• Journal of the Korean Society of Radiology
• /
• v.16 no.1
• /
• pp.25-34
• /
• 2022

Brain computed tomography (CT) is useful for brain lesion diagnosis, such as brain hemorrhage, due to non-invasive methodology, 3-dimensional image provision, low radiation dose. However, there has been numerous misdiagnosis owing to a lack of radiologist and heavy workload. Recently, object detection technologies based on artificial intelligence have been developed in order to overcome the limitations of traditional diagnosis. In this study, the applicability of a deep learning-based YOLOv5s model was evaluated for brain hemorrhage detection using brain CT images. Also, the effect of hyperparameters in the trained YOLOv5s model was analyzed. The YOLOv5s model consisted of backbone, neck and output modules. The trained model was able to detect a region of brain hemorrhage and provide the information of the region. The YOLOv5s model was trained with various activation functions, optimizer functions, loss functions and epochs, and the performance of the trained model was evaluated in terms of brain hemorrhage detection accuracy and training time. The results showed that the trained YOLOv5s model is able to provide a bounding box for a region of brain hemorrhage and the accuracy of the corresponding box. The performance of the YOLOv5s model was improved by using the mish activation function, the stochastic gradient descent (SGD) optimizer function and the completed intersection over union (CIoU) loss function. Also, the accuracy and training time of the YOLOv5s model increased with the number of epochs. Therefore, the YOLOv5s model is suitable for brain hemorrhage detection using brain CT images, and the performance of the model can be maximized by using appropriate hyperparameters.

• Korean Journal of Remote Sensing
• /
• v.39 no.2
• /
• pp.143-156
• /
• 2023

To precisely and reliably analyze the contents of the satellite imagery, recognizing the clouds which are the obstacle to gathering the useful information is essential. In recent times, deep learning yielded satisfactory results in various tasks, so many studies using deep neural networks have been conducted to improve the performance of cloud detection. However, existing methods for cloud detection have the limitation on increasing the performance due to the adopting the network models for semantic image segmentation without modification. To tackle this problem, we introduced the multi-branch neural architecture search to find optimal network structure for cloud detection. Additionally, the proposed method adopts the soft intersection over union (IoU) as loss function to mitigate the disagreement between the loss function and the evaluation metric and uses the various data augmentation methods. The experiments are conducted using the cloud detection dataset acquired by Arirang-3/3A satellite imagery. The experimental results showed that the proposed network which are searched network architecture using cloud dataset is 4% higher than the existing network model which are searched network structure using urban street scenes with regard to the IoU. Also, the experimental results showed that the soft IoU exhibits the best performance on cloud detection among the various loss functions. When comparing the proposed method with the state-of-the-art (SOTA) models in the field of semantic segmentation, the proposed method showed better performance than the SOTA models with regard to the mean IoU and overall accuracy.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.27 no.5
• /
• pp.113-119
• /
• 2023

Most infrastructure structures were completed during periods of economic growth. The number of infrastructure structures reaching their lifespan is increasing, and the proportion of old structures is gradually increasing. The functions and performance of these structures at the time of design may deteriorate and may even lead to safety accidents. To prevent this repercussion, accurate inspection and appropriate repair are requisite. To this end, demand is increasing for computer vision and deep learning technology to accurately detect even minute cracks. However, deep learning algorithms require a large number of training data. In particular, label images indicating the location of cracks in the image are required. To secure a large number of those label images, a lot of labor and time are consumed. To reduce these costs as well as increase detection accuracy, this study proposed a learning structure based on mean teacher method. This learning structure was trained on a dataset of 900 labeled image dataset and 3000 unlabeled image dataset. The crack detection network model was evaluated on over 300 labeled image dataset, and the detection accuracy recorded a mean intersection over union of 89.23% and an F1 score of 89.12%. Through this experiment, it was confirmed that detection performance was improved compared to supervised learning. It is expected that this proposed method will be used in the future to reduce the cost required to secure label images.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.16 no.5
• /
• pp.96-108
• /
• 2017

The current collision warning and avoidance system(CWAS) is one of the representative Advanced Driver Assistance Systems (ADAS) that significantly contributes to improve the safety performance of a vehicle and mitigate the severity of an accident. However, current CWAS mainly have focused on preventing a forward collision in an uninterrupted flow, and the prevention performance near intersections and other various types of accident scenarios are not extensively studied. In this paper, the safety performance of Vision-Sensor (VS) and Radar-Sensor(RS) - based collision warning systems are evaluated near an intersection area with the data from Naturalistic Driving Study(NDS) of Second Strategic Highway Research Program(SHRP2). Based on the VS and RS data, we newly derived sixteen vehicle-to-vehicle accident scenarios near an intersection. Then, we evaluated the detection performance of VS and RS within the derived scenarios. The results showed that VS and RS can prevent an accident in limited situations due to their restrained field-of-view. With an accident prevention rate of 0.7, VS and RS can prevent an accident in five and four scenarios, respectively. For an efficient accident prevention, a different system that can detect vehicles'movement with longer range than VS and RS is required as well as an algorithm that can predict the future movement of other vehicles. In order to further improve the safety performance of CWAS near intersection areas, a communication-based collision warning system such as integration algorithm of data from infrastructure and in-vehicle sensor shall be developed.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.9
• /
• pp.2927-2941
• /
• 2022

The primary task of machine fault diagnosis is to judge whether the current state is normal or damaged, so it is a typical binary classification problem with mutual exclusion. Mutually exclusive events and out-of-domain detection have one thing in common: there are two types of data and no intersection. We proposed a fusion model method to improve the accuracy of machine fault diagnosis, which is based on the mutual exclusivity of events and the commonality of out-of-distribution detection, and finally generalized to all binary classification problems. It is reported that the performance of a convolutional neural network (CNN) will decrease as the recognition type increases, so the variational auto-encoder (VAE) is used as the primary model. Two VAE models are used to train the machine's normal and fault sound data. Two reconstruction probabilities will be obtained during the test. The smaller value is transformed into a correction value of another value according to the mutually exclusive characteristics. Finally, the classification result is obtained according to the fusion algorithm. Filtering normal data features from fault data features is proposed, which shields the interference and makes the fault features more prominent. We confirm that good performance improvements have been achieved in the machine fault detection data set, and the results are better than most mainstream models.

• Geomechanics and Engineering
• /
• v.38 no.1
• /
• pp.29-44
• /
• 2024

This research investigates the effectiveness of data augmentation techniques in the automated analysis of B-scan images from ground-penetrating radar (GPR) using deep learning. In spite of the growing interest in automating GPR data analysis and advancements in deep learning for image classification and object detection, many deep learning-based GPR data analysis studies have been limited by the availability of large, diverse GPR datasets. Data augmentation techniques are widely used in deep learning to improve model performance. In this study, we applied four data augmentation techniques (geometric transformation, color-space transformation, noise injection, and applying kernel filter) to the GPR datasets obtained from a testbed. A deep learning model for GPR data analysis was developed using three models (Faster R-CNN ResNet, SSD ResNet, and EfficientDet) based on transfer learning. It was found that data augmentation significantly enhances model performance across all cases, with the mAP and AR for the Faster R-CNN ResNet model increasing by approximately 4%, achieving a maximum mAP (Intersection over Union = 0.5:1.0) of 87.5% and maximum AR of 90.5%. These results highlight the importance of data augmentation in improving the robustness and accuracy of deep learning models for GPR B-scan analysis. The enhanced detection capabilities achieved through these techniques contribute to more reliable subsurface investigations in geotechnical engineering.

• 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.

• Korean Journal of Remote Sensing
• /
• v.38 no.6_1
• /
• pp.1109-1124
• /
• 2022

This study proposes a marine debris monitoring methods using satellite and drone multispectral images. A multi-layer perceptron (MLP) model was applied to detect marine debris using Sentinel-2 satellite image. And for the detection of marine debris using drone multispectral images, performance evaluation and comparison of U-Net, DeepLabv3+ (ResNet50) and DeepLabv3+ (Inceptionv3) among deep learning models were performed (mIoU 0.68). As a result of marine debris detection using satellite image, the F1-Score was 0.97. Marine debris detection using drone multispectral images was performed on vegetative debris and plastics. As a result of detection, when DeepLabv3+ (Inceptionv3) was used, the most model accuracy, mean intersection over union (mIoU), was 0.68. Vegetative debris showed an F1-Score of 0.93 and IoU of 0.86, while plastics showed low performance with an F1-Score of 0.5 and IoU of 0.33. However, the F1-Score of the spectral index applied to generate plastic mask images was 0.81, which was higher than the plastics detection performance of DeepLabv3+ (Inceptionv3), and it was confirmed that plastics monitoring using the spectral index was possible. The marine debris monitoring technique proposed in this study can be used to establish a plan for marine debris collection and treatment as well as to provide quantitative data on marine debris generation.

• Korean Journal of Remote Sensing
• /
• v.38 no.6_2
• /
• pp.1623-1631
• /
• 2022

Since oil spills can be a significant threat to the marine ecosystem, it is necessary to obtain information on the current contamination status quickly to minimize the damage. Satellite-based detection of marine oil spills has the advantage of spatiotemporal coverage because it can monitor a wide area compared to aircraft. Due to the recent development of computer vision and deep learning, marine oil spill detection can also be facilitated by deep learning. Unlike the existing studies based on Synthetic Aperture Radar (SAR) images, we conducted a deep learning modeling using PlanetScope optical satellite images. The blind test of the DeepLabV3+ model for oil spill detection showed the performance statistics with an accuracy of 0.885, a precision of 0.888, a recall of 0.886, an F1-score of 0.883, and a Mean Intersection over Union (mIOU) of 0.793.

• Journal of Institute of Control, Robotics and Systems
• /
• v.20 no.10
• /
• pp.1057-1062
• /
• 2014

This paper proposes a tip-over detection method for a mobile robot using a support inscribed circle defined as an inscribed circle of a support polygon. A support polygon defined by the contact points between the robot and the terrain is often used to analyze the tip-over. For a robot moving on uneven terrain, if the intersection between the extended line of gravity from the robot's COG and the terrain is inside the support polygon, tip-over will not occur. On the contrary, if the intersection is outside, tip-over will occur. The terrain is detected by using an RGB-D sensor. The terrain is locally modeled as a plane, and thus the normal vector can be obtained at each point on the terrain. The support polygon and the terrain's normal vector are used to detect tip-over. However, tip-over cannot be detected in advance since the support polygon is determined depending on the orientation of the robot. Thus, the support polygon is approximated as its inscribed circle to detect the tip-over regardless of the robot's orientation. To verify the effectiveness of the proposed method, the experiments are carried out using a 4-wheeled robot, ERP-42, with the Xtion RGB-D sensor.