• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.9
• /
• pp.3204-3220
• /
• 2021

We perform the task of video object segmentation by incorporating a conditional random field (CRF) and convolutional neural networks (CNNs). Most methods employ a CRF to refine a coarse output from fully convolutional networks. Others treat the inference process of the CRF as a recurrent neural network and then combine CNNs and the CRF into an end-to-end model for video object segmentation. In contrast to these methods, we propose a novel higher-order CRF model to solve the problem of video object segmentation. Specifically, we use CNNs to establish a higher-order dependence among pixels, and this dependence can provide critical global information for a segmentation model to enhance the global consistency of segmentation. In general, the optimization of the higher-order energy is extremely difficult. To make the problem tractable, we decompose the higher-order energy into two parts by utilizing auxiliary variables and then solve it by using an iterative process. We conduct quantitative and qualitative analyses on multiple datasets, and the proposed method achieves competitive results.

• Journal of the Ergonomics Society of Korea
• /
• v.34 no.5
• /
• pp.541-548
• /
• 2015

Objective: We introduce a hand gesture segmentation method using a wrist-worn wearable device which can recognize simple gestures of clenching and unclenching ones' fist. Background: There are many types of smart watches and fitness bands in the markets. And most of them already adopt a gesture interaction to provide ease of use. However, there are many cases in which the malfunction is difficult to distinguish between the user's gesture commands and user's daily life motion. It is needed to develop a simple and clear gesture segmentation method to improve the gesture interaction performance. Method: At first, we defined the gestures of making a fist (start of gesture command) and opening one's fist (end of gesture command) as segmentation gestures to distinguish a gesture. The gestures of clenching and unclenching one's fist are simple and intuitive. And we also designed a single gesture consisting of a set of making a fist, a command gesture, and opening one's fist in order. To detect segmentation gestures at the bottom of the wrist, we used a wrist strap on which an array of infrared sensors (emitters and receivers) were mounted. When a user takes gestures of making a fist and opening one's a fist, this changes the shape of the bottom of the wrist, and simultaneously changes the reflected amount of the infrared light detected by the receiver sensor. Results: An experiment was conducted in order to evaluate gesture segmentation performance. 12 participants took part in the experiment: 10 males, and 2 females with an average age of 38. The recognition rates of the segmentation gestures, clenching and unclenching one's fist, are 99.58% and 100%, respectively. Conclusion: Through the experiment, we have evaluated gesture segmentation performance and its usability. The experimental results show a potential for our suggested segmentation method in the future. Application: The results of this study can be used to develop guidelines to prevent injury in auto workers at mission assembly plants.

• International journal of advanced smart convergence
• /
• v.12 no.2
• /
• pp.108-116
• /
• 2023

Smart home and artificial intelligence technologies are developing rapidly, and various smart home systems associated with artificial intelligence (AI) improved the quality of living for people. In the present research, we examine the role of individuals' motivational system in their responses to the application of AI in smart homes. In particular, this research focuses on individuals' prevention motivational system and investigates whether individuals' attitudes toward the application of AI in smart homes differ according to their level of prevention motivation. Specifically, it is hypothesized that individuals with strong (vs. weak) prevention motivation will have more favorable attitudes toward the application of AI in smart homes. Consistent with the hypothesis, the results reveal that the respondents in the strong (vs. weak) prevention motivation reported significantly more favorable attitudes toward the six types of AI-based application in smart homes (e.g., AIbased AR/VR games, AI pet care system, AI robots, etc.). Our findings suggest that individuals' prevention motivational system may be an effective market segmentation tool in facilitating their positive responses to the application of AI in smart homes.

• Journal of the Semiconductor & Display Technology
• /
• v.15 no.1
• /
• pp.33-35
• /
• 2016

This paper proposes a method utilizing image compression and transmission method for image segmentation in order to reduce the time required in the process of analyzing the image information that has in the image compression process. Many studies of existing with respect to the image segmentation are being studied as a way to split a lot of a particular part in the image. We divide full image into the N equal parts. And it is compressed using the field coding. This will reduce the time-consuming than using the conventional method.

• International journal of advanced smart convergence
• /
• v.11 no.2
• /
• pp.102-107
• /
• 2022

Smart home systems for safety and security are in high demand and always needed for many reasons including people's desire to feel safe in their own houses and to avoid a high rate of crime. In the current research, we investigate the role of individuals' motivational orientation to prevention in their responses to smart home systems for safety and security. That is, this research examines whether individuals' attitudes toward smart home systems for safety and security vary depending on their level of prevention orientation. Specifically, it is hypothesized that individuals with strong (vs. weak) prevention orientation will have more positive attitudes toward smart home systems for safety and security. In support of the hypothesis, the results indicate that respondents in the strong (vs. weak) prevention orientation reported significantly more positive attitudes toward smart home systems for safety and security. Our findings imply that individuals' motivational orientation to prevention may be an effective marketing and segmentation tool in facilitating their favorable responses to the smart home systems for safety and security.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.33 no.6
• /
• pp.605-614
• /
• 2015

Drone imaging, which is more cost-effective and controllable compared to airborne LiDAR, requires a low-cost camera and is used for capturing color images. From the overlapped color images, we produced two high-resolution digital surface models over different test areas. After segmentation, we performed tree identification according to the method proposed by , and computed the tree height and the canopy crown size. Compared with the field measurements, the computed results for the tree height in test area 1 (coniferous trees) were found to be accurate, while the results in test area 2 (deciduous coniferous trees) were found to be underestimated. The RMSE of the tree height was 0.84 m, and the width of the canopy crown was 1.51 m in test area 1. Further, the RMSE of the tree height was 2.45 m, and the width of the canopy crown was 1.53 m in test area 2. The experiment results validated the use of drone images for the extraction of a tree structure.

• Journal of Digital Contents Society
• /
• v.19 no.8
• /
• pp.1453-1462
• /
• 2018

In this paper, we look photographes of costumes and composed them as image files by extracting only costume part of the photograph excluding the background part. And we calculated representative color value to implement smart costume coordination program using complementary colors corresponding to representative color values in the costume area. And then, We have solved the problem of over-segmentation caused by extracting the costumes area by applying an anisotropic diffusion algorithm that can remove the noise of the image and flatten the gradient. In order to satisfy users' various needs, we plan to add not only complementary colors coordination but also more various color scheme.

• Smart Media Journal
• /
• v.11 no.11
• /
• pp.40-48
• /
• 2022

In this paper, an educational kit that can be used in AI education was developed to solve the difficulties of AI education. Through this, object detection and person detection in computer vision using CNN and OpenCV to learn practical-oriented experiences from theory-centered and user image recognition (Your Own) that learns and recognizes specific objects Image Recognition), user object classification (Segmentation) and segmentation (Classification Datasets), IoT hardware control that attacks the learned target, and Jetson Nano GPIO, an AI board, are developed and utilized to develop and utilize textbooks that help effective AI learning made it possible.

• IEIE Transactions on Smart Processing and Computing
• /
• v.1 no.3
• /
• pp.125-132
• /
• 2012

This paper proposes an automatic object segmentation and background composition method for video communication over consumer mobile phones. The object regions were extracted based on the motion and color variance of the first two frames. To combine the motion and variance information, the Euclidean distance between the motion boundary pixel and the neighboring color variance edge pixels was calculated, and the nearest edge pixel was labeled to the object boundary. The labeling results were refined using the morphology for a more accurate and natural-looking boundary. The grow-cut segmentation algorithm begins in the expanded label map, where the inner and outer boundary belongs to the foreground and background, respectively. The segmented object region and a new background image stored a priori in the mobile phone was then composed. In the background composition process, the background motion was measured using the optical-flow, and the final result was synthesized by accurately locating the object region according to the motion information. This study can be considered an extended, improved version of the existing background composition algorithm by considering motion information in a video. The proposed segmentation algorithm reduces the computational complexity significantly by choosing the minimum resolution at each segmentation step. The experimental results showed that the proposed algorithm can generate a fast, accurate and natural-looking background composition.

• Smart Structures and Systems
• /
• v.29 no.1
• /
• pp.1-16
• /
• 2022

Despite recent breakthroughs in deep learning and computer vision fields, the pixel-wise identification of tiny objects in high-resolution images with complex disturbances remains challenging. This study proposes a modified U-net for tiny crack segmentation in real-world steel-box-girder bridges. The modified U-net adopts the common U-net framework and a novel Self-Attention-Self-Adaption (SASA) neuron as the fundamental computing element. The Self-Attention module applies softmax and gate operations to obtain the attention vector. It enables the neuron to focus on the most significant receptive fields when processing large-scale feature maps. The Self-Adaption module consists of a multiplayer perceptron subnet and achieves deeper feature extraction inside a single neuron. For data augmentation, a grid-based crack random elastic deformation (CRED) algorithm is designed to enrich the diversities and irregular shapes of distributed cracks. Grid-based uniform control nodes are first set on both input images and binary labels, random offsets are then employed on these control nodes, and bilinear interpolation is performed for the rest pixels. The proposed SASA neuron and CRED algorithm are simultaneously deployed to train the modified U-net. 200 raw images with a high resolution of 4928 × 3264 are collected, 160 for training and the rest 40 for the test. 512 × 512 patches are generated from the original images by a sliding window with an overlap of 256 as inputs. Results show that the average IoU between the recognized and ground-truth cracks reaches 0.409, which is 29.8% higher than the regular U-net. A five-fold cross-validation study is performed to verify that the proposed method is robust to different training and test images. Ablation experiments further demonstrate the effectiveness of the proposed SASA neuron and CRED algorithm. Promotions of the average IoU individually utilizing the SASA and CRED module add up to the final promotion of the full model, indicating that the SASA and CRED modules contribute to the different stages of model and data in the training process.