAN A and C displayed a mean DSC of 87.8%, and 3) PAN B and C demonstrated a mean DSC of 88.4%. Conclusion: This multi-device study indicated that the examined CNN-based deep learning approach can achieve excellent canal segmentation performance, with a DSC exceeding 88%. Furthermore, the study highlighted the importance of considering the characteristics of panoramic radiographs when developing a robust deep-learning network, rather than depending solely on the size of the dataset.

• Journal of the Semiconductor & Display Technology
• /
• v.19 no.3
• /
• pp.12-18
• /
• 2020

In semiconductor manufacturing, defect detection is critical to maintain high yield. Currently, computer vision systems used in semiconductor photo lithography still have adopt to digital image processing algorithm, which often occur inspection faults due to sensitivity to external environment. Thus, we intend to handle this problem by means of using Mask R-CNN instead of digital image processing algorithm. Additionally, Mask R-CNN can be trained with image dataset pre-processed by means of the specific designed digital image filter to extract the enhanced feature map of Convolutional Neural Network (CNN). Our approach converged advantage of digital image processing and instance segmentation with deep learning yields more efficient semiconductor photo lithography inspection system than conventional system.

• Journal of Information Processing Systems
• /
• v.14 no.6
• /
• pp.1405-1419
• /
• 2018

An image fusion method is proposed on the basis of depth model segmentation to overcome the shortcomings of noise interference and artifacts caused by infrared and visible image fusion. Firstly, the deep Boltzmann machine is used to perform the priori learning of infrared and visible target and background contour, and the depth segmentation model of the contour is constructed. The Split Bregman iterative algorithm is employed to gain the optimal energy segmentation of infrared and visible image contours. Then, the nonsubsampled contourlet transform (NSCT) transform is taken to decompose the source image, and the corresponding rules are used to integrate the coefficients in the light of the segmented background contour. Finally, the NSCT inverse transform is used to reconstruct the fused image. The simulation results of MATLAB indicates that the proposed algorithm can obtain the fusion result of both target and background contours effectively, with a high contrast and noise suppression in subjective evaluation as well as great merits in objective quantitative indicators.

• Journal of IKEEE
• /
• v.24 no.1
• /
• pp.147-153
• /
• 2020

Conventional lane detection algorithms have problems in that the detection rate is lowered in road environments having a large change in curvature and illumination. The probabilistic Hough transform method has low lane detection rate since it exploits edges and restrictive angles. On the other hand, the method using a sliding window can detect a curved lane as the lane is detected by dividing the image into windows. However, the detection rate of this method is affected by road slopes because it uses affine transformation. In order to detect lanes robustly and avoid obstacles, we propose driving assist system using semantic segmentation based on deep learning. The architecture for segmentation is SegNet based on VGG-16. The semantic image segmentation feature can be used to calculate safety space and predict collisions so that we control a vehicle using adaptive-MPC to avoid objects and keep lanes. Simulation results with CARLA show that the proposed algorithm detects lanes robustly and avoids unknown obstacles in front of vehicle.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2023.01a
• /
• pp.391-394
• /
• 2023

일반적으로 화재 감지 시스템은 정확하고 빠르게 화재를 감지하는 것은 어려운 문제 중 하나이다. 본 논문에서는 U-net을 활용하여 기존의 화재(불) 영역 추출 기법으로 Segmentation으로 보다 정밀하게 탐지하는 기법을 제안한다. 이 기법은 화재 이미지에서 연기제거 및 색상보정을 통해 이미지를 전처리하여 화염 영역을 추출한 뒤 U-Net으로 학습시켜 이미지를 입력하면 불 영역의 Segmentation을 추출하도록 한다.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.23 no.1
• /
• pp.65-70
• /
• 2023

In this paper, we used a deep learning model to detect and segment flame and smoke in real time from fires. To this end, well known U-NET was used to separate and divide the flame and smoke of the fire using multi-class. As a result of learning using the proposed technique, the values of loss error and accuracy are very good at 0.0486 and 0.97996, respectively. The IOU value used in object detection is also very good at 0.849. As a result of predicting fire images that were not used for learning using the learned model, the flame and smoke of fire are well detected and segmented, and smoke color were well distinguished. Proposed method can be used to build fire prediction and detection system.