• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2020.11a
• /
• pp.252-255
• /
• 2020

Unsupervised deep learning methods have shown impressive results for the challenging monocular depth estimation task, a field of study that has gained attention in recent years. A common approach for this task is to train a deep convolutional neural network (DCNN) via an image synthesis sub-task, where additional views are utilized during training to minimize a photometric reconstruction error. Previous unsupervised depth estimation networks are trained within a fixed depth estimation range, irrespective of its possible range for a given image, leading to suboptimal estimates. To overcome this suboptimal limitation, we first propose an unsupervised adaptive depth estimation method guided by minimum and maximum (min-max) depth priors for a given input image. The incorporation of min-max depth priors can drastically reduce the depth estimation complexity and produce depth estimates with higher accuracy. Moreover, we propose a novel network architecture for adaptive depth estimation, called the AdaMM-DepthNet, which adopts the min-max depth estimation in its front side. Intensive experimental results demonstrate that the adaptive depth estimation can significantly boost up the accuracy with a fewer number of parameters over the conventional approaches with a fixed minimum and maximum depth range.

• MALSORI
• /
• no.67
• /
• pp.135-147
• /
• 2008

In this paper, we propose a method for source localization in reverberant environments based on an adaptive eigenvalue decomposition (AED) algorithm which directly estimates channel impulse responses from a speaker to microphones. Unfortunately, the AED algorithm may suffer from whitening effects on channels estimated from temporally correlated natural sounds. The proposed method which applies sparse priors to the estimated channels can avoid the temporal whitening and improve the performance of source localization in reverberant environments. Experimental results show the effectiveness of the proposed method.

• The Journal of the Acoustical Society of Korea
• /
• v.30 no.6
• /
• pp.315-323
• /
• 2011

This paper proposes two methods of estimating prior distribution to improve the performance of rapid speaker adaptation based on maximum a posteriori linear regression (MAPLR). In general, prior distribution of the transformation matrix used in MAPLR adaptation is estimated from all of the training speakers who are employed to construct the speaker-independent model, and it is applied identically to all new speakers. In this paper, we propose a method in which prior distribution is estimated from a group of reference speakers, selected using adaptation data, so that the acoustic characteristics of the selected reference speakers may be similar to that of the new speaker. Additionally, in MAPLR adaptation with block-diagonal transformation matrix, we propose a method in which the mean matrix and covariance matrix of prior distribution are estimated from two groups of transformation matrices obtained from the same training speakers, respectively. To evaluate the performance of the proposed methods, we examine word accuracy according to the number of adaptation words in the isolated word recognition task. Experimental results show that, for very limited adaptation data, statistically significant performance improvement is obtained in comparison with the conventional MAPLR adaptation.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.8 no.8
• /
• pp.2851-2865
• /
• 2014

To improve the rate-distortion performance of distributed video compressive sensing (DVCS), the adaptive sparse basis and nonlocal similarity of video are proposed to jointly reconstruct the video signal in this paper. Due to the lack of motion information between frames and the appearance of some noises in the reference frames, the sparse dictionary, which is constructed using the examples directly extracted from the reference frames, has already not better obtained the sparse representation of the interpolated block. This paper proposes a method to construct the sparse dictionary. Firstly, the example-based data matrix is constructed by using the motion information between frames, and then the principle components analysis (PCA) is used to compute some significant principle components of data matrix. Finally, the sparse dictionary is constructed by these significant principle components. The merit of the proposed sparse dictionary is that it can not only adaptively change in terms of the spatial-temporal characteristics, but also has ability to suppress noises. Besides, considering that the sparse priors cannot preserve the edges and textures of video frames well, the nonlocal similarity regularization term has also been introduced into reconstruction model. Experimental results show that the proposed algorithm can improve the objective and subjective quality of video frame, and achieve the better rate-distortion performance of DVCS system at the cost of a certain computational complexity.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.12 no.3
• /
• pp.1264-1286
• /
• 2018

In this paper, a novel background prior-based salient object detection framework is proposed to deal with images those are more complicated. We take the superpixels located in four borders into consideration and exploit a mechanism based on image boundary information to remove the foreground noises, which are used to form the background prior. Afterward, an initial foreground prior is obtained by selecting superpixels that are the most dissimilar to the background prior. To determine the regions of foreground and background based on the prior of them, a threshold is needed in this process. According to a fixed threshold, the remaining superpixels are iteratively assigned based on their proximity to the foreground or background prior. As the threshold changes, different foreground priors generate multiple different partitions that are assigned a likelihood of being foreground. Last, all segments are combined into a saliency map based on the idea of similarity voting. Experiments on five benchmark databases demonstrate the proposed method performs well when it compares with the state-of-the-art methods in terms of accuracy and robustness.