• Journal of Broadcast Engineering
• /
• v.26 no.4
• /
• pp.429-440
• /
• 2021

With the recent development of deep convolutional neural network learning, deep learning techniques applied to single image super-resolution are showing good results. One of the existing deep learning-based super-resolution techniques is RDN(Residual Dense Network), in which the initial feature information is transmitted to the last layer using residual dense blocks, and subsequent layers are restored using input information of previous layers. However, if all hierarchical features are connected and learned and a large number of residual dense blocks are stacked, despite good performance, a large number of parameters and huge computational load are needed, so it takes a lot of time to learn a network and a slow processing speed, and it is not applicable to a mobile system. In this paper, we use the residual dense structure, which is a continuous memory structure that reuses previous information, and the residual dense channel attention block using the channel attention method that determines the importance according to the feature map of the image. We propose a method that can increase the depth to obtain a large receptive field and maintain a concise model at the same time. As a result of the experiment, the proposed network obtained PSNR as low as 0.205dB on average at 4× magnification compared to RDN, but about 1.8 times faster processing speed, about 10 times less number of parameters and about 1.74 times less computation.

• Journal of Korea Multimedia Society
• /
• v.23 no.12
• /
• pp.1540-1551
• /
• 2020

Aiming at the problem that the existing human behavior recognition algorithm cannot fully utilize the multi-level spatio-temporal information of the network, a human behavior recognition algorithm based on a dense three-dimensional residual network is proposed. First, the proposed algorithm uses a dense block of three-dimensional residuals as the basic module of the network. The module extracts the hierarchical features of human behavior through densely connected convolutional layers; Secondly, the local feature aggregation adaptive method is used to learn the local dense features of human behavior; Then, the residual connection module is applied to promote the flow of feature information and reduced the difficulty of training; Finally, the multi-layer local feature extraction of the network is realized by cascading multiple three-dimensional residual dense blocks, and use the global feature aggregation adaptive method to learn the features of all network layers to realize human behavior recognition. A large number of experimental results on benchmark datasets KTH show that the recognition rate (top-l accuracy) of the proposed algorithm reaches 93.52%. Compared with the three-dimensional convolutional neural network (C3D) algorithm, it has improved by 3.93 percentage points. The proposed algorithm framework has good robustness and transfer learning ability, and can effectively handle a variety of video behavior recognition tasks.

• Journal of Internet of Things and Convergence
• /
• v.9 no.1
• /
• pp.131-138
• /
• 2023

This paper is related to performance improvement of Image-to-Image translation using Relativistic Average Patch GAN and Residual in Residual Dense Block. The purpose of this paper is to improve performance through technical improvements in three aspects to compensate for the shortcomings of the previous pix2pix, a type of Image-to-Image translation. First, unlike the previous pix2pix constructor, it enables deeper learning by using Residual in Residual Block in the part of encoding the input image. Second, since we use a loss function based on Relativistic Average Patch GAN to predict how real the original image is compared to the generated image, both of these images affect adversarial generative learning. Finally, the generator is pre-trained to prevent the discriminator from being learned prematurely. According to the proposed method, it was possible to generate images superior to the previous pix2pix by more than 13% on average at the aspect of FID.

• Journal of Broadcast Engineering
• /
• v.24 no.5
• /
• pp.703-712
• /
• 2019

Single image Super-Resolution (SISR) aims to generate a visually pleasing high-resolution image from its degraded low-resolution measurement. In recent years, deep learning - based super - resolution methods have been actively researched and have shown more reliable and high performance. A typical method is WaveletSRNet, which restores high-resolution images through wavelet coefficient learning based on feature maps of images. However, there are two disadvantages in WaveletSRNet. One is a big processing time due to the complexity of the algorithm. The other is not to utilize feature maps efficiently when extracting input image's features. To improve this problems, we propose an efficient single image super resolution method, named RDB-WaveletSRNet. The proposed method uses the residual dense block to effectively extract low-resolution feature maps to improve single image super-resolution performance. We also adjust appropriated growth rates to solve complex computational problems. In addition, wavelet packet decomposition is used to obtain the wavelet coefficients according to the possibility of large scale ratio. In the experimental result on various images, we have proven that the proposed method has faster processing time and better image quality than the conventional methods. Experimental results have shown that the proposed method has better image quality by increasing 0.1813dB of PSNR and 1.17 times faster than the conventional method.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.9
• /
• pp.2882-2903
• /
• 2022

Image super-resolution (SR) processing is of great value in the fields of digital image processing, intelligent security, film and television production and so on. This paper proposed a densely connected deep learning network based on cascade architecture, which can be used to solve the problem of super-resolution in the field of image quality enhancement. We proposed a more efficient residual scaling dense block (RSDB) and the multi-channel cascade architecture to realize more efficient feature reuse. Also we proposed a hybrid loss function based on L₁ error and L_∞ error to achieve better L_∞ error performance. The experimental results show that the overall performance of the network is effectively improved on cascade architecture and residual scaling. Compared with the residual dense net (RDN), the PSNR / SSIM of the new method is improved by 2.24% / 1.44% respectively, and the L_∞ performance is improved by 3.64%. It shows that the cascade connection and residual scaling method can effectively realize feature reuse, improving the residual convergence speed and learning efficiency of our network. The L_∞ performance is improved by 11.09% with only a minimal loses of 1.14% / 0.60% on PSNR / SSIM performance after adopting the new loss function. That is to say, the L_∞ performance can be improved greatly on the new loss function with a minor loss of PSNR / SSIM performance, which is of great value in L_∞ error sensitive tasks.

• Journal of Broadcast Engineering
• /
• v.25 no.2
• /
• pp.242-251
• /
• 2020

Recently, many deep convolutional neural networks for image super-resolution have been studied. Existing deep learning-based super-resolution algorithms are architecture that up-samples the resolution at the end of the network. The post-upsampling architecture has an inefficient structure at large scaling factor result of predicting a lot of information for mapping from low-resolution to high-resolution at once. In this paper, we propose a single image super-resolution using Channel Attention Residual Dense Block based on an iterative up-down sampling architecture. The proposed algorithm efficiently predicts the mapping relationship between low-resolution and high-resolution, and shows up to 0.14dB performance improvement and enhanced subjective image quality compared to the existing algorithm at large scaling factor result.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2019.06a
• /
• pp.5-8
• /
• 2019

단일 영상 초해상도 (Single Image Super-Resolution - SISR)기법은 카메라로 획득된 저해상도 영상에 필터 기반의 연산을 적용하여 좋은 화질의 고해상도 영상을 복원하는 과정이다. 최근에 심층 합성곱 신경망 학습의 발전에 따라 단일 영상 초해상도에 적용되는 심층 학습 기법들은 좋은 성과를 보여 주고 있다. 본 논문은 단일 영상 초해상도 성능을 개선하기 위해 웨이블릿 예측 네트워크를 효율적으로 적용하는 방법에 대해 연구하였으며, 저해상도 입력 영상의 특징을 잘 추출해내기 위해 네트워크 내부에 RDB를 적용하여 기존 방식보다 효율적으로 고해상도 영상 복원하는 기법을 제안한다. 모의실험을 통해 제안하는 방법이 기존 방법보다 화질은 약 PSNR 0.18dB만큼 우수하며 속도는 1.17배 빠른 것을 확인하였다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.4
• /
• pp.1234-1257
• /
• 2023

In this paper, we propose a framework for multi-focus image fusion called PATN. In our approach, by aggregating deep features extracted based on the U-type Transformer mechanism and shallow features extracted using the PSA module, we make PATN feed both long-range image texture information and focus on local detail information of the image. Meanwhile, the edge-preserving information value of the fused image is enhanced using a dense residual block containing the Sobel gradient operator, and three loss functions are introduced to retain more source image texture information. PATN is compared with 17 more advanced MFIF methods on three datasets to verify the effectiveness and robustness of PATN.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2021.06a
• /
• pp.335-338
• /
• 2021

본 논문에서는 기존 AHDRNet에 channel attention 기법을 적용했을 때 성능에 어떠한 변화가 있는지를 평가하였다. 기존 모델의 병합 망에 존재하는 DRDB(Dilated Residual Dense Block) 사이, 그리고 DRDB 내의 확장된 합성곱 레이어 (dilated convolutional layer) 뒤에 또다른 합성곱 레이어를 추가하는 방식으로 channel attention 기법을 적용하였다. 데이터셋은 Kalantari의 데이터셋을 사용하였으며, PSNR(Peak Signal-to-Noise Ratio)로 비교해본 결과 기존의 AHDRNet의 PSNR은 42.1656이며, 제안된 모델의 PSNR은 42.8135로 더 높아진 것을 확인하였다.

• Journal of Broadcast Engineering
• /
• v.28 no.1
• /
• pp.124-131
• /
• 2023

Object detection techniques are increasingly used to obtain information on physical characteristics or situations of a specific area from remote images. The accuracy of object detection is decreased in remote sensing images with low resolution because the low resolution reduces the amount of detail that can be captured in an image. A single neural network is proposed to joint the super-resolution method and object detection method. The proposed method constructs a deep residual-based network to restore object features in low-resolution images. Moreover, the proposed method is used to improve the performance of object detection by jointing a single network with YOLOv5. The proposed method is experimentally tested using VEDAI data for low-resolution images. The results show that vehicle detection performance improved by 81.38% on mAP@0.5 for VISIBLE data.