• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.41 no.6
• /
• pp.19-24
• /
• 2004

A novel fast parallel NTGST is proposed for high resolution computer vision inspection of the BLUs in a LCD production line. The conventional computation- intensive NTGST algorithm is modified and its C codes are optimized into fast NTGST to be adapted to the SIMD parallel architecture. And then, the input inspection image is partitioned and allocated to each of the P processors in multi-threaded implementation, and the NTGST is executed on SIMD architecture of N data items simultaneously in each thread. Thus, the proposed inspection system can achieve the speedup of O(NP). Experiments using Dual-Pentium III processor with its MMX and extended MMX SIMD technology show that the proposed parallel NTGST is about Sp=8 times faster than the conventional NTGST, which shows the scalability of the proposed system implementation for the fast, high resolution computer vision inspection of the various sized BLUs in LCD production lines.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.21 no.1
• /
• pp.49-54
• /
• 2011

In this paper, we represent a mobile robot which can recognize chemical odor, measure concentration, and track its source indoors. The mobile robot has the function of smell that can sort several gases in experiment such as ammonia, ethanol, and their mixture with neural network algorithm and measure each gas concentration with fuzzy rules. In addition, it can not only navigate to the desired position with vision system by avoiding obstacles but also transmit odor information and warning messages earned from its own operations to other nodes by multi-hop communication in wireless sensor network. We suggest the way of odor sorting, concentration measurement, and source tracking for a mobile robot in wireless sensor network using a hybrid algorithm with vision system and gas sensors. The experimental studies prove that the efficiency of the proposed algorithm for odor recognition, concentration measurement, and source tracking.

• Smart Structures and Systems
• /
• v.31 no.4
• /
• pp.325-334
• /
• 2023

Computer vision-based damage detection enables non-contact, efficient and low-cost bridge health monitoring, which reduces the need for labor-intensive manual inspection or that for a large number of on-site sensing instruments. By leveraging recent semantic segmentation approaches, we can detect regions of critical structural components and identify damages at pixel level on images. However, existing methods perform poorly when detecting small and thin damages (e.g., cracks); the problem is exacerbated by imbalanced samples. To this end, we incorporate domain knowledge to introduce a hierarchical semantic segmentation framework that imposes a hierarchical semantic relationship between component categories and damage types. For instance, certain types of concrete cracks are only present on bridge columns, and therefore the noncolumn region may be masked out when detecting such damages. In this way, the damage detection model focuses on extracting features from relevant structural components and avoid those from irrelevant regions. We also utilize multi-scale augmentation to preserve contextual information of each image, without losing the ability to handle small and/or thin damages. In addition, our framework employs an importance sampling, where images with rare components are sampled more often, to address sample imbalance. We evaluated our framework on a public synthetic dataset that consists of 2,000 railway bridges. Our framework achieves a 0.836 mean intersection over union (IoU) for structural component segmentation and a 0.483 mean IoU for damage segmentation. Our results have in total 5% and 18% improvements for the structural component segmentation and damage segmentation tasks, respectively, compared to the best-performing baseline model.

• SUVANNABHUMI
• /
• v.10 no.1
• /
• pp.63-91
• /
• 2018

One of the goals of this article is to continue the momentum begun by emerging scholarship on theory and practice of writing about visual culture of and in Southeast Asia. I hope to offer culturally sensitive and embodied ways of looking at images and objects as sites/sights of cultural knowledge as further theoretical intervention. The argument put forward in my essay is three-fold: first, I critique the prevailing logocentric approach in the field of Southeast Asian Studies and I argue that in a postcolonial, global, and transnational period, it is important to be inclusive of other objects as sites/sights of social, political and cultural analysis beyond written and oral texts. Second, I argue that although it has its own political and theoretical problems, the evolving field of Visual Studies as it is practiced in the United States is one of many ways to decolonize the prevailing logocentric approach to Southeast Asian Studies. Third, I argue that if one reads these Euro-American derived theories of vision and visuality through the lens of what Walter Mignolo calls "colonial difference(s)," then Visual Studies as an evolving field has the potential to offer more nuanced local ways of looking at and understanding objects, vision, and visuality. Last, I point out that unlike in the West where there is an understanding of pure, objective and empirical vision, local Southeast Asian perspectives on objects and visions are more embodied and multi-sensorial. I argue that if one is ethically mindful of the local cultural ways of seeing and knowing objects, then the evolving field of Visual Studies offers a much-needed intervention to the privileged, lingering logocentric approach to Southeast Asian Studies. Moreover, these alternative methods might help to decolonize method and theory in academic disciplines that were invented during the colonial period.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.2
• /
• pp.311-326
• /
• 2024

The rapid development of neural network technology promotes the neural network model driven by big data to overcome the texture effect of complex objects. Due to the limitations in complex scenes, it is necessary to establish custom template matching and apply it to the research of many fields of computational vision technology. The dependence on high-quality small label sample database data is not very strong, and the machine learning system of deep feature connection to complete the task of texture effect inference and speculation is relatively poor. The style transfer algorithm based on neural network collects and preserves the data of patterns, extracts and modernizes their features. Through the algorithm model, it is easier to present the texture color of patterns and display them digitally. In this paper, according to the texture effect reasoning of custom template matching, the 3D visualization of the target is transformed into a 3D model. The high similarity between the scene to be inferred and the user-defined template is calculated by the user-defined template of the multi-dimensional external feature label. The convolutional neural network is adopted to optimize the external area of the object to improve the sampling quality and computational performance of the sample pyramid structure. The results indicate that the proposed algorithm can accurately capture the significant target, achieve more ablation noise, and improve the visualization results. The proposed deep convolutional neural network optimization algorithm has good rapidity, data accuracy and robustness. The proposed algorithm can adapt to the calculation of more task scenes, display the redundant vision-related information of image conversion, enhance the powerful computing power, and further improve the computational efficiency and accuracy of convolutional networks, which has a high research significance for the study of image information conversion.

• Journal of Advanced Navigation Technology
• /
• v.21 no.3
• /
• pp.251-257
• /
• 2017

Recently, hybrid positioning system combining GPS, vision sensor, and inertial sensor has drawn many attentions to estimate accurate vehicle positions. Since accurate multi-sensor fusion requires efficient time synchronization, this paper proposes an efficient method to obtain time synchronized measurements of vision sensor, inertial sensor, and OBD device based on GPS time information. In the proposed method, the time and position information is obtained by the GPS receiver, the attitude information is obtained by the inertial sensor, and the speed information is obtained by the OBD device. The obtained time, position, speed, and attitude information is converted to the color information. The color information is inserted to several corner pixels of the corresponding image frame. An experiment was performed with real measurements to evaluate the feasibility of the proposed method.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.12
• /
• pp.3976-3990
• /
• 2022

Currently, cross-attention is widely used in Siamese trackers to replace traditional correlation operations for feature fusion between template and search region. The former can establish a similar relationship between the target and the search region better than the latter for robust visual object tracking. But existing trackers using cross-attention only focus on rich semantic information of high-level features, while ignoring the appearance information contained in low-level features, which makes trackers vulnerable to interference from similar objects. In this paper, we propose a Multi-level Cross-attention Siamese network(MCSiam) to aggregate the semantic information and appearance information at the same time. Specifically, a multi-level cross-attention module is designed to fuse the multi-layer features extracted from the backbone, which integrate different levels of the template and search region features, so that the rich appearance information and semantic information can be used to carry out the tracking task simultaneously. In addition, before cross-attention, a target-aware module is introduced to enhance the target feature and alleviate interference, which makes the multi-level cross-attention module more efficient to fuse the information of the target and the search region. We test the MCSiam on four tracking benchmarks and the result show that the proposed tracker achieves comparable performance to the state-of-the-art trackers.

• Archives of design research
• /
• v.19 no.2 s.64
• /
• pp.91-98
• /
• 2006

The product convergence and complex application environment raise the need of multi-modal interface which enables us to interact products through various human senses. The sense of vision has been used predominantly more than any other senses for the traditional and general information gathering situation, but in the future which will be developed based on the digital network technology, the practical use of the various senses will be desired for more convenient and rational usage of the information appliances. The sense of auditory which possibility of practical use is becoming higher than ever with the sense of vision, the possible usage will be developed broader and in the various ways in the future. Based on this situation, the characteristics of the written language and the colloquial language and the comparative analysis of the difference between male and female's reaction for each language were examined through this study. To achieve this purpose, the literature research about the diverse components of the language system was peformed. Then, some peculiar characters of the sense of vision and auditory were reviewed and the appropriate experimentation was planned and carried out. The result of the accomplished experimentation was examined by the objective analysis method. The main results of this study are as follows: first, the reaction time for written language is shorter than colloquial language, second, there is a partial difference between the male's and female's reaction for those two stimuli, third, there is no selection bias between the sense of sight and the sense of hearing. I think the continuous development of the broad and diverse ways of study for various senses is needed based on this study.

• Journal of Korean Society of Archives and Records Management
• /
• v.17 no.2
• /
• pp.101-128
• /
• 2017

This study proposed an educational program using presidential records to develop the self-esteem of children from multi-cultural families in accordance with the vision of the Presidential Archives-including political, economic, historical, and cultural aspects-to activate programs for the underprivileged. To accomplish this, we performed a literature review of self-esteem-enhancing programs for such children, and compared and analyzed the Presidential Archives' educational programs of the United States and Korea. We also conducted a survey and interviewed teachers who have experienced teaching children from multi-cultural families. Through the process, this study proposed an educational program for such children to develop their self-esteem.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.43 no.5
• /
• pp.667-674
• /
• 2023

In the event of a disaster occurring within a building, the prompt and efficient evacuation and rescue of occupants within the building becomes the foremost priority to minimize casualties. For the purpose of such rescue operations, it is essential to ascertain the distribution of individuals within the building. Nevertheless, there is a primary dependence on accounts provided by pertinent individuals like building proprietors or security staff, alongside fundamental data encompassing floor dimensions and maximum capacity. Consequently, accurate determination of the number of occupants within the building holds paramount significance in reducing uncertainties at the site and facilitating effective rescue activities during the golden hour. This research introduces a methodology employing computer vision algorithms to count the number of occupants within distinct building locations based on images captured by installed multiple CCTV cameras. The counting methodology consists of three stages: (1) establishing virtual Lines of Interest (LOI) for each camera to construct a multi-camera network environment, (2) detecting and tracking people within the monitoring area using deep learning, and (3) aggregating counts across the multi-camera network. The proposed methodology was validated through experiments conducted in a five-story building with the average accurary of 89.9% and the average MAE of 0.178 and RMSE of 0.339, and the advantages of using multiple cameras for occupant counting were explained. This paper showed the potential of the proposed methodology for more effective and timely disaster management through common surveillance systems by providing prompt occupancy information.