• Journal of the Korea Convergence Society
• /
• v.11 no.12
• /
• pp.39-47
• /
• 2020

In this paper, we proposed a deep learning-based detection method using Saliency Attention to detect salient objects in images. The salient object detection separates the object where the human eye is focused from the background, and determines the highly relevant part of the image. It is usefully used in various fields such as object tracking, detection, and recognition. Existing deep learning-based methods are mostly Autoencoder structures, and many feature losses occur in encoders that compress and extract features and decoders that decompress and extend the extracted features. These losses cause the salient object area to be lost or detect the background as an object. In the proposed method, Saliency Attention is proposed to reduce the feature loss and suppress the background region in the Autoencoder structure. The influence of the feature values was determined using the ELU activation function, and Attention was performed on the feature values in the normalized negative and positive regions, respectively. Through this Attention method, the background area was suppressed and the projected object area was emphasized. Experimental results showed improved detection results compared to existing deep learning methods.

• Korean Journal of Remote Sensing
• /
• v.38 no.6_1
• /
• pp.1329-1341
• /
• 2022

Destroying the marine environment and marine ecosystem and causing marine accidents, marine debris is generated every year, and among them, submerged marine debris is difficult to identify and collect because it is on the seabed. Therefore, deep-learning-based semantic segmentation was experimented on waste fish nets and waste ropes using underwater images to identify efficient collection and distribution. For segmentation, a high-resolution network (HRNet), a state-of-the-art deep learning technique, was used, and the performance of each optimizer was compared. In the segmentation result fish net, F1 score=(86.46%, 86.20%, 85.29%), IoU=(76.15%, 75.74%, 74.36%), For the rope F1 score=(80.49%, 80.48%, 77.86%), IoU=(67.35%, 67.33%, 63.75%) in the order of adaptive moment estimation (Adam), Momentum, and stochastic gradient descent (SGD). Adam's results were the highest in both fish net and rope. Through the research results, the evaluation of segmentation performance for each optimizer and the possibility of segmentation of marine debris in the latest deep learning technique were confirmed. Accordingly, it is judged that by applying the latest deep learning technique to the identification of submerged marine debris through underwater images, it will be helpful in estimating the distribution of marine sedimentation debris through more accurate and efficient identification than identification through the naked eye.

• Journal of Intelligence and Information Systems
• /
• v.29 no.1
• /
• pp.233-247
• /
• 2023

Recently, research on detecting objects in hidden spaces beyond the direct line-of-sight of observers has received attention. Most studies use optical equipment that utilizes the directional of light, but sound that has both diffraction and directional is also suitable for non-line-of-sight(NLOS) research. In this paper, we propose a novel method of detecting objects in non-line-of-sight (NLOS) areas using acoustic signals in the audible frequency range. We developed a deep learning model that extracts information from the NLOS area by inputting only acoustic signals and predicts the properties and location of hidden objects. Additionally, for the training and evaluation of the deep learning model, we collected data by varying the signal transmission and reception location for a total of 11 objects. We show that the deep learning model demonstrates outstanding performance in detecting objects in the NLOS area using acoustic signals. We observed that the performance decreases as the distance between the signal collection location and the reflecting wall, and the performance improves through the combination of signals collected from multiple locations. Finally, we propose the optimal conditions for detecting objects in the NLOS area using acoustic signals.

• Journal of the Society of Disaster Information
• /
• v.19 no.3
• /
• pp.498-509
• /
• 2023

Purpose: This paper proposes a method detecting the falling of a maintenance worker in the underground utility tunnel, by applying deep learning techniques using CCTV video, and evaluates the applicability of the proposed method to the worker monitoring of the utility tunnel. Method: Each rule was designed to detect the falling of a maintenance worker by using the inference results from pre-trained YOLOv5 and OpenPose models, respectively. The rules were then integrally applied to detect worker falls within the utility tunnel. Result: Although the worker presence and falling were detected by the proposed model, the inference results were dependent on both the distance between the worker and CCTV and the falling direction of the worker. Additionally, the falling detection system using YOLOv5 shows superior performance, due to its lower dependence on distance and fall direction, compared to the OpenPose-based. Consequently, results from the fall detection using the integrated dual deep learning model were dependent on the YOLOv5 detection performance. Conclusion: The proposed hybrid model shows detecting an abnormal worker in the utility tunnel but the improvement of the model was meaningless compared to the single model based YOLOv5 due to severe differences in detection performance between each deep learning model

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.10a
• /
• pp.407-408
• /
• 2022

In this paper, we will look at the components of the FPGA-based object recognition system one by one. Let's take a look at each function of the components camera, DLM, service system, video output monitor, deep trainer software, and external deep learning software.

• Journal of IKEEE
• /
• v.23 no.4
• /
• pp.1250-1256
• /
• 2019

Although one can easily generate real-world 3D mesh data using a 3D printer or a depth camera, the generated data inevitably includes unnecessary noise. Therefore, mesh denoising is essential to obtain intact 3D mesh data. However, conventional mathematical denoising methods require preprocessing and often eliminate some important features of the 3D mesh. To address this problem, this paper proposes a deep learning based 3D mesh denoising method. Specifically, we propose a convolution-based autoencoder model consisting of an encoder and a decoder. The convolution operation applied to the mesh data performs denoising considering the relationship between each vertex constituting the mesh data and the surrounding vertices. When the convolution is completed, a sampling operation is performed to improve the learning speed. Experimental results show that the proposed autoencoder model produces faster and higher quality denoised data than the conventional methods.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.21 no.1
• /
• pp.195-200
• /
• 2021

With the development of transportation and mobiles demand for tourism travel is increasing and related industries are also developing significantly. The combination of augmented reality and tourism contents one of the areas of digital media technology, is also actively being studied, and artificial intelligence is already combined with the tourism industry in various directions, enriching tourists' travel experiences. In this paper, we propose a system that scans miniature models produced by reducing tourist areas, finds the relevant tourist sites based on models learned using deep learning in advance, and provides relevant information and 3D models as AR services. Because model learning and object detection are carried out using YOLOv3 neural networks, one of various deep learning neural networks, object detection can be performed at a fast rate to provide real-time service.

• The Journal of the Korea Contents Association
• /
• v.21 no.6
• /
• pp.552-560
• /
• 2021

With the recent development of the art distribution system, interest in art investment is increasing rather than seeing art as an object of aesthetic utility. Unlike stocks and bonds, the price of artworks has a heterogeneous characteristic that is determined by reflecting both objective and subjective factors, so the uncertainty in price prediction is high. In this study, we used LSTM Recurrent Neural Network deep learning model to predict the auction winning price by inputting the artist, physical and sales charateristics of the Korean artist. According to the result, the RMSE value, which explains the difference between the predicted and actual price by model, was 0.064. Painter Lee Dae Won had the highest predictive power, and Lee Joong Seop had the lowest. The results suggest the art market becomes more active as investment goods and demand for auction winning price increases.

• Journal of Korea Society of Industrial Information Systems
• /
• v.27 no.6
• /
• pp.95-103
• /
• 2022

Quick and accurate understanding of the situation in a severe accident is essential for conducting the appropriate accident management and response using the accident diagnosis information. This study employed deep learning technology to diagnose severe accidents through the major safety parameters transferred from a nuclear power plant (NPP) to AtomCARE. After selecting the major accident scenarios to consider, a learning database was established for particular scenarios affiliated with major scenarios by performing a large number of severe accident analyses using MAAP5 code. The severe accident diagnosis technology, which classifies detailed accident scenarios using the major safety parameters from NPPs, was developed by training it with the established database . Verification and validation were conducted by blind test and principal component analysis. The technology developed in this study is expected to be extended and applied to all severe accident scenarios and be utilized as a base technology for quick and accurate severe accident diagnosis.

• KIPS Transactions on Computer and Communication Systems
• /
• v.11 no.11
• /
• pp.411-418
• /
• 2022

Incorrectly loaded containers can easily knock down by strong winds. Container collapse accidents can lead to material damage and paralysis of the port system. In this paper, We propose a deep learning-based container loading state and accident risk detection technique. Using Darknet-based YOLO, the container load status identifies in real-time through corner casting on the top and bottom of the container, and the risk of accidents notifies the manager. We present criteria for classifying container alignment states and select efficient learning algorithms based on inference speed, classification accuracy, detection accuracy, and FPS in real embedded devices in the same environment. The study found that YOLOv4 had a weaker inference speed and performance of FPS than YOLOv3, but showed strong performance in classification accuracy and detection accuracy.