• Proceedings of the Korea Information Processing Society Conference
• /
• 2021.11a
• /
• pp.878-879
• /
• 2021

Most state-of-the-art CNNs for action recognition are based on a two-stream architecture: RGB frames stream represents the appearance and the optical flow stream interprets the motion of action. However, the cost of optical flow computation is very high and then it increases action recognition latency. We introduce a design strategy for action recognition inspired by a two-stream network and teacher-student architecture. There are two sub-networks in our neural networks, the optical flow sub-network as a teacher and the RGB frames sub-network as a student. In the training stage, we distill the feature from the teacher as a baseline to train student sub-network. In the test stage, we only use the student so that the latency reduces without computing optical flow. Our experiments show that its advantages over two-stream architecture in both speed and performance.

• Journal of Electrical Engineering and information Science
• /
• v.3 no.3
• /
• pp.342-347
• /
• 1998

An OptiNeural system is developed for optical pattern classification. It is a novel hybrid system which consists of an optical processor and a multilayer neural network. It takes advantages of two dimensional processing capability of an optical processor and nonlinear mapping capability of a neural network. The optical processor with a binary phase only filter is used as a preprocessor for feature extraction and the neural network is used as a decision system through mapping. OptiNeural system is trained for optical pattern classification by use of a simulated annealing algorithm. Its classification performance for grey tone texture patterns is excellent, while a conventional optical system shows poor classification performance.

• Journal of the Optical Society of Korea
• /
• v.4 no.2
• /
• pp.89-93
• /
• 2000

Recently a new signal processing algorithm for white light interferometry was presented. In this paper, the proposed signal processing algorithm was applied for absolute temperature measurement using white light interferometry. Stability testing and absolute temperature measurement were demonstrated. Stability test demonstrated the feasibility of absolute temperature measurement with an accuracy of 0.015 fringe. The test also showed that the absolute temperature measurement system using white light interferometry is capable of obtaining the theoretical minimum detectable change (0.0005 fringe), which is consistent with the performance predicted by the proposed signal processing algorithm.

• Proceedings of the Korean Institute of Communication Sciences Conference
• /
• 1991.10a
• /
• pp.86-91
• /
• 1991

A capability of performing the optical logic and arithmetic operations is followed by an effective encoding technique. In this paper, we proposed the color light encoding technique. By using this encoding technique, the space bandwidth product(SBP) is minimized in the output plane. In addition, we proposed the pre-operation pro-carry processing method that performs faster than the same time operation and carry processing method in optical computing. We proposed that the color liquid crystal device(CLCD) is used as the encoded color light input source.

• Korean Journal of Optics and Photonics
• /
• v.18 no.5
• /
• pp.309-316
• /
• 2007

We demonstrate the wavelength swept source and signal processing for the frequency domain optical coherence tomography. The laser output performance is improved by using a semiconductor optical amplifier with a booster amplifier. The laser generates 14 mW of average power of which wavelength shift in the lasing spectral shape is compensated. Adopting a Fabry-Perot etalon and digital signal processing, the broadening of the beat frequency due to the variance of wavelength-sweep-velocity is calibrated. The optical coherence tomography system shows 154.4 kHz of axial scanning speed, 0.95mm of depth range, and $12{\pm}0.37{\mu}m$ of axial resolution.

• The Magazine of the IEIE
• /
• v.12 no.5
• /
• pp.47-52
• /
• 1985

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.32B no.11
• /
• pp.1481-1488
• /
• 1995

Due to the low loss, broadband and accurate short time delay properties of optical fiber, it has attracted as a delay medium for high speed and broad-band signal processing. In this paper, we consider the coherent optical fiber filter of IIR lattice structure, which uses coherent light sources and consists of directional couplers whose coupling coefficients are restricted between 0 and 1. Considering restrictions of directional coupler, the design formulae and condition for realibility of optical fiber filter of IIR lattice structure which makes the optimal use of optical signal energy are derived.

• ETRI Journal
• /
• v.34 no.1
• /
• pp.122-125
• /
• 2012

A video signal through a high-density optical link has been demonstrated to show the reliability of optical link for high-data-rate transmission. To reduce optical point-to-point links, an electrical link has been utilized for control and clock signaling. The latency and flicker with background noise occurred during the transferring of data across the optical link due to electrical-to-optical with optical-to-electrical conversions. The proposed synchronization technology combined with a flicker and denoising algorithm has given good results and can be applied in high-definition serial data interface (HD-SDI), ultra-HD-SDI, and HD multimedia interface transmission system applications.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.6 no.12
• /
• pp.3315-3337
• /
• 2012

Crowded scenes analysis is a challenging topic in computer vision field. How to detect diverse motion patterns in crowded scenarios from videos is the critical yet hard part of this problem. In this paper, we propose a novel approach to mining motion patterns by utilizing motion information during both long-term period and short interval simultaneously. To capture long-term motions effectively, we introduce Motion History Image (MHI) representation to access to the global perspective about the crowd motion. The combination of MHI and optical flow, which is used to get instant motion information, gives rise to discriminative spatial-temporal motion features. Benefitting from the robustness and efficiency of the novel motion representation, the following motion pattern mining is implemented in a completely unsupervised way. The motion vectors are clustered hierarchically through automatic hierarchical clustering algorithm building on the basis of graphic model. This method overcomes the instability of optical flow in dealing with time continuity in crowded scenes. The results of clustering reveal the situations of motion pattern distribution in current crowded videos. To validate the performance of the proposed approach, we conduct experimental evaluations on some challenging videos including vehicles and pedestrians. The reliable detection results demonstrate the effectiveness of our approach.

• Journal of information and communication convergence engineering
• /
• v.4 no.3
• /
• pp.105-107
• /
• 2006

Amorphous silicon is a kind of optical to electric conversion material with current or voltage type after generating a numerous free electron and hole when it is injected by light. It is very effective technology to make schottky diode by bonding thin film to use optical diode. In this paper, we have fabricated optical diode device by forming chrome silicide film through thermal processing with thin film($100{\AA}$) having optimal amorphous silicon. The optimal condition is that we make a thin film by using PECVD(Plasma Enhanced Chemical Vapor Deposition) to improve reliability and characteristics of optical diode. We have obtained high quality diode by using chrome silicide optical diode from dark current and optical current measurement compared to previous method. It makes a simple process and improves a good reliability.