• Journal of Information Technology Applications and Management
• /
• v.13 no.1
• /
• pp.137-147
• /
• 2006

Spatiotemporal data are records of the spatial changes of moving objects over time. Most data in corporate databases have a spatiotemporal nature, but they are typically treated as merely descriptive semantic data without considering their potential visual (or cartographic) representation. Businesses such as geographical CRM, location-based services, and technologies like GPS and RFID depend on the storage and analysis of spatiotemporal data. Effectively handling the data analysis process may be accomplished through spatiotemporal data warehouse and spatial OLAP. This paper proposes a multidimensional model for spatiotemporal data analysis, and cartographically represents the results of the analysis.

• ETRI Journal
• /
• v.33 no.2
• /
• pp.295-298
• /
• 2011

We propose a motion-compensated frame interpolation method in which an accurate backward/forward motion vector pair (MVP) is estimated based on a parabolic motion model. A reliability measure for an MVP is also proposed to select the most reliable MVP for each interpolated block. The possibility of deformation of bidirectional corresponding blocks is estimated from the selected MVP. Then, each interpolated block is produced by combining corresponding blocks with the weights based on the possibility of deformation. Experimental results show that the proposed method improves PSNR performance by up to 2.8 dB as compared to conventional methods and achieves higher visual quality without annoying blockiness artifacts.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2012.11a
• /
• pp.552-555
• /
• 2012

The main goal of this paper is to develop a robust visual tracking algorithm with particle filtering. Visual Tracking with particle filter technique is not easy task due to cluttered environment, illumination changes. To deal with these problems, we develop an efficient observation model for target tracking with particle filter. We develop a robust phase correlation combined with motion information based observation model for particle filter framework. Phase correlation provides straight-forward estimation of rigid translational motion between two images, which is based on the well-known Fourier shift property. Phase correlation has the advantage that it is not affected by any intensity or contrast differences between two images. On the other hand, motion cue is also very well known technique and widely used due to its simplicity. Therefore, we apply the phase correlation integrated with motion information in particle filter framework for robust tracking. In experimental results, we show that tracking with multiple cues based model provides more reliable performance than single cue.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.17 no.6
• /
• pp.347-353
• /
• 2022

In this paper, we propose a method that performs a text-video retrieval model by replacing video properties using captions. In general, the exisiting embedding-based models consist of both joint embedding space construction and the CNN-based video encoding process, which requires a lot of computation in the training as well as the inference process. To overcome this problem, we introduce a video-captioning module to replace the visual property of video with captions generated by the video-captioning module. To be specific, we adopt the caption generator that converts candidate videos into captions in the inference process, thereby enabling direct comparison between the text given as a query and candidate videos without joint embedding space. Through the experiment, the proposed model successfully reduces the amount of computation and inference time by skipping the visual processing process and joint embedding space construction on two benchmark dataset, MSR-VTT and VATEX.

• Journal of Institute of Control, Robotics and Systems
• /
• v.20 no.6
• /
• pp.606-611
• /
• 2014

The understanding of another's behavior is a fundamental cognitive ability for primates including humans. Recent neuro-physiological studies suggested that there is a direct matching algorithm from visual observation onto an individual's own motor repertories for interpreting cognitive ability. The mirror neurons are known as core regions and are handled as a functionality of intent recognition on the basis of imitative learning of an observed action which is acquired from visual-information of a goal-directed action. In this paper, we addressed previous works used to model the function and mechanisms of mirror neurons and proposed a computational model of a mirror neuron system which can be used in human-robot interaction environments. The major focus of the computation model is the reproduction of an individual's motor repertory with different embodiments. The model's aim is the design of a continuous process which combines sensory evidence, prior task knowledge and a goal-directed matching of action observation and execution. We also propose a biologically inspired plausible equation model.

• Proceedings of the KSME Conference
• /
• 2008.11b
• /
• pp.2862-2867
• /
• 2008

High-temperature components of gas turbine operated for certain period of time can be reused by being repaired or rejuvenated. In case of the gas turbine combustion liners, the biggest and the most important one in the high-temperature components, come in a repair shop after operated for 8,000 or 12,000 hours according to the model and go through the repair and rejuvenation in order to be reused. A stated combustion liner is the first channel which has the combustion gas reached a nozzle from a fuel nozzle. Materials and coating properties of old and new model combustion liners were investigated. To repair these components after the visual inspection, the coatings of combustion liners were removed and then FPI(Fluorescent Penetrant Inspection), a kind of the NDI(Non-Destructive Inspection), was conducted. Damage patterns and the number of the damaged components were classified and analyzed based on data provided from the visual inspection over a long period of time. Focusing on the difference between old model and new model combustion liners, we analyzed the damage distribution and changes and consequently concluded that new model combustion liner would increase repair rate.

• ETRI Journal
• /
• v.46 no.1
• /
• pp.22-34
• /
• 2024

Exposure to varied noisy environments impairs the recognition performance of artificial intelligence-based speech recognition technologies. Degraded-performance services can be utilized as limited systems that assure good performance in certain environments, but impair the general quality of speech recognition services. This study introduces an audiovisual speech recognition (AVSR) model robust to various noise settings, mimicking human dialogue recognition elements. The model converts word embeddings and log-Mel spectrograms into feature vectors for audio recognition. A dense spatial-temporal convolutional neural network model extracts features from log-Mel spectrograms, transformed for visual-based recognition. This approach exhibits improved aural and visual recognition capabilities. We assess the signal-to-noise ratio in nine synthesized noise environments, with the proposed model exhibiting lower average error rates. The error rate for the AVSR model using a three-feature multi-fusion method is 1.711%, compared to the general 3.939% rate. This model is applicable in noise-affected environments owing to its enhanced stability and recognition rate.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.21 no.1
• /
• pp.1-11
• /
• 1997

Austomated visual inspection(AVI) capability has become an important key component in the automated manufacturing system. In such a visual inspection system an intensity(or color) image of a scene is quickly affected by optical property of objects, condition and roughness of surface, lens and filters, image sensor property and lighting system. In particular, the lighting system disign is the most important factor, since it affects overall performance of the visual system. For fast and cheap automated visual inspection system it is important to obtain the good image quality which results from careful attention to the design of the lighting system. In this paper, the lighting subsystem of AVI system is analysed for the inspection of printed circuit board(PCB) patterns. The spectral reflectance of materials, which are composed of PCB, is measured for choosing the light source. The reflection property is theoretically obtained by a reflection model and also obtained by experiments which measure intensity with varying the viewing direction of image sensor and the lighting direction of illuminator. The illumination uniformity of a ring-type illuminator. The lighting system is designed based upon the experimental results and theoretial analysis.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.3 no.4
• /
• pp.344-365
• /
• 2009

The performance of a tracking system is greatly increased if multiple types of sensors are combined to achieve the objective of the tracking instead of relying on single type of sensor. To conduct the multi-modal tracking, we have previously developed a multi-modal sensor-based tracking model where acoustic sensors mainly track the objects and visual sensors compensate the tracking errors [1]. In this paper, we find a network synchronization problem appearing in the developed tracking system. The problem is caused by the different location and traffic characteristics of multi-modal sensors and non-synchronized arrival of the captured sensor data at a processing server. To effectively deliver the sensor data, we propose a time-based packet aggregation algorithm where the acoustic sensor data are aggregated based on the sampling time and sent to the server. The delivered acoustic sensor data is then compensated by visual images to correct the tracking errors and such a compensation process improves the tracking accuracy in ideal case. However, in real situations, the tracking improvement from visual compensation can be severely degraded due to the aforementioned network synchronization problem, the impact of which is analyzed by simulations in this paper. To resolve the network synchronization problem, we differentiate the service level of sensor traffic based on Weight Round Robin (WRR) scheduling at the routers. The weighting factor allocated to each queue is calculated by a proposed Delay-based Weight Allocation (DWA) algorithm. From the simulations, we show the traffic differentiation model can mitigate the non-synchronization of sensor data. Finally, we analyze expected traffic behaviors of the tracking system in terms of acoustic sampling interval and visual image size.

• The Transactions of the Korea Information Processing Society
• /
• v.6 no.4
• /
• pp.1022-1031
• /
• 1999

In this paper, we propose the framework of a visual language named VIOLA(VIsual Object-oriented Language for Multimedia Applications), which is developed for web authoring. VIOLA supports the user to construct HTML documents and CGI programs even if he/she doesn't know exact HTML tags and CGI programming. VIOLA, a user interface building part and a programming logic building part are combined by the data-flow model. the user interface building part provides direct manipulation and a WSIKWYG interface, and the program logic building part provides more intuitive interface by using predefined classes and the data-flow model. thus, even a novice user can construct sophisticated applications by simply moving or clicking the mouse. several classes which generate CGI codes are predefined, and they are represented with highly abstracted visual components, By reusing predefined classes, CGI codes are automatically generated. In VIOLA, all major steps in builidng generated wit HTML documents and Java CGI programs.