• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 1999.06a
• /
• pp.49-56
• /
• 1999

In this paper, the general formula of disparity estimation based on Bayesian Maximum A Posteriori (MAP) algorithm is derived. The generalized formula is implemented with the plane configuration model and applied to multiple baselined stereograms. The probabilistic plane configuration model consists of independence and similarity among the neighboring disparities in the configuration. The independence probabilistic model reduces the computation and guarantees the discontinuity at the object boundary region. The similarity model preserves the continuity or the high correlation of disparity distribution. In addition, we propose a hierarchical scheme of disparity compensation in the application to multiple-view stereo images. According to the experiments, the derived formula and the proposed estimation algorithm outperformed other ones. The proposed probabilistic models are reasonable and approximate the pure joint probability distribution very well with decreasing the computations to O(n(D)) from O(n(D)4) of the generalized formula. And, the hierarchical scheme of disparity compensation with multiple-view stereos improves the performance without any additional overhead to the decoder.

• ETRI Journal
• /
• v.45 no.5
• /
• pp.822-835
• /
• 2023

Recent semantic segmentation frameworks usually combine low-level and high-level context information to achieve improved performance. In addition, postlevel context information is also considered. In this study, we present a Context ReFinement Network (CRFNet) and its training method to improve the semantic predictions of segmentation models of the encoder-decoder structure. Our study is based on postprocessing, which directly considers the relationship between spatially neighboring pixels of a label map, such as Markov and conditional random fields. CRFNet comprises two modules: a refiner and a combiner that, respectively, refine the context information from the output features of the conventional semantic segmentation network model and combine the refined features with the intermediate features from the decoding process of the segmentation model to produce the final output. To train CRFNet to refine the semantic predictions more accurately, we proposed a sequential training scheme. Using various backbone networks (ENet, ERFNet, and HyperSeg), we extensively evaluated our model on three large-scale, real-world datasets to demonstrate the effectiveness of our approach.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.9 no.2
• /
• pp.111-116
• /
• 2009

In this paper, we propose a phase offset estimation algorithm which is based on turbo coded digital broadcasting system. The phase estimator is an estimator outside turbo code decoder using LMS (Least Mean Square) algorithm to estimate the phase of next state. While the conventional LMS algorithm with a fixed step size is easy implemented, it has weak points that are difficult the channel estimation and tracking in the multipath environment. To resolve this problem, we propose new phase offset estimation method with a variable step size LMS (VS-LMS). Additionally, we propose a scheme which consists of a conventional LMS. The performance is verified by computer simulation according to a fixed phase offset and a increased phase offset, the proposed algorithm improve the bit error rate performance than the conventional algorithm.

• Journal of Broadcast Engineering
• /
• v.9 no.3
• /
• pp.196-206
• /
• 2004

This paper presents an efficient joint disparity-motion estimation algorithm for stereo sequence CODEC. Disparity vectors are estimated by the left and right motion vectors and previous disparity vectors for every frame. In order to obtain more accurate disparity vectors. we include a spatial prediction Process after the feint estimation. From joint estimation and spatial prediction, we can obtain accurate disparity vectors and then Increase coding efficiency. Finally, we proposed the backward quadtree decomposition. which helps the encoder to have a more detailed disparity vector map without transmitting additional coding bits for quadtree information. We confirmed superior performance of the proposed method through computer simulation.

• Journal of KIISE
• /
• v.45 no.1
• /
• pp.94-98
• /
• 2018

We propose Wide Inception ResNet (WIR Net) an optimized neural network architecture as a real-time semantic segmentation method for autonomous driving. The neural network architecture consists of an encoder that extracts features by applying a residual connection and inception module, and a decoder that increases the resolution by using transposed convolution and a low layer feature map. We also improved the performance by applying an ELU activation function and optimized the neural network by reducing the number of layers and increasing the number of filters. The performance evaluations used an NVIDIA Geforce GTX 1080 and TX1 boards to assess the class and category IoU for cityscapes data in the driving environment. The experimental results show that the accuracy of class IoU 53.4, category IoU 81.8 and the execution speed of $640{\times}360$, $720{\times}480$ resolution image processing 17.8fps and 13.0fps on TX1 board.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.32 no.5C
• /
• pp.469-477
• /
• 2007

Most multimedia source coders exhibit unequal bit error sensitivity. Efficient transmission system design should therefore incorporate the use of matching unequal error protection (UEP). In this paper, we present and evaluate a flexible space-time coding system with unequal error protection. Multiple transmit and receive antennas and bit-interleaved coded modulation techniques are used combined with rate compatible punctured convolutional codes. A near optimum iterative receiver is employed with a multiple-in multiple-out inverse mapper and a MAP decoder as component decoders. We illustrate how the UEP system gain can be achieved either as a power or bandwidth gain compared to the equal error protection system (EEP) for the identical source and equal overall quality for both the UEP and EEP systems. An example with two/three transmit and two receive antennas using BPSK modulation is given for the block fading channel.

• Journal of Convergence for Information Technology
• /
• v.11 no.10
• /
• pp.45-52
• /
• 2021

In this paper, we proposed an Atrous Residual U-Net (AR-UNet) to improve the segmentation accuracy of semantic segmentation method based on U-Net. The U-Net is mainly used in fields such as medical image analysis, autonomous vehicles, and remote sensing images. The conventional U-Net lacks extracted features due to the small number of convolution layers in the encoder part. The extracted features are essential for classifying object categories, and if they are insufficient, it causes a problem of lowering the segmentation accuracy. Therefore, to improve this problem, we proposed the AR-UNet using residual learning and ASPP in the encoder. Residual learning improves feature extraction ability and is effective in preventing feature loss and vanishing gradient problems caused by continuous convolutions. In addition, ASPP enables additional feature extraction without reducing the resolution of the feature map. Experiments verified the effectiveness of the AR-UNet with Cityscapes dataset. The experimental results showed that the AR-UNet showed improved segmentation results compared to the conventional U-Net. In this way, AR-UNet can contribute to the advancement of many applications where accuracy is important.

• Journal of the Institute of Electronics Engineers of Korea TC
• /
• v.44 no.6 s.360
• /
• pp.40-47
• /
• 2007

In this paper, we propose and analyze the Adaptive Modulation System with optimal Turbo Coded V-BLAST(Vertical-Bell-lab Layered Space-Time) technique that adopts the extrinsic information from MAP (Maximum A Posteriori) Decoder with Iterative Decoding as a priori probability in two decoding procedures of V-BLAST; the ordering and the slicing. Also, we consider and compare the Adaptive Modulation System using conventional Turbo Coded V-BLAST technique that is simply combined V-BLAST with Turbo Coding scheme and the Adaptive Modulation System using conventional Turbo Coded V-BLAST technique that is decoded by the ML (Maximum Likelihood) decoding algorithm. We observe a throughput performance and a complexity. As a result of a performance comparison of each system, it has been proved that the complexity of the proposed decoding algorithm is lower than that of the ML decoding algorithm but is higher than that of the conventional V-BLAST decoding algorithm. however, we can see that the proposed system achieves a better throughput performance than the conventional system in the whole SNR (Signal to Noise Ratio) range. And the result shows that the proposed system achieves a throughput performance close to the ML decoded system. Specifically, a simulation shows that the maximum throughput improvement in each MIMO scheme is respectively about 350 kbps, 460 kbps, and 740 kbps compared to the conventional system. It is suggested that the effect of the proposed decoding algorithm accordingly gets higher as the number of system antenna increases.