scholarly journals Infrared Image Super Resolution by Combining Compressive Sensing and Deep Learning

Sensors ◽  
2018 ◽  
Vol 18 (8) ◽  
pp. 2587 ◽  
Author(s):  
Xudong Zhang ◽  
Chunlai Li ◽  
Qingpeng Meng ◽  
Shijie Liu ◽  
Yue Zhang ◽  
...  
Keyword(s):  
Deep Learning ◽  
High Resolution ◽  
Compressive Sensing ◽  
High Frequency ◽  
Infrared Imaging ◽  
Infrared Image ◽  
Super Resolution ◽  
Infrared Images ◽  
Frequency Information ◽  
Image Super Resolution

Super resolution methods alleviate the high cost and high difficulty in applying high resolution infrared image sensors. In this paper we present a novel single image super resolution method for infrared images by combining compressive sensing theory and deep learning. Low resolution images can be regarded as the compressed sampling results of the high resolution ones in compressive sensing. With sparsity in this theory, higher resolution images can be reconstructed. However, because of diverse level of sparsity for different images, the output contains noise and loss of high frequency information. Deep convolutional neural network provides a solution to relieve the noise and supplement some missing high frequency information. By concatenating two methods, we manage to produce better results in super resolution tasks for infrared images than SRCNN and ScSR. PSNR and SSIM values are used to quantify the performance. Applying our method to open datasets and actual infrared imaging experiments, we also find better visual results are preserved.

scholarly journals Image Super Resolution Reconstruction Based on Improved Invertible Rescaling Net

2021 ◽  
Author(s):  
Taiping Mo ◽  
Dehong Chen
Keyword(s):  
Feature Extraction ◽  
High Frequency ◽  
Interpolation Method ◽  
Super Resolution ◽  
Frequency Information ◽  
Ill Posed ◽  
Image Edge ◽  
Image Super Resolution ◽  
Improved Model ◽  
Image Details

Abstract The Invertible Rescaling Net (IRN) is modeling image downscaling and upscaling as a unified task to alleviate the ill-posed problem in the super-resolution task. However, the ability of potential variables of the model embedded high-frequency information is general, which affects the performance of the reconstructed image. In order to improve the ability of embedding high-frequency information and further reduce the complexity of the model, the potential variables and feature extraction of key components of IRN are improved. Attention mechanism and dilated convolution are used to improve the feature extraction block, reduce the parameters of feature extraction block, and allocate more attention to the image details. The high frequency sub-band interpolation method of wavelet domain is used to improve the potential variables, process and save the image edge, and enhance the ability of embedding high frequency information. Experimental results show that compared with IRN model, improved model has less complexity and excellent performance.

Low-observable targets detection for autonomous vehicles based on dual-modal sensor fusion with deep learning approach

2019 ◽  
Vol 233 (9) ◽  
pp. 2270-2283
Author(s):  
Keke Geng ◽  
Wei Zou ◽  
Guodong Yin ◽  
Yang Li ◽  
Zihao Zhou ◽  
...  
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Autonomous Vehicles ◽  
Deep Neural Network ◽  
Infrared Imaging ◽  
Infrared Image ◽  
Complex Environments ◽  
Infrared Images ◽  
Night Time ◽  
Perception System

Environment perception is a basic and necessary technology for autonomous vehicles to ensure safety and reliable driving. A lot of studies have focused on the ideal environment, while much less work has been done on the perception of low-observable targets, features of which may not be obvious in a complex environment. However, it is inevitable for autonomous vehicles to drive in environmental conditions such as rain, snow and night-time, during which the features of the targets are not obvious and detection models trained by images with significant features fail to detect low-observable target. This article mainly studies the efficient and intelligent recognition algorithm of low-observable targets in complex environments, focuses on the development of engineering method to dual-modal image (color–infrared images) low-observable target recognition and explores the applications of infrared imaging and color imaging for an intelligent perception system in autonomous vehicles. A dual-modal deep neural network is established to fuse the color and infrared images and detect low-observable targets in dual-modal images. A manually labeled color–infrared image dataset of low-observable targets is built. The deep learning neural network is trained to optimize internal parameters to make the system capable for both pedestrians and vehicle recognition in complex environments. The experimental results indicate that the dual-modal deep neural network has a better performance on the low-observable target detection and recognition in complex environments than traditional methods.

scholarly journals Infrared Image Super-Resolution Reconstruction Based on Quaternion Fractional Order Total Variation with Lp Quasinorm

2018 ◽  
Vol 8 (10) ◽  
pp. 1864 ◽  
Author(s):  
Xingguo Liu ◽  
Yingpin Chen ◽  
Zhenming Peng ◽  
Juan Wu ◽  
Zhuoran Wang
Keyword(s):  
Total Variation ◽  
Fractional Order ◽  
Infrared Image ◽  
Super Resolution ◽  
Objective Evaluation ◽  
Imaging Systems ◽  
Infrared Images ◽  
Alternating Direction ◽  
Image Super Resolution ◽  
Staircase Artifacts

Owing to the limitations of the imaging principle as well as the properties of imaging systems, infrared images often have some drawbacks, including low resolution, a lack of detail, and indistinct edges. Therefore, it is essential to improve infrared image quality. Considering the information of neighbors, a description of sparse edges, and by avoiding staircase artifacts, a new super-resolution reconstruction (SRR) method is proposed for infrared images, which is based on fractional order total variation (FTV) with quaternion total variation and the L p quasinorm. Our proposed method improves the sparsity exploitation of FTV, and efficiently preserves image structures. Furthermore, we adopt the plug-and-play alternating direction method of multipliers (ADMM) and the fast Fourier transform (FFT) theory for the proposed method to improve the efficiency and robustness of our algorithm; in addition, an accelerated step is adopted. Our experimental results show that the proposed method leads to excellent performances in terms of an objective evaluation and the subjective visual effect.

scholarly journals Align-Filter & Learn Video Super Resolution using Deep learning (AFLVSR)

2019 ◽  
Vol 8 (3S3) ◽  
pp. 634-640
Keyword(s):  
Deep Learning ◽  
High Resolution ◽  
Super Resolution ◽  
Multimedia Data ◽  
Data Streaming ◽  
High Resolution Data ◽  
Image Super Resolution ◽  
Increasing Demand ◽  
Temporal Information Extraction ◽  
Feature Alignment

In this article, we focused on the super-resolution technique in computer vision applications. During last decade, image super-resolution techniques have been introduced and adopted widely in various applications. However, increasing demand of high quality multimedia data has lead towards the high resolution data streaming. The conventional techniques which are based on the image super-resolution are not suitable for multi-frame SR. Moreover, the motion estimation, motion compensation, spatial and temporal information extraction are the well-known challenging issues in video super-resolution field. In this work, we address these issues and developed deep learning based novel architecture which performs feature alignment, filtering the image using deep learning and estimates the residual of low-resolution frames to generate the high-resolution frame. The proposed approach is named as Align-Filter & Learn Video Super resolution using Deep learning (AFLVSR). We have conducted and extensive experimental analysis which shows a significant improvement in the performance when compared with the state-of-art video SR techniques.

scholarly journals Infrared Image Super-Resolution via Progressive Compact Distillation Network

Electronics ◽  
2021 ◽  
Vol 10 (24) ◽  
pp. 3107
Author(s):  
Kefeng Fan ◽  
Kai Hong ◽  
Fei Li
Keyword(s):  
Transfer Learning ◽  
Learning Strategy ◽  
Infrared Image ◽  
Super Resolution ◽  
Infrared Images ◽  
Deep Convolutional Neural Networks ◽  
Calculation Algorithm ◽  
Reconstruction Performance ◽  
Image Super Resolution ◽  
Public Datasets

Deep convolutional neural networks are capable of achieving remarkable performance in single-image super-resolution (SISR). However, due to the weak availability of infrared images, heavy network architectures for insufficient infrared images are confronted by excessive parameters and computational complexity. To address these issues, we propose a lightweight progressive compact distillation network (PCDN) with a transfer learning strategy to achieve infrared image super-resolution reconstruction with a few samples. We design a progressive feature residual distillation (PFDB) block to efficiently refine hierarchical features, and parallel dilation convolutions are utilized to expand PFDB’s receptive field, thereby maximizing the characterization power of marginal features and minimizing the network parameters. Moreover, the bil-global connection mechanism and the difference calculation algorithm between two adjacent PFDBs are proposed to accelerate the network convergence and extract the high-frequency information, respectively. Furthermore, we introduce transfer learning to fine-tune network weights with few-shot infrared images to obtain infrared image mapping information. Experimental results suggest the effectiveness and superiority of the proposed framework with low computational load in infrared image super-resolution. Notably, our PCDN outperforms existing methods on two public datasets for both ×2 and ×4 with parameters less than 240 k, proving its efficient and excellent reconstruction performance.

scholarly journals SR-Inpaint: A General Deep Learning Framework for High Resolution Image Inpainting

Algorithms ◽  
2021 ◽  
Vol 14 (8) ◽  
pp. 236
Author(s):  
Haoran Xu ◽  
Xinya Li ◽  
Kaiyi Zhang ◽  
Yanbai He ◽  
Haoran Fan ◽  
...  
Keyword(s):  
Deep Learning ◽  
High Resolution ◽  
High Frequency ◽  
Image Inpainting ◽  
Super Resolution ◽  
Low Resolution ◽  
Resolution Image ◽  
Learning Framework ◽  
High Resolution Image ◽  
High Resolution Images

Recently, deep learning has enabled a huge leap forward in image inpainting. However, due to the memory and computational limitation, most existing methods are able to handle only low-resolution inputs, typically less than 1 K. With the improvement of Internet transmission capacity and mobile device cameras, the resolution of image and video sources available to users via the cloud or locally is increasing. For high-resolution images, the common inpainting methods simply upsample the inpainted result of the shrinked image to yield a blurry result. In recent years, there is an urgent need to reconstruct the missing high-frequency information in high-resolution images and generate sharp texture details. Hence, we propose a general deep learning framework for high-resolution image inpainting, which first hallucinates a semantically continuous blurred result using low-resolution inpainting and suppresses computational overhead. Then the sharp high-frequency details with original resolution are reconstructed using super-resolution refinement. Experimentally, our method achieves inspiring inpainting quality on 2K and 4K resolution images, ahead of the state-of-the-art high-resolution inpainting technique. This framework is expected to be popularized for high-resolution image editing tasks on personal computers and mobile devices in the future.

Sign in / Sign up

Export Citation Format

Share Document