scholarly journals Nonuniformity Correction of Single Infrared Images Based on Deep Filter Neural Network

Symmetry ◽  
2018 ◽  
Vol 10 (11) ◽  
pp. 612 ◽  
Author(s):  
Xianzhong Jian ◽  
Chen Lv ◽  
Ruzhi Wang
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Infrared Imaging ◽  
Imaging System ◽  
Infrared Images ◽  
Nonuniformity Correction ◽  
Training Images ◽  
Quantitative Measurements ◽  
Complex Training ◽  
Simulated Training

The fixed-pattern noise (FPN) caused by nonuniform optoelectronic response limits the sensitivity of an infrared imaging system and severely reduces the image quality. Therefore, nonuniform correction of infrared images is very important. In this paper, we propose a deep filter neural network to solve the problems of network underfitting and complex training with convolutional neural network (CNN) applications in nonuniform correction. Our work is mainly based on the idea of deep learning, where the nonuniform image noise features are fully learned from a large number of simulated training images. The network is designed by introducing the filter and the subtraction structure. The background interference of the image is removed by the filter, so the learning model is gathered in the nonuniform noise. The subtraction structure is used to further reduce the input-to-output mapping range, which effectively simplifies the training process. The results from the test on infrared images shows that our algorithm is superior to the state-of-the-art algorithm in visual effects and quantitative measurements, providing a new method for deep learning in nonuniformity correction of single images.

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.

Ammonia and Near-Infrared Observations of Southern Dark Clouds

1993 ◽  
Vol 10 (3) ◽  
pp. 236-240 ◽  
Author(s):  
T.L. Bourke ◽  
A.R. Hyland ◽  
G. Robinson ◽  
S.D. James
Keyword(s):  
Near Infrared ◽  
Infrared Imaging ◽  
Imaging System ◽  
Ammonia Emission ◽  
Infrared Images ◽  
Infrared Source ◽  
Visual Appearance ◽  
Infrared Observations ◽  
Dark Clouds ◽  
Ammonia Source

AbstractThe Parkes radio telescope has been used to search a list of small, dense southern dark clouds and Bok globules for ammonia emission at 23.7 GHz. The ammonia observations, together with IRAS data and the cloud’s visual appearance, have been used to determine a short list of dark clouds for observation with the infrared imaging system (IRIS) on the Anglo-Australian Telescope, in an attempt to determine the dust density distribution within the clouds. Near-infrared images of a number of the short listed clouds have been obtained with IRIS at J, H and K’. Preliminary results are reported for this ammonia survey, together with IRIS images of the strong ammonia source DC 297.7–2.8. Coincident with the dense ammonia core of this object is an IRAS ‘core’ source, IRAS 11590–6452 and an extremely interesting near-infrared source, which lies on the edge of the error ellipse of the IRAS source.

Stripe nonuniformity correction for infrared imaging system based on single image optimization

2018 ◽  
Vol 91 ◽  
pp. 250-262 ◽  
Author(s):  
Weiping Hua ◽  
Jufeng Zhao ◽  
Guangmang Cui ◽  
Xiaoli Gong ◽  
Peng Ge ◽  
...  
Keyword(s):  
Infrared Imaging ◽  
Imaging System ◽  
Single Image ◽  
Nonuniformity Correction ◽  
Infrared Imaging System ◽  
Image Optimization

scholarly journals Classification Using Neural Networks and Deep Learning

2020 ◽  
Author(s):  
Raju Singh
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Deep Learning ◽  
Training Images ◽  
The World ◽  
Insight Into

This report is an insight into the world of deep learning and CNN networks. It is an attempt to perform classification using neural network and deep learning for a given dataset (which is a subset from the MNIST dataset). The MNIST dataset contains 70,000 images of handwritten digits, divided into 60,000 training images and 10,000 testing images.

scholarly journals Deep-Learning-Based Halo-Free White-Light Diffraction Phase Imaging

2021 ◽  
Vol 9 ◽  
Author(s):  
Kehua Zhang ◽  
Miaomiao Zhu ◽  
Lihong Ma ◽  
Jiaheng Zhang ◽  
Yong Li
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
White Light ◽  
Imaging System ◽  
Light Diffraction ◽  
Phase Image ◽  
Phase Imaging ◽  
The Neural Network ◽  
Phase Images ◽  
Measured Phase

In white-light diffraction phase imaging, when used with insufficient spatial filtering, phase image exhibits object-dependent artifacts, especially around the edges of the object, referred to the well-known halo effect. Here we present a new deep-learning-based approach for recovering halo-free white-light diffraction phase images. The neural network-based method can accurately and rapidly remove the halo artifacts not relying on any priori knowledge. First, the neural network, namely HFDNN (deep neural network for halo free), is designed. Then, the HFDNN is trained by using pairs of the measured phase images, acquired by white-light diffraction phase imaging system, and the true phase images. After the training, the HFDNN takes a measured phase image as input to rapidly correct the halo artifacts and reconstruct an accurate halo-free phase image. We validate the effectiveness and the robustness of the method by correcting the phase images on various samples, including standard polystyrene beads, living red blood cells and monascus spores and hyphaes. In contrast to the existing halo-free methods, the proposed HFDNN method does not rely on the hardware design or does not need iterative computations, providing a new avenue to all halo-free white-light phase imaging techniques.

scholarly journals Face Recognition with CNN and Inception Deep Learning Models

2019 ◽  
Vol 8 (3) ◽  
pp. 1932-1938
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Deep Learning ◽  
Face Recognition ◽  
Convolutional Neural Network ◽  
Training Image ◽  
Learning Models ◽  
Training Images ◽  
Testing Data ◽  
Facial Images

In this work, deep learning methods are used to classify the facial images. ORL Database is used for the purpose of training the models and for testing. Three kinds of models are developed and their performances are measured. Convolutional Neural Networks (CNN), Convolutional Neural Network Based Inception Model with single training image per class (CNN-INC) and Convolutional Neural Network Based Inception Model with several training images per class (CNN-INC-MEAN) are developed. The ORL database has ten facial images for each person. Five images are used for training purpose and remaining 5 images are used for testing. The five images for the training are chosen randomly so that two sets of training and testing data is generated. The models are trained and tested on the two sets that are drawn from the same population. The results are presented for accuracy of face recognition

A Hardware Method of Realizing IRFPA Nonuniformity Compressing Correction

2013 ◽  
Vol 427-429 ◽  
pp. 1068-1071
Author(s):  
Peng Fei Li ◽  
Zhi Hui Du ◽  
Xing Fu Li ◽  
Yong Qiang Liu
Keyword(s):  
Real Time ◽  
Infrared Imaging ◽  
Imaging System ◽  
Correction Method ◽  
Circuit Diagram ◽  
Simple Circuit ◽  
Nonuniformity Correction ◽  
Infrared Imaging System ◽  
Hardware Circuit

Nonuniformity of Infrared Focal Plane Array (IRFPA) has greatly limited the quality of infrared imaging system, so nonuniformity must be corrected before using IRFPA. In order to reduce nonuniformity correction calculating amount and improve real-time nonuniformity correction speed, a new compressing correction method of utilizing hardware memory is presented. In this paper, memory compressing correction principle and implementing process are expounded in detail, and the hardware circuit diagram is given out. The experimental results prove that the method has simple circuit and excellent image quality and it easily realizes real-time nonuniformity correction.

Sign in / Sign up

Export Citation Format

Share Document