• The Transactions of the Korea Information Processing Society
• /
• v.6 no.4
• /
• pp.868-876
• /
• 1999

In this paper, an efficient automatic video parsing technique on MPEG-compressed video that is fundamental for content-based indexing is described. The proposed method detects scene changes, regardless of IPB picture composition. To detect abrupt changes, the difference measure based on the dc coefficient in I picture and the macroblock reference feature in P and B pictures are utilized. For gradual scene changes, we use the macroblock reference information in P and B pictures. the process of scene change detection can be efficiently handled by extracting necessary data without full decoding of MPEG sequence. The performance of the proposed algorithm is analyzed based on precision and recall. the experimental results verified the effectiveness of the method for detecting scene changes of various MPEG sequences.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• v.9 no.1
• /
• pp.497-503
• /
• 2005

본 논문에서는 퍼지 RBF 네트워크를 이용한 운송 컨테이너 식별자 인식 시스템을 제안한다. 일반적으로 운송 컨테이너의 식별자들은 크기나 위치가 정형화되어 있지 않고 외부 잡음으로 인하여 식별자의 형태가 변형될 수 있기 때문에 일정한 규칙으로 찾기는 힘들다. 본 논문에서는 이러한 특성을 고려하여 컨테이너 영상에 대해 Canny 마스크를 이용하여 에지를 검출하고, 검출된 에지 정보에서 영상획득 시 외부 광원에 의해 수직으로 길게 발생하는 잡음들을 퍼지 추론 방법을 적용하여 제거한 후에 수직 블록과 수평 블록을 검출하여 컨테이너의 식별자 영역을 추출하고 이진화한다. 이진화된 식별자 영역에 대해 검정색의 빈도수를 이용하여 흰바탕과 민바탕을 구분하고 4방향 윤광선 추적 알고리즘을 적용하여 개별 식별자를 추출한다. 개별 식별자 인식을 위해 퍼지 C-Means 알고리즘을 이용한 퍼지 RBF 네트워크를 제안하여 개별 식별자에 적용한다. 제안된 퍼지 RBF 네트워크는 퍼지 C-Means 알고리즘을 중간층으로 적용하고 중간층과 출력층 간의 학습에는 일반화된 델타 학습 방법과Delta-bar-Delta 알고리즘을 적용하여 학습 성능을 개선한다. 실제 컨테이너 영상을 대상으로 실험한 결과, 기존의 식별자 추출 방법보다 제안된 식별자 추출방법이 개선되었다. 그리고 기존의 ART2 기반 RBF 네트워크보다 제안된 퍼지 RBF 네트워크가 컨테이너 식별자의 학습 및 인식에 있어서 우수함을 확인하였다.

• Journal of Broadcast Engineering
• /
• v.19 no.2
• /
• pp.240-249
• /
• 2014

According to the compressive sensing theory, it is possible to perfectly reconstruct a signal only with a fewer number of measurements than the Nyquist sampling rate if the signal is a sparse signal which satisfies a few related conditions. From practical viewpoint for image applications, it is important to reduce its computational complexity and memory burden required in reconstruction. In this regard, a Block-based Compressive Sensing (BCS) scheme with Smooth Projected Landweber (BCS-SPL) has been already introduced. However, it still has the computational complexity problem in reconstruction. In this paper, we propose a method which modifies its stopping criterion, tolerance, and convergence control to make it converge faster. Experimental results show that the proposed method requires less iterations but achieves better quality of reconstructed image than the conventional BCS-SPL.

• Journal of Internet Computing and Services
• /
• v.15 no.4
• /
• pp.119-124
• /
• 2014

Blind adaptive systems based on the Euclidean distance (ED) between the distribution function of the output samples and that of a set of random symbols generated at the receiver matching with the distribution function of the transmitted symbol points estimate the ED at each iteration time to examine its convergence state or its minimum ED value. The problem is that this ED estimation obtained by block?data processing requires a heavy calculation burden. In this paper, a recursive ED estimation method is proposed that reduces the computational complexity by way of utilizing the relationship between the current and previous states of the datablock. The relationship provides a ground that the currently estimated ED value can be used for the estimation of the next ED without the need for processing the whole new data block. From the simulation results the proposed recursive ED estimation shows the same estimation values as that of the conventional method, and in the aspect of computational burden, the proposed method requires only O(N) at each iteration time while the conventional block?processing method does $O(N^2)$.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.46 no.6
• /
• pp.68-77
• /
• 2009

A single field deinterlacing method, namely interpolation algorithm derived from low resolution (ILR), is presented in this paper. Traditional deinterlacing methods usually employ edge-based interpolation technique within pixel-based estimation. However, edge-based methods are somehow sensitive to noise and intensity variation in the image. Moreover, the methods are not satisfied in deciding the exact edge direction which controls the performance of the interpolation. In order to reduce the sensitivity, the proposed algorithm investigates low-resolution characteristics of the pixel to be interpolated, and applies it to high-resolution image. Simulation results demonstrates that the proposed method gives not only a better objective performance in terms of PSNR results compare to conventional edge-based interpolation methods, but also better subjective image quality.

• The Journal of the Acoustical Society of Korea
• /
• v.43 no.2
• /
• pp.207-213
• /
• 2024

In this paper, we study how to improve the performance of a machine learning-based automatic music transcription model by adding musical information to the input data. Where, the added musical information is information on the number of pitches that occur in each time frame, and which is obtained by counting the number of notes activated in the answer sheet. The obtained information on the number of pitches was used by concatenating it to the log mel-spectrogram, which is the input of the existing model. In this study, we use the automatic music transcription model included the four types of block predicting four types of musical information, we demonstrate that a simple method of adding pitch number information corresponding to the music information to be predicted by each block to the existing input was helpful in training the model. In order to evaluate the performance improvement proceed with an experiment using MIDI Aligned Piano Sounds (MAPS) data, as a result, when using all pitch number information, performance improvement was confirmed by 9.7 % in frame-based F1 score and 21.8 % in note-based F1 score including offset.

• Journal of Broadcast Engineering
• /
• v.17 no.5
• /
• pp.742-755
• /
• 2012

In this paper, we propose a parallel deblocking algorithm to resolve workload imbalance when the deblocking filter of high efficiency video coding (HEVC) decoder is parallelized. In HEVC, the deblocking filter which is one of the in-loop filters conducts two-step filtering on vertical edges first and horizontal edges later. The deblocking filtering can be conducted with high-speed through data-level parallelism because there is no dependency between adjacent edges for deblocking filtering processes. However, workloads would be imbalanced among regions even though the same amount of data for each region is allocated, which causes performance loss of decoder parallelization. In this paper, we solve the problem for workload imbalance by predicting the complexity of deblocking filtering with coding unit (CU) depth information at a coding tree block (CTB) and by allocating the same amount of workload to each core. Experimental results show that the proposed method achieves average time saving (ATS) by 64.3%, compared to single core-based deblocking filtering and also achieves ATS by 6.7% on average and 13.5% on maximum, compared to the conventional uniform data-level parallelism.

• Journal of Broadcast Engineering
• /
• v.14 no.5
• /
• pp.601-615
• /
• 2009

This paper proposes an efficient depth-map coding method for generating virtual-view images in 3D-Video. Virtual-view images can be generated by the view-interpolation based on the depth-map of the image. A conventional video coding method such as H.264 has been used. However, a conventional video coding method does not consider the image characteristics of the depth-map. Therefore, this paper proposes an adaptive depth-map coding method that can select between the H.264/AVC coding scheme and the proposed gray-coded bit plane-based coding scheme in a unit of block. This improves the coding efficiency of the depth-map data. Simulation results show that the proposed method, in comparison with the H.264/AVC coding scheme, improves the average BD-rate savings by 7.43% and the average BD-PSNR gains by 0.5dB. It also improves the subjective picture quality of synthesized virtual-view images using decoded depth-maps.

• Journal of the Korea Society of Computer and Information
• /
• v.14 no.3
• /
• pp.93-101
• /
• 2009

This paper suggests a new algorithm automatically searching for Region-of-Interest(ROI) with high speed, using the edge information of high frequency subband transformed with wavelet. The proposed method executes a searching algorithm of 4-direction object boundary by the unit of block using the edge information, and detects ROIs. The whole image is splitted by $64{\times}64$ or $32{\times}32$ sized blocks and the blocks can be ROI block or background block according to taking the edges or not. The 4-directions searche the image from the outside to the center and the algorithm uses a feature that the low-DOF image has some edges as one goes to center. After searching all the edges, the method regards the inner blocks of the edges as ROI, and makes the ROI masks and sends them to server. This is one of the dynamic ROI method. The existing methods have had some problems of complicated filtering and region merge, but this method improved considerably the problems. Also, it was possible to apply to an application requiring real-time processing caused by the process of the unit of block.

• The KIPS Transactions:PartB
• /
• v.15B no.4
• /
• pp.259-268
• /
• 2008

In an effort to increase the data capacity of one-dimensional symbology, 2D barcodes have been proposed a decade ago. In this paper, we present an effective 2D barcode detection algorithm from gray-level images, especially for the handheld 2D barcode recognition system. To locate the symbol inside the image, a criteria based on the block contrast is adopted, and a gray-scale projection with sub-pixel operation is utilized to segment the symbol precisely from the region of interest(ROI). Finally, the segmented ROI is normalized using the inverse perspective transformation for the following decoding processes. We also introduce the post-processing steps for decoding the QR-code. The proposed method ensures high performances under various lighting/printing conditions and strong perspective deformations. Experiments shows that our method is very robust and efficient in detecting the code area for the various types of 2D barcodes in real time.