• Journal of Information Processing Systems
• /
• v.19 no.1
• /
• pp.80-88
• /
• 2023

RGB-thermal (RGB-T) tracking using unmanned aerial vehicles (UAVs) involves challenges with regards to the similarity of objects, occlusion, fast motion, and motion blur, among other issues. In this study, we propose dynamic tracking aggregation (DTA) as a unified framework to perform object detection and data association. The proposed approach obtains fused features based a transformer model and an L1-norm strategy. To link the current frame with recent information, a dynamically updated embedding called dynamic tracking identification (DTID) is used to model the iterative tracking process. For object association, we designed a long short-term tracking aggregation module for dynamic feature propagation to match spatial and temporal embeddings. DTA achieved a highly competitive performance in an experimental evaluation on public benchmark datasets.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2008.05a
• /
• pp.253-259
• /
• 2008

RFID is a generic term for technologies which use RF waves to identify, track, or categorize any object. A radio frequency identification (RFID) reader recognizes objects through wireless communications with RFID tags. Tag collision arbitration for passive tags is a significant issue for fast tag identification due to communication over a shared wireless channel. One of the research areas in RFID system is a tag anti-collision protocol. In this paper, various anti-collision protocols are discussed. The pros and cons of different anti-collision protocols are compared with each other and their performance is analyzed and the better performance anti-collision protocol is suggested.

• Publications of The Korean Astronomical Society
• /
• v.12 no.1
• /
• pp.185-196
• /
• 1997

We present a code which identifies individual clouds in crowded region using IMFORT interface within Image Reduction and Analysis Facility (IRAF). We define a cloud as an object composed of all pixels in longitude, latitude, and velocity that are simply connected and that lie above some threshold temperature. The code searches the whole pixels of the data cube in efficient way to isolate individual clouds. Along with identification of clouds it is designed to estimate their mean values of longitudes, latitudes, and velocities. In addition, a function of generating individual images (or cube data) of identified clouds is added up. We also present identified individual clouds using a $^{12}CO$ survey data cube of Galactic Anticenter Region (Lee et al. 1997) as a test example. We used a threshold temperature of $5\sigma$ rms noise level of the data With a higher threshold temperature, we isolated subclouds of a huge cloud identified originally. As the most important parameter to identify clouds is the threshold value, its effect to the size and velocity dispersion is discussed rigorously.

• 한국HCI학회:학술대회논문집
• /
• 2008.02a
• /
• pp.693-696
• /
• 2008

Motion blurs are caused by relative motion between the camera and the scene. The blurred image needs to be restored because undesired blur effect degrades the quality of the image. In this paper, we propose a new method for the identification of blur parameters. Experiment shows that the proposed method identifies blur extent regardless of the size of the blur and the object in the original image.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.7 no.11
• /
• pp.2690-2701
• /
• 2013

Humans are able to recognize small number of people they know well by the way they walk. This ability represents basic motivation for using human gait as the means for biometric identification. Such biometric can be captured at public places from a distance without subject's collaboration, awareness or even consent. Although current approaches give encouraging results, we are still far from effective use in practical applications. In general, methods set various constraints to circumvent the influence factors like changes of view, walking speed, capture environment, clothing, footwear, object carrying, that have negative impact on recognition results. In this paper we investigate the influence of walking speed variation to different visual based gait recognition approaches and propose normalization based on geometric transformations, which mitigates its influence on recognition results. With the evaluation on MoBo gait dataset we demonstrate the benefits of using such normalization in combination with different types of gait recognition approaches.

• Journal of Korea Multimedia Society
• /
• v.10 no.10
• /
• pp.1251-1259
• /
• 2007

Motion blurs are caused by relative motion between the camera and the scene. The blurred image needs to be restored because undesired blur effect degrades the quality of the image. In this paper, we propose a new method for the identification of blur extent. Experiment shows that the proposed method identifies blur extent regardless of the size of the blur and the object in the original image.

• The Journal of the Society of Korean Medicine Diagnostics
• /
• v.19 no.2
• /
• pp.109-113
• /
• 2015

Byunzheng(辨證), 'Identification of Patterns' implies the process of identifying the original cause from symptoms and signs. Each symptom and sign has a meaning that manifests. But in Clinic, it is difficult to recognize the main cause through symptoms and signs by itself, because the patients complaint their symptoms differently. When considering Byunzheng, not only one symptom of one cause but relationship of manifested symptoms and causes are necessary. The object of Byunzheng is to diagnose Illness and disease through symptoms and signs and to coordinate Therapeutic Methods by Byunzheng. In Byunzheng, there are patterns according to the function of Internal Organs(臟腑), the Channels, the Eight Principles, the Five Elements and etc. Process to Diagnose Byunzheng is the most important. Until present, it is not clear to conclude the Byunzheng process or criteria. In certain case of Byunzheng is recognized by doctor's intuition, but most case is needed for conscious reasoning. Therefore, in this statement, process of conclude Byunzheng is reviewed rather than describing each character of Byunzheng.

• Textile Coloration and Finishing
• /
• v.25 no.4
• /
• pp.287-291
• /
• 2013

Nowadays, terms such as 'Smart Textile', 'Intelligent Textile' and 'Wearable Computing' are commonly used in everyday contexts. And radio-frequency identification (RFID) is the use of a wireless non-contact system that uses radio-frequency electromagnetic fields to transfer data from a tag attached to an object, for the purposes of automatic identification and tracking. These products are required technologies which are textile treatments, printing, ink, etc. Durability of textile substrates is an essential marker for conductive ink printing process. Especially, heat stability is important, since conductive ink should be processable (annealing, curing) at temperatures below $150^{\circ}C$. This study was application of RFID on textiles. The textile pre-treatment processes should be carried out to use RFID antenna on textiles.

• Journal of the Korean Society of Safety
• /
• v.11 no.2
• /
• pp.143-149
• /
• 1996

We propose an Opto-Digital hybrid fingerprint Identification system based on the binary phase extraction joint transform correlator(BPEJTC) for validation and security yerification. It is shown that since the BPEJTC provides higher peak-to-sidelobe ratio than that of the conventional JTC and does not cause correlation peaks due to intra-class association, this system is well-adaptive to the multiple object environments. Experimental results show that this system has a good performance in the presence of multiple images and the variations of the same person.

• Journal of the Korean Society of Industry Convergence
• /
• v.24 no.1
• /
• pp.1-7
• /
• 2021

In this paper, we presented the experimental basis for the theoretical background and robustness of the Convolutional Neural Network for object recognition based on artificial intelligence. An experimental result was performed to visualize the weighting filters and feature maps for each layer to determine what characteristics CNN is automatically generating. experimental results were presented on the trend of learning error and identification error rate by checking the relevance of the weight filter and feature map for learning error and identification error. The weighting filter and characteristic map are presented as experimental results. The automatically generated characteristic quantities presented the results of error rates for moving and rotating robustness to geometric changes.