专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明专利

AU2020100178A4 Multiple decision maps based infrared and visible image fusion 未知
公开(公告)号：AU2020100178A4
公开(公告)日：2020-03-19
申请号：AU2020100178
申请日：2020-02-04
申请人： HUANG SHUYING DR , LIU JIAXIANG MR , WEN WENYING DR , YANG YONG PROF
发明人： YANG YONG , LIU JIAXIANG , HUANG SHUYING , WEN WENYING
IPC分类号： G06K9/62 , G06K9/46 , G06N3/04
摘要： Abstract: A VGG-based multiple decision maps fusion method is proposed for infrared and visible image fusion. In our method, firstly, the infrared and visible images are fed into a pre-trained model of VGG-16 to extract features. Then, we design a feature representation method to construct saliency maps by those features. Next, multiple decision maps are constructed by saliency maps and guided filter. Finally, the final fusion image is achieved by weighting the source images based on multiple decision maps. To the best of our knowledge, it is the first introduction of decision map in the field of infrared and visible image fusion. Experimental results demonstrate that the proposed method can obtain better performance compared with state-of-the-art infrared and visible image fusion methods.

2. 发明专利

AU2020100175A4 Retinex-based progressive image enhancement method 未知
公开(公告)号：AU2020100175A4
公开(公告)日：2020-04-09
申请号：AU2020100175
申请日：2020-02-04
申请人： HU WEI MR , HUANG SHUYING DR , WEN WENYING DR , YANG YONG PROF
发明人： YANG YONG , HU WEI , HUANG SHUYING , WEN WENYING
IPC分类号： G06T5/00
摘要： Abstract: Image enhancement algorithms are widely needed for their effectiveness in low-light image restoration. This present patent analyzes the essential causes of image degradation, and proposes a low-exposure image enhancement method based on a progressive dual network model. This method includes two parts: image enhancement module and image denoising module. The progressive thinking is also adopted for the construction of each module, considering the brightness change from dark to light and the image restoration process from coarse to fine, so that the enhanced result is closer to the real image. In order to better train the network, we construct a two-way constraint loss function, which makes the network learning results approach the real data from the positive and negative directions of the image degradation model to achieve dynamic equilibrium.

3. 发明专利

AU2020100200A4 Content-guide Residual Network for Image Super-Resolution 未知
公开(公告)号：AU2020100200A4
公开(公告)日：2020-06-11
申请号：AU2020100200
申请日：2020-02-08
申请人： HUANG SHUYING DR , WU ZHENG MR , YANG YONG PROF
发明人： YANG YONG , WU ZHENG , HUANG SHUYING
IPC分类号： G06T3/40
摘要： Abstract: Single image super-resolution (SISR) has always received much attention, as one of the basic assignment of computer vision. The development and extensive exploration of deep learning have brought remarkable performance and index improvement to the SISR. However, most of existing CNN-based SISR methods concentrate on using wider or deeper architecture to obtain better results, while ignoring the portability of the network. The huge network structure expend too much computing resources, which constraint its application in mobile equipment. In order to address these problems, this patent advanced a content-based network, which can extract features more efficiently under the premise of ensuring quality and complexity. Experimental results testify that our network achieved better results compared with state-of-the-art SISR methods in terms of both objective indicators and visual quality.

4. 发明专利

AU2020100460A4 Single image deraining algorithm based on multi-scale dictionary 未知
公开(公告)号：AU2020100460A4
公开(公告)日：2020-04-30
申请号：AU2020100460
申请日：2020-03-26
申请人： HUANG SHUYING DR , XU YATING MISS , YANG YONG PROF
发明人： HUANG SHUYING , XU YATING , YANG YONG
IPC分类号： G06T5/00 , G06N20/00
摘要： We aim to remove the rain tracks from the rain images and retain the structure information of the original rain map to the greatest extent. Due to the complexity of the rain layer, the rainless background layer cannot be directly obtained at one time. Therefore, We according to the rain streaks of many aspects, such as sparsity, structural and directional information, proposed a new single image to the rain, which framework of the method through constant iterative update background layer, the sparse coefficient of the rain layer, the rain dictionary and a new rain layer, thereby gaining a free-rain image. Our main contribution can be divided into three parts: (I) A very effective convolutional sparse coding framework is proposed to iteratively update the rain layer and the background layer. (II) Considering the multi-scale characteristics of the noise rain layer information in the rain image taken in reality under different the depth of field, we proposed the method of learning multi dictionary, and carried out the convolution sparse coding for the raindrop information of different sizes (III) In the process of solving the rain layer, we proposed to use the multi-scale dictionary to solve the updated rain layer information, and to use the consistency of rain direction and the structure of raindrops to propose two prior constraints based on gradient, so as to obtain better results. Finally, ADMM algorithm is used to solve the model alternately to obtain the rainless image with rich details.

5. 发明专利

AU2020100275A4 Remote sensing image super-resolution based on multi-dictionary sparse representation with fractal classification 未知
$Remote sensing image super-resolution based on multi-dictionary sparse representation with fractal classification$
公开(公告)号：AU2020100275A4
公开(公告)日：2020-03-26
申请号：AU2020100275
申请日：2020-02-25
申请人： HUANG SHUYING DR , WU XIN MISS , YANG YONG PROF
发明人： HUANG SHUYING , WU XIN , YANG YONG
IPC分类号： G06T3/40 , G06N20/00 , G06T5/00 , G06T7/136
摘要： Image super resolution technology has a wide range of applications in military, medical and other aspects of important application prospects, but also faced with a variety of problems. This patent studies a super-resolution technology of single remote sensing image. Firstly, the input high-resolution remote sensing image is blurred and sampled down to obtain the corresponding low-resolution image. Secondly, the low-resolution of the image is divided into a few patches, and to assess each small patch of fractal dimension, and according to the value size of the fractal dimension, the image patches are divided into two categories, texture patches and smooth patches. Thirdly, using the existing trained dictionary pairs for low-resolution texture and smooth patches corresponding to high-resolution image reconstruction. Finally, high-resolution image is synthesized from these small patches of high resolution.

6. 发明专利

AU2020100274A4 A Multi-Scale Feature Fusion Network based on GANs for Haze Removal 未知
公开(公告)号：AU2020100274A4
公开(公告)日：2020-03-26
申请号：AU2020100274
申请日：2020-02-25
申请人： HUANG SHUYING DR , LI HONGXIA MISS , YANG YONG PROF
发明人： HUANG SHUYING , LI HONGXIA , YANG YONG
IPC分类号： G06T5/00 , G06N3/02 , G06N20/00 , G06T7/10
摘要： Image is an important objective representation of natural things, which is the basis of human vision, but it is facing the problem of haze pollution. This patent investigates a deep image dehazing network based on multi-scale feature extraction of Generative Adversarial Networks (GANs). Firstly, we split the hazy images into 9 image blocks, which not only makes the haze removal faster, but also takes into account the fact that the haze concentration at different depths of the image is inconsistent. Secondly, the hazy image blocks are sequentially sent into the proposed multi-scale feature fusion GANs for training. Finally, a splicing operation is performed on the 9 dehazed image blocks, then a deep-guided filtering is applied to the spliced image to eliminate the block effect. Image Cutting Figure 1 c Figure 2

7. 发明专利

AU2020100199A4 A medical image fusion method based on two-layer decomposition and improved spatial frequency 未知
公开(公告)号：AU2020100199A4
公开(公告)日：2020-03-19
申请号：AU2020100199
申请日：2020-02-08
申请人： CAO SIHUA MR , HUANG SHUYING DR , YANG YONG PROF
发明人： YANG YONG , CAO SIHUA , HUANG SHUYING
IPC分类号： G06T5/50
摘要： Abstract: Multi-modal medical image fusion is widely used in clinical diagnosis and treatment. This present patent investigates a novel multi-modal medical image fusion method based on Latent Low-Rank Representation (LatLRR) and modified spatial frequency. Firstly, the LatLRR is utilized to learn a project matrix which used to extract salient features. Then, the project matrix L after learning is used to decompose the source image into base part and detail part. Finally, for the detail layer, the modified spatial frequency is used to fuse the detail layer, and then guided filter is used to preserve the edge of the fused detail layer. For the base part, the method based on Visual saliency mapping (VSM) is used to fuse the base part. The fused image is obtained by combine the fused detail part and the base part. In addition, compared with other state-of-the-art fusion methods, experimental results demonstrate that proposed method has better fusion performance both in subjective visual and objective evaluation.

8. 发明专利

AU2020100462A4 Edge-preserving image super-resolution via low rank and total variation model 未知
公开(公告)号：AU2020100462A4
公开(公告)日：2020-04-30
申请号：AU2020100462
申请日：2020-03-26
申请人： HU XIAOYAN MISS , HUANG SHUYING DR , YANG YONG PROF
发明人： HUANG SHUYING , HU XIAOYAN , YANG YONG
IPC分类号： G06T5/00 , G06T5/20
摘要： The purpose of image super-resolution is to recover the corresponding high-resolution which can meet the corresponding needs from the low-resolution image. Because the low resolution image is blurred and noisy, some traditional methods in the past can not get good reconstruction results. In this patent, a method of low rank, total variation regularization and gradient regularization based on nearest neighbor regression are used to recover high-quality images. Block-Matching 3D filtering (BM3D) is used to make our method more robust to noise. The neighborhood regression method is used to reconstruct the low-resolution image to get more details. Low rank prior can be used to complete a matrix which principle is some rows and columns in the matrix can be linearly represented by other rows and columns. Total variation prior can effectively remove noise and process image edge information reasonably. Alternating direction method of multipliers (ADMM) method is used to optimize the algorithm and get better image super-resolution results. (a)BICUBIC (b)LRTV (c)SCSR (e)NCSR (f)OURS (h)ORIGINAL Figure 1

9. 发明专利

AU2020100196A4 A method of removing rain from single image based on detail supplement 未知
公开(公告)号：AU2020100196A4
公开(公告)日：2020-03-19
申请号：AU2020100196
申请日：2020-02-08
申请人： GUAN JUWEI , HUANG SHUYING DR , YANG YONG PROF
发明人： YANG YONG , GUAN JUWEI , HUANG SHUYING
IPC分类号： G06T5/20 , G06T7/33
摘要： Abstract: Images taken in rainy condition often contain a large number of raindrops, which will affect the image quality. Therefore, images taken in rainy days affect the improvement of application effects in other fields to some extent, such as object detection, image classification, image super-resolution, image segmentation, etc. Hence, we built a algorithm based on deep learning network with three steps to remove raindrops in the images and restore it to a high-quality image. Firstly, We built a generic diamond residual blocks to improve the ability to extract image features of convolution neural network, which can provide rich image context information for subsequent deraining steps. Secondly, Due to the mixability of raindrop shape, size and direction, a recurrent deraining structure is proposed for the network. Through the idea of derain step by step, the mixed raindrop is gradually removed and the image is recovered. Finally, In the process of remove raindrops often accompanied by some loss of image details. Based on this negative effect, a hybrid details complementary mechanism is constructed, which pass the residual information of shallow characteristics subtracted from deeper features of diamond residual block to the next iteration, and combined with the memory of the Gated Recurrent Unit to supplement details again, then details loss is well suppressed.

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式