• Journal of Broadcast Engineering
• /
• v.22 no.2
• /
• pp.193-206
• /
• 2017

In this paper, we propose a rate control method based on the $R-{\lambda}$ model that supports a parallel encoding structure in GOP levels or IDR period levels for 4K UHD input video in real-time. For this, a slice-level bit allocation method is proposed for parallel encoding instead of sequential encoding. When a rate control algorithm is applied in the GOP level or IDR period level parallelism, the information of how many bits are consumed cannot be shared among the frames belonging to a same frame level except the lowest frame level of the hierarchical B structure. Therefore, it is impossible to manage the bit budget with the existing bit allocation method. In order to solve this problem, we improve the bit allocation procedure of the conventional ones that allocate target bits sequentially according to the encoding order. That is, the proposed bit allocation strategy is to assign the target bits in GOPs first, then to distribute the assigned target bits from the lowest depth level to the highest depth level of the HEVC hierarchical B structure within each GOP. In addition, we proposed a processing method that is used to improve subjective image qualities by allocating the bits according to the coding complexities of the frames. Experimental results show that the proposed bit allocation method works well for frame-level parallel HEVC software encoders and it is confirmed that the performance of our rate controller can be improved with a more elaborate bit allocation strategy by using the preprocessing results.

• Korean Journal of Remote Sensing
• /
• v.38 no.5_2
• /
• pp.707-723
• /
• 2022

Although satellite-based sea surface temperature (SST) is advantageous for monitoring large areas, spatiotemporal data gaps frequently occur due to various environmental or mechanical causes. Thus, it is crucial to fill in the gaps to maximize its usability. In this study, daily SST composite fields with a resolution of 4 km were produced through a two-step machine learning approach using polar-orbiting and geostationary satellite SST data. The first step was SST reconstruction based on Data Interpolate Convolutional AutoEncoder (DINCAE) using multi-satellite-derived SST data. The second step improved the reconstructed SST targeting in situ measurements based on light gradient boosting machine (LGBM) to finally produce daily SST composite fields. The DINCAE model was validated using random masks for 50 days, whereas the LGBM model was evaluated using leave-one-year-out cross-validation (LOYOCV). The SST reconstruction accuracy was high, resulting in R² of 0.98, and a root-mean-square-error (RMSE) of 0.97℃. The accuracy increase by the second step was also high when compared to in situ measurements, resulting in an RMSE decrease of 0.21-0.29℃ and an MAE decrease of 0.17-0.24℃. The SST composite fields generated using all in situ data in this study were comparable with the existing data assimilated SST composite fields. In addition, the LGBM model in the second step greatly reduced the overfitting, which was reported as a limitation in the previous study that used random forest. The spatial distribution of the corrected SST was similar to those of existing high resolution SST composite fields, revealing that spatial details of oceanic phenomena such as fronts, eddies and SST gradients were well simulated. This research demonstrated the potential to produce high resolution seamless SST composite fields using multi-satellite data and artificial intelligence.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.32 no.9C
• /
• pp.849-860
• /
• 2007

Because the H.264/AVC standard adopts the variable length coding algorithm, the rate of encoded video bitstream fluctuates a lot as time flows, though its compression efficiency is superior to that of existing standards. When a video is transmitted in real-time over networks with fixed low-bandwidth, it is necessary to control the bit rate which is generated from encoder. Many existing rate control algorithms have been adopting the quadratic rate-distortion model which determines the target bits for each frame. We propose a new rate control algorithm for H.264/AVC video transmission over networks with fixed bandwidth. The proposed algorithm predicts quantization parameter adaptively to reduce video distortion using the quadratic rate-distortion model, which uses the target bit rate and the mean absolute difference for current frame considering pixel difference between macroblocks in the previous and the current frame. On video samples with high motion and scene change cases, experimental results show that (1) the proposed algorithm adapts the encoded bitstream to limited channel capacity, while existing algorithms abruptly excess the limit bit rate; (2) the proposed algorithm improves picture quality with $0.4{\sim}0.9dB$ in average.

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.45 no.6
• /
• pp.26-34
• /
• 2008

The information of traversability and path planning is essential for UGV(Unmanned Ground Vehicle) navigation. Such information can be obtained by analyzing 3D terrain. In this paper, we present the method of 3D terrain modeling with color information from a camera, precise distance information from a 2D Laser Range Finder(LRF) and wheel encoder information from mobile robot with less data. And also we present the method of 3B terrain modeling with the information from GPS/IMU and 2D LRF with less data. To fuse the color information from camera and distance information from 2D LRF, we obtain extrinsic parameters between a camera and LRF using planar pattern. We set up such a fused system on a mobile robot and make an experiment on indoor environment. And we make an experiment on outdoor environment to reconstruction 3D terrain with 2D LRF and GPS/IMU(Inertial Measurement Unit). The obtained 3D terrain model is based on points and requires large amount of data. To reduce the amount of data, we use cubic grid-based model instead of point-based model.

• Phonetics and Speech Sciences
• /
• v.12 no.2
• /
• pp.29-37
• /
• 2020

Recently, the neural network-based deep learning algorithm has dramatically improved performance compared to the classical Gaussian mixture model based hidden Markov model (GMM-HMM) automatic speech recognition (ASR) system. In addition, researches on end-to-end (E2E) speech recognition systems integrating language modeling and decoding processes have been actively conducted to better utilize the advantages of deep learning techniques. In general, E2E ASR systems consist of multiple layers of encoder-decoder structure with attention. Therefore, E2E ASR systems require data with a large amount of speech-text paired data in order to achieve good performance. Obtaining speech-text paired data requires a lot of human labor and time, and is a high barrier to building E2E ASR system. Therefore, there are previous studies that improve the performance of E2E ASR system using relatively small amount of speech-text paired data, but most studies have been conducted by using only speech-only data or text-only data. In this study, we proposed a semi-supervised training method that enables E2E ASR system to perform well in corpus in different domains by using both speech or text only data. The proposed method works effectively by adapting to different domains, showing good performance in the target domain and not degrading much in the source domain.

• Smart Media Journal
• /
• v.8 no.2
• /
• pp.58-65
• /
• 2019

Automatic text summarization is a process of shortening a text document by either extraction or abstraction. The abstraction approach inspired by deep learning methods scaling to a large amount of document is applied in recent work. Abstractive text summarization involves utilizing pre-generated word embedding information. Low-frequent but salient words such as terminologies are seldom included to dictionaries, that are so called, out-of-vocabulary(OOV) problems. OOV deteriorates the performance of Encoder-Decoder model in neural network. In order to address OOV words in abstractive text summarization, we propose a copy mechanism to facilitate copying new words in the target document and generating summary sentences. Different from the previous studies, the proposed approach combines accurate pointing information and selective copy mechanism based on bidirectional RNN and bidirectional LSTM. In addition, neural network gate model to estimate the generation probability and the loss function to optimize the entire abstraction model has been applied. The dataset has been constructed from the collection of abstractions and titles of journal articles. Experimental results demonstrate that both ROUGE-1 (based on word recall) and ROUGE-L (employed longest common subsequence) of the proposed Encoding-Decoding model have been improved to 47.01 and 29.55, respectively.

• Geophysics and Geophysical Exploration
• /
• v.25 no.4
• /
• pp.227-241
• /
• 2022

Full waveform inversion (FWI) in the field of seismic data processing is an inversion technique that is used to estimate the velocity model of the subsurface for oil and gas exploration. Recently, deep learning (DL) technology has been increasingly used for seismic data processing, and its combination with FWI has attracted remarkable research efforts. For example, DL-based data processing techniques have been utilized for preprocessing input data for FWI, enabling the direct implementation of FWI through DL technology. DL-based FWI can be divided into the following methods: pure data-based, physics-based neural network, encoder-decoder, reparameterized FWI, and physics-informed neural network. In this review, we describe the theory and characteristics of the methods by systematizing them in the order of advancements. In the early days of DL-based FWI, the DL model predicted the velocity model by preparing a large training data set to adopt faithfully the basic principles of data science and apply a pure data-based prediction model. The current research trend is to supplement the shortcomings of the pure data-based approach using the loss function consisting of seismic data or physical information from the wave equation itself in deep neural networks. Based on these developments, DL-based FWI has evolved to not require a large amount of learning data, alleviating the cycle-skipping problem, which is an intrinsic limitation of FWI, and reducing computation times dramatically. The value of DL-based FWI is expected to increase continually in the processing of seismic data.

• KIISE Transactions on Computing Practices
• /
• v.24 no.3
• /
• pp.138-144
• /
• 2018

A video is a vivid medium similar to human's visual-linguistic experiences, since it can inculcate a sequence of situations, actions or dialogues that can be told as a story. In this study, we propose story learning/regeneration frameworks from videos with successive event order supervision for contextual coherence. The supervision induces each episode to have a form of trajectory in the latent space, which constructs a composite representation of ordering and semantics. In this study, we incorporated the use of kids videos as a training data. Some of the advantages associated with the kids videos include omnibus style, simple/explicit storyline in short, chronological narrative order, and relatively limited number of characters and spatial environments. We build the encoder-decoder structure with successive event order embedding, and train bi-directional LSTMs as sequence models considering multi-step sequence prediction. Using a series of approximately 200 episodes of kids videos named 'Pororo the Little Penguin', we give empirical results for story regeneration tasks and SEOE. In addition, each episode shows a trajectory-like shape on the latent space of the model, which gives the geometric information for the sequence models.

• Journal of Broadcast Engineering
• /
• v.25 no.3
• /
• pp.305-312
• /
• 2020

As a demand for a new video coding standard having higher coding efficiency than the existing standards is growing, recently, MPEG and VCEG has been developing and standardizing the next-generation video coding project, named Versatile Video Coding (VVC). Many inter prediction techniques have been introduced to increase the coding efficiency, and among them, an adaptive motion vector resolution (AMVR) technique has contributed on increasing the efficiency of VVC. However, the best motion vector can only be determined by computing many rate-distortion costs, thereby increasing encoding complexity. It is necessary to reduce the complexity for real-time video broadcasting and streaming services, but it is yet an open research topic to reduce the complexity of AMVR. Therefore, in this paper, an efficient technique is proposed, which reduces the encoding complexity of AMVR. For that, the proposed method exploits a special VVC tree structure (i.e., multi-type tree structure) to accelerate the decision process of AMVR. Experiment results show that the proposed decision method reduces the encoding complexity of VVC test model by 10% with a negligible loss of coding efficiency.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.11 no.6
• /
• pp.255-260
• /
• 2011

The security issue in urban transit system has been widely considered as the common matters. The safe urban transit system is highly demanded because of the vast number of daily passengers, and providing safety is one of the most challenging projects. We introduced a test model for integrated security system for urban transit system and built it at a subway station to demonstrate its performance. This system consists of cameras, sensor network and central monitoring software. We described the smart camera functionality in more detail. The proposed smart camera includes the moving objects recognition module, video analytics, video encoder and server module that transmits video and audio information. We demonstrated the system's excellent performance.