• Journal of information and communication convergence engineering
• /
• v.9 no.1
• /
• pp.83-88
• /
• 2011

Abstract. Image segmentation is always a challenging task in computer vision as well as in pattern recognition. Nowadays, this method has great importance in the field of stereo vision. The disparity information extracting from the binocular image pairs has essential relevance in the fields like Stereoscopic (3D) Imaging Systems, Virtual Reality and 3D Graphics. The term 'disparity' represents the horizontal shift between left camera image and right camera image. Till now, many methods are proposed to visualize or estimate the disparity. In this paper, we present a new technique to visualize the horizontal disparity between two stereo images based on image segmentation method. The process of comparing left camera image with right camera image is popularly known as 'Stereo-Matching'. This method is used in the field of stereo vision for many years and it has large contribution in generating depth and disparity maps. Correlation based stereo-matching are used most of the times to visualize the disparity. Although, for few stereo image pairs it is easy to estimate the horizontal disparity but in case of some other stereo images it becomes quite difficult to distinguish the disparity. Therefore, in order to visualize the horizontal disparity between any stereo image pairs in more robust way, a novel stereo-matching algorithm is proposed which is named as "Quadtree Segmentation of Pixels Disparity Estimation (QSPDE)".

• Journal of IKEEE
• /
• v.27 no.3
• /
• pp.251-257
• /
• 2023

In this paper, we propose a dual-structured self-attention method that improves the lack of regional features of the vision transformer's self-attention. Vision Transformers, which are more computationally efficient than convolutional neural networks in object classification, object segmentation, and video image recognition, lack the ability to extract regional features relatively. To solve this problem, many studies are conducted based on Windows or Shift Windows, but these methods weaken the advantages of self-attention-based transformers by increasing computational complexity using multiple levels of encoders. This paper proposes a dual-structure self-attention using self-attention and neighborhood network to improve locality inductive bias compared to the existing method. The neighborhood network for extracting local context information provides a much simpler computational complexity than the window structure. CIFAR-10 and CIFAR-100 were used to compare the performance of the proposed dual-structure self-attention transformer and the existing transformer, and the experiment showed improvements of 0.63% and 1.57% in Top-1 accuracy, respectively.

• Information Systems Review
• /
• v.26 no.2
• /
• pp.205-221
• /
• 2024

In June 2023, the term "spatial computing" began gaining recognition among the public with Apple's Vision Pro announcement, and interest surged exponentially after its official release in February 2024. With the market opening up, there's a need to analyze public perception for sustainable growth of Spatial Computing and provide evidence-based strategies for industry and government response. This study explores domestic public perception of Spatial Computing using various text mining techniques and seeks strategic directions for successful market penetration based on the analysis. Significantly, the study contributes by leading research on Spatial Computing, proposing new research methodologies, and offering strategic and policy directions for stakeholders.

• Electronics and Telecommunications Trends
• /
• v.33 no.4
• /
• pp.33-42
• /
• 2018

Object classification and detection are fundamental technologies in computer vision and its applications. Recently, a deep-learning based approach has shown significant improvement in terms of object classification and detection. This report reviews the progress of deep-learning based object classification and detection in views of the ImageNet Large Scale Visual Recognition Challenge (ILSVRC), and analyzes recent trends of object classification and detection technology and its applications.

• Journal of Institute of Control, Robotics and Systems
• /
• v.17 no.3
• /
• pp.277-282
• /
• 2011

This paper describes a sensor fusion-based semantic map building which can improve the capabilities of a mobile robot in various domains including localization, path-planning and mapping. To build a semantic map, various environmental information, such as doors and cliff areas, should be extracted autonomously. Therefore, we propose a method to detect doors, cliff areas and robust visual features using a laser scanner and a vision sensor. The GHT (General Hough Transform) based recognition of door handles and the geometrical features of a door are used to detect doors. To detect the cliff area and robust visual features, the tilting laser scanner and SIFT features are used, respectively. The proposed method was verified by various experiments and showed that the robot could build a semantic map autonomously in various indoor environments.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2004.05b
• /
• pp.587-590
• /
• 2004

In this paper proposed a HMM(Hidden Martov Model)-based segmentation method which is able to model shadows as well as foreground and background regions. Shadow of moving objects often obstruct visual tracking. We propose an HMM-based segmentation method which classifies in real time oath objects. In the case of traffic monitoring movies, the effectiveness of the proposed method has been proven through experimental results

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.3
• /
• pp.490-493
• /
• 2021

This paper proposes an embedded system that detects mask and face recognition based on a microprocessor instead of Nvidia Jetson Board what is popular development kit. We use a class of efficient models called Mobilenets for mobile and embedded vision applications. MobileNets are based on a streamlined architechture that uses depthwise separable convolutions to build light weight deep neural networks. The device used a Maix development board with CNN hardware acceleration function, and the training model used MobileNet_V2 based SSD(Single Shot Multibox Detector) optimized for mobile devices. To make training model, 7553 face data from Kaggle are used. As a result of test dataset, the AUC (Area Under The Curve) value is as high as 0.98.

• Journal of the Society of Disaster Information
• /
• v.18 no.2
• /
• pp.269-279
• /
• 2022

Purpose: The purpose of this study is to develop a deep learning-based personal protective equipment detection model for disaster prevention at construction sites, and to apply it to actual construction sites and to analyze the results. Method: In the method of conducting this study, the dataset on the real environment was constructed and the developed personal protective equipment(PPE) detection model was applied. The PPE detection model mainly consists of worker detection and PPE classification model.The worker detection model uses a deep learning-based algorithm to build a dataset obtained from the actual field to learn and detect workers, and the PPE classification model applies the PPE detection algorithm learned from the worker detection area extracted from the work detection model. For verification of the proposed model, experimental results were derived from data obtained from three construction sites. Results: The application of the PPE recognition model to construction site brings up the problems related to mis-recognition and non-recognition. Conclusions: The analysis outcomes were produced to apply the object recognition technology to a construction site, and the need for follow-up research was suggested through representative cases of worker recognition and non-recognition, and mis-recognition of personal protective equipment.

• Journal of the Korea Society of Computer and Information
• /
• v.19 no.10
• /
• pp.35-42
• /
• 2014

It is possible to improve the obstacle avoidance capability by training and recognizing the obstacles which is in certain indoor environment. We propose the technique that use underlying intensity value along with intensity map from RGB-D image which is derived from stereo vision Kinect sensor and recognize an obstacle within constant distance. We test and experiment the accuracy and execution time of the pattern recognition algorithms like PCA, ICA, LDA, SVM to show the recognition possibility of it. From the comparison experiment between RGB-D data and intensity data, RGB-D data got 4.2% better accuracy rate than intensity data but intensity data got 29% and 31% faster than RGB-D in terms of training time and intensity data got 70% and 33% faster than RGB-D in terms of testing time for LDA and SVM, respectively. So, LDA, SVM have good accuracy and better training/testing time to use for obstacle avoidance based on intensity dataset of mobile robot.

• Journal of Broadcast Engineering
• /
• v.22 no.6
• /
• pp.774-784
• /
• 2017

Occupancy sensors installed in buildings and households turn off the light if the space is vacant. Currently PIR (pyroelectric infra-red) motion sensors have been utilized. Recently, the researches using camera sensors have been carried out in order to overcome the demerit of PIR that can not detect static people. If the tradeoff of cost and performance is satisfied, the camera sensors are expected to replace the current PIRs. In this paper, we propose vision sensor-based occupancy detection being composed of tracking, recognition and detection. Our softeware is designed to meet the real-time processing. In experiments, 14.5fps is achieved at 15fps USB input. Also, the detection accuracy reached 82.0%.