• Proceedings of the Korea Information Processing Society Conference
• /
• 2021.11a
• /
• pp.927-929
• /
• 2021

최근 펫팸족(Pet-Family)과 같이 반려동물을 가족처럼 생각하는 가구가 증가하면서 반려동물 시장이 크게 성장하고 있다. 이러한 이유로 본 논문에서는 반려동물의 객체 식별을 통한 객체 분할과 신체 좌표추정에 기반을 둔 반려동물의 행동 분류 방법을 제안한다. 이 방법은 CCTV를 통해 반려동물 영상 데이터를 수집한다. 수집된 영상 데이터는 반려동물의 인스턴스 분할을 위해 Mask R-CNN(Region Convolutional Neural Networks) 모델을 적용하고, DeepLabCut 모델을 통해 추정된 신체 좌푯값을 도출한다. 이 결과로 도출된 영상 데이터와 추정된 신체 좌표 값은 CNN(Convolutional Neural Networks)-LSTM(Long Short-Term Memory) 모델을 적용하여 행동을 분류한다. 본 모델을 바탕으로 행동을 분석 및 분류하여, 반려동물의 위험 상황과 돌발 행동에 대한 올바른 대처를 제공할 수 있는 기반을 제공할 것이라 기대한다.

• ETRI Journal
• /
• v.31 no.4
• /
• pp.429-437
• /
• 2009

This paper proposes a novel technique for 3D scene relighting with interactive viewpoint changes. The proposed technique is based on a deep framebuffer framework for fast relighting computation which adopts image-based techniques to provide arbitrary view-changing. In the preprocessing stage, the shading parameters required for the surface shaders, such as surface color, normal, depth, ambient/diffuse/specular coefficients, and roughness, are cached into multiple deep framebuffers generated by several caching cameras which are created in an automatic manner. When the user designs the lighting setup, the relighting renderer builds a map to connect a screen pixel for the current rendering camera to the corresponding deep framebuffer pixel and then computes illumination at each pixel with the cache values taken from the deep framebuffers. All the relighting computations except the deep framebuffer pre-computation are carried out at interactive rates by the GPU.

• International Journal of Naval Architecture and Ocean Engineering
• /
• v.11 no.1
• /
• pp.448-461
• /
• 2019

Changes in gravity and buoyancy of a Full Ocean Depth Autonomous Underwater Vehicle (FOD-AUV) during its descending and ascending process must be considered very carefully compared with a Human Occupied Vehicle (HOV) or a Remotely Pperated Vehicle (ROV) whose activities rely on human decision. We firstly designed a two-step weight dropping pattern to achieve a high descending and ascending efficiency and a gravity-buoyancy balance at designed depth. The static equations showed that gravity acceleration, seawater density and displacement are three key aspects affecting the balance. Secondly, we try our best to analysis the gravity and buoyancy changing according to the previous known scientific information, such as anomaly of gravity acceleration, changing of seawater states. Finally, we drew conclusion that gravity changes little (no more than 0.1kgf, it is impossible to give a accurate value). A density-depth relationship at the Challenger Deep was acquired and the displacement changing of the FOD-AUV was calculated preciously.

• Journal of Korea Multimedia Society
• /
• v.22 no.9
• /
• pp.1000-1010
• /
• 2019

Image semantic segmentation and dehazing are key tasks in the computer vision. In recent years, researches in both tasks have achieved substantial improvements in performance with the development of Convolutional Neural Network (CNN). However, most of the previous works for semantic segmentation assume the images are captured in clear weather and show degraded performance under hazy images with low contrast and faded color. Meanwhile, dehazing aims to recover clear image given observed hazy image, which is an ill-posed problem and can be alleviated with additional information about the image. In this work, we propose a deep multi-task network for simultaneous semantic segmentation and dehazing. The proposed network takes single haze image as input and predicts dense semantic segmentation map and clear image. The visual information getting refined during the dehazing process can help the recognition task of semantic segmentation. On the other hand, semantic features obtained during the semantic segmentation process can provide cues for color priors for objects, which can help dehazing process. Experimental results demonstrate the effectiveness of the proposed multi-task approach, showing improved performance compared to the separate networks.

• Journal of Korean Association for Spatial Structures
• /
• v.23 no.3
• /
• pp.4-10
• /
• 2023

• IEIE Transactions on Smart Processing and Computing
• /
• v.6 no.1
• /
• pp.53-59
• /
• 2017

Optical character recognition (OCR) automatically recognizes text in an image. OCR is still a challenging problem in computer vision. A successful solution to OCR has important device applications, such as text-to-speech conversion and automatic document classification. In this work, we analyze character recognition performance using the current state-of-the-art deep-learning structures. One is the AlexNet structure, another is the LeNet structure, and the other one is the SPNet structure. For this, we have built our own dataset that contains digits and upper- and lower-case characters. We experiment in the presence of salt-and-pepper noise or Gaussian noise, and report the performance comparison in terms of recognition error. Experimental results indicate by five-fold cross-validation that the SPNet structure (our approach) outperforms AlexNet and LeNet in recognition error.

• Journal of Korea Multimedia Society
• /
• v.22 no.10
• /
• pp.1149-1159
• /
• 2019

We present a novel deep learning architecture for obtaining a latent image from a single blurry image, which contains dynamic motion blurs through object/camera movements. The proposed architecture consists of two sub-modules: blur image restoration and optical flow estimation. The tasks are highly related in that object/camera movements make cause blurry artifacts, whereas they are estimated through optical flow. The ablation study demonstrates that training multi-task architecture simultaneously improves both tasks compared to handling them separately. Objective and subjective evaluations show that our method outperforms the state-of-the-arts deep learning based techniques.

• Journal of Biomedical Engineering Research
• /
• v.43 no.5
• /
• pp.341-352
• /
• 2022

Medical image segmentation is the most important task in radiation therapy. Especially, when segmenting medical images, the liver is one of the most difficult organs to segment because it has various shapes and is close to other organs. Therefore, automatic segmentation of the liver in computed tomography (CT) images is a difficult task. Since tumors also have low contrast in surrounding tissues, and the shape, location, size, and number of tumors vary from patient to patient, accurate tumor segmentation takes a long time. In this study, we propose a method algorithm for automatically segmenting the liver and tumor for this purpose. As an advantage of setting the boundaries of the tumor, the liver and tumor were automatically segmented from the CT image using the 2D CoordConv DeepLab V3+ model using the CoordConv layer. For tumors, only cropped liver images were used to improve accuracy. Additionally, to increase the segmentation accuracy, augmentation, preprocess, loss function, and hyperparameter were used to find optimal values. We compared the CoordConv DeepLab v3+ model using the CoordConv layer and the DeepLab V3+ model without the CoordConv layer to determine whether they affected the segmentation accuracy. The data sets used included 131 hepatic tumor segmentation (LiTS) challenge data sets (100 train sets, 16 validation sets, and 15 test sets). Additional learned data were tested using 15 clinical data from Seoul St. Mary's Hospital. The evaluation was compared with the study results learned with a two-dimensional deep learning-based model. Dice values without the CoordConv layer achieved 0.965 ± 0.01 for liver segmentation and 0.925 ± 0.04 for tumor segmentation using the LiTS data set. Results from the clinical data set achieved 0.927 ± 0.02 for liver division and 0.903 ± 0.05 for tumor division. The dice values using the CoordConv layer achieved 0.989 ± 0.02 for liver segmentation and 0.937 ± 0.07 for tumor segmentation using the LiTS data set. Results from the clinical data set achieved 0.944 ± 0.02 for liver division and 0.916 ± 0.18 for tumor division. The use of CoordConv layers improves the segmentation accuracy. The highest of the most recently published values were 0.960 and 0.749 for liver and tumor division, respectively. However, better performance was achieved with 0.989 and 0.937 results for liver and tumor, which would have been used with the algorithm proposed in this study. The algorithm proposed in this study can play a useful role in treatment planning by improving contouring accuracy and reducing time when segmentation evaluation of liver and tumor is performed. And accurate identification of liver anatomy in medical imaging applications, such as surgical planning, as well as radiotherapy, which can leverage the findings of this study, can help clinical evaluation of the risks and benefits of liver intervention.

• Korean Journal of Remote Sensing
• /
• v.38 no.5_1
• /
• pp.511-521
• /
• 2022

Cloud detection and removal from satellite images is an essential process for topographic observation and analysis. Threshold-based cloud detection techniques show stable performance because they detect using the physical characteristics of clouds, but they have the disadvantage of requiring all channels' images and long computational time. Cloud detection techniques using deep learning, which have been studied recently, show short computational time and excellent performance even using only four or less channel (RGB, NIR) images. In this paper, we confirm the performance dependence of the deep learning network according to the heterogeneous learning dataset with different resolutions. The DeepLabV3+ network was improved so that channel features of cloud detection were extracted and learned with two published heterogeneous datasets and mixed data respectively. As a result of the experiment, clouds' Jaccard index was low in a network that learned with different kind of images from test images. However, clouds' Jaccard index was high in a network learned with mixed data that added some of the same kind of test data. Clouds are not structured in a shape, so reflecting channel features in learning is more effective in cloud detection than spatial features. It is necessary to learn channel features of each satellite sensors for cloud detection. Therefore, cloud detection of heterogeneous sensors with different resolutions is very dependent on the learning dataset.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.17 no.3
• /
• pp.177-183
• /
• 2022

To measure the size and weight of the fish, we developed an automatic fish size measurement system using a deep neural network, where the YOLO (You Only Look Once)v3 model was used. To detect fish, an IP camera with infrared function was installed over the fish pool to acquire image data and used as input data for the deep neural network. Using the bounding box information generated as a result of detecting the fish and the structure for which the actual length is known, the size of the fish can be obtained. A GUI (Graphical User Interface) program was implemented using LabVIEW and RTSP (Real-Time Streaming protocol). The automatic fish size measurement system shows the results and stores them in a database for future work.