Infrared Image Simulation Research Articles

An improved infrared simulation method based on generative adversarial networks

Infrared simulation technology has great application value in the fields of UAV target simulation and infrared signal processing. However, traditional infrared simulation technology has the disadvantages of poor scene adaptability, low fidelity of infrared simulation images and long training time. This paper proposes an infrared image simulation algorithm based on improved Generative Adversarial Networks(GAN) to generate multi-scene infrared images, which could provide a reliable expansion of infrared database. First, we construct a GAN model by introducing a multi-resolution hierarchical structure and attention mechanism, which can effectively enhance the model’s adaptability to different scenes during the simulation of generating infrared images. Secondly, the SSIM loss term and L1 loss term are introduced during the training process to form a composite loss function, which prompts the proposed GAN to generate high-fidelity infrared simulation images. Finally, while maintaining the quality of simulated infrared images, a lightweight model is designed through model compression to significantly reduce the number of model parameters.The traditional discriminator based on the UNet-self attention is replaced by a discriminator based on attention mechanisms and adaptive max-pooling structure. The proposed GAN is trained and tested on three public datasets. Experimental results demonstrate that the proposed method improves structural similarity by 11% compared to Pix2Pix and achieves a Peak Signal-to-Noise Ratio (PSNR) of 25.8, which is 3.9 higher than InfraGAN. At the same time, compared with InfraGAN, the number of model parameters is reduced by 68% , which makes the method efficiently obtain simulated infrared images corresponding to given visible images.

Research on Simulation Technology of Photoelectric Theodolite Based on Measured Infrared Image Sequence

Infrared image simulation[1] is an effective means to test, train and evaluate photoelectric theodolite, which has very important economic and military value. To solve the problems of weak pertinence, low fidelity, and complex algorithm of traditional infrared image simulation technology, this paper proposes a new infrared simulation technology based on a measured image sequence. Through automatic background stitching, moving target detection and extraction, a real-time fusion of target background, and infrared image simulation of real target/background is realized. The experimental results show that the technique has high accuracy and good real-time performance, and provides reliable technical support for the performance evaluation and personnel training of photoelectric theodolite.

Learning to measure infrared properties of street views from visible images

With the rapid development of infrared cameras, infrared images which have the unique advantage of all-weather detection ability are more and more incorporated into practical applications. However, it is hard to develop infrared-domain artificial intelligence with the shortage of labeled infrared data. Traditional infrared image simulation techniques face the problem of strict parameters, slow solution speed, and limited scenarios. In this paper, we tackle the problem of simulating infrared image proprieties with generative networks via reference to visible images. We propose a novel infrared image generation model that complied with the infrared imaging principle, the V2IR-GAN, consisting of spontaneous emission, reflected radiation and transmission coefficient modules. Extensive experiments and analyses are conducted to demonstrate the high stimulative performance of the V2IR-GAN, showing that it achieves the best SSIM of 88.2% against the state-of-the-art generative models. We also provide a specific application to validate the practicability of the V2IR-GAN.

Amalgamation of Geometry Structure, Meteorological and Thermophysical Parameters for Intelligent Prediction of Temperature Fields in 3D Scenes.

Temperature field calculation is an important step in infrared image simulation. However, the existing solutions, such as heat conduction modelling and pre-generated lookup tables based on temperature calculation tools, are difficult to meet the requirements of high-performance simulation of infrared images based on three-dimensional scenes under multi-environmental conditions in terms of accuracy, timeliness, and flexibility. In recent years, machine learning-based temperature field prediction methods have been proposed, but these methods only consider the influence of meteorological parameters on the temperature value, while not considering the geometric structure and the thermophysical parameters of the object, which results in the low accuracy. In this paper, a multivariate temperature field prediction network based on heterogeneous data (MTPHNet) is proposed. The network fuses geometry structure, meteorological, and thermophysical parameters to predict temperature. First, a Point Cloud Feature Extraction Module and Environmental Data Mapping Module are used to extract geometric information, thermophysical, and meteorological features. The extracted features are fused by the Data Fusion Module for temperature field prediction. Experiment results show that MTPHNet significantly improves the prediction accuracy of the temperature field. Compared with the v-Support Vector Regression and the combined back-propagation neural network, the mean absolute error and root mean square error of MTPHNet are reduced by at least 23.4% and 27.7%, respectively, while the R-square is increased by at least 5.85%. MTPHNet also achieves good results in multi-target and complex target temperature field prediction tasks. These results validate the effectiveness of the proposed method.

V2T-GAN: Three-Level Refined Light-Weight GAN with Cascaded Guidance for Visible-to-Thermal Translation.

Infrared image simulation is challenging because it is complex to model. To estimate the corresponding infrared image directly from the visible light image, we propose a three-level refined light-weight generative adversarial network with cascaded guidance (V2T-GAN), which can improve the accuracy of the infrared simulation image. V2T-GAN is guided by cascading auxiliary tasks and auxiliary information: the first-level adversarial network uses semantic segmentation as an auxiliary task, focusing on the structural information of the infrared image; the second-level adversarial network uses the grayscale inverted visible image as the auxiliary task to supplement the texture details of the infrared image; the third-level network obtains a sharp and accurate edge by adding auxiliary information of the edge image and a displacement network. Experiments on the public dataset Multispectral Pedestrian Dataset demonstrate that the structure and texture features of the infrared simulation image obtained by V2T-GAN are correct, and outperform the state-of-the-art methods in objective metrics and subjective visualization effects.

Research on simulated infrared image utility evaluation using deep representation

Infrared (IR) image simulation is an important data source for various target recognition systems. However, whether simulated IR images could be used as training data for classifiers depends on the features of fidelity and authenticity of simulated IR images. For evaluation of IR image features, a deep-representation-based algorithm is proposed. Being different from conventional methods, which usually adopt a priori knowledge or manually designed feature, the proposed method can extract essential features and quantitatively evaluate the utility of simulated IR images. First, for data preparation, we employ our IR image simulation system to generate large amounts of IR images. Then, we present the evaluation model of simulated IR image, for which an end-to-end IR feature extraction and target detection model based on deep convolutional neural network is designed. At last, the experiments illustrate that our proposed method outperforms other verification algorithms in evaluating simulated IR images. Cross-validation, variable proportion mixed data validation, and simulation process contrast experiments are carried out to evaluate the utility and objectivity of the images generated by our simulation system. The optimum mixing ratio between simulated and real data is 0.2≤γ≤0.3, which is an effective data augmentation method for real IR images.

Parallel BRDF-based infrared radiation simulation of aerial targets implemented on Intel Xeon processor and Xeon Phi coprocessor

The infrared (IR) radiance of an aerial target owing to the reflection of the external sources including the sun, atmosphere and the earth’s surface is a key factor to consider in the modeling and simulation of the IR image in the studies of target detection and tracking, guidance and camouflage. Since the radiations of atmosphere and the earth’s surface spread in the whole space and over a wide spectrum, the geometrical shape of targets is complex, and their surfaces are usually non-Lambertian, serial implementation on a CPU platform is time-consuming, and thus, the acceleration of the calculation process is desired in engineering projects. The inherent parallelism that the reflection of radiations incident from different directions in each spectral wavelength can be calculated in parallel in this problem encourages us to accelerate it on multi-core platforms, which are common nowadays. In this work, a dual-socket Intel Xeon E5-2620 nodes running at 2.00 GHz are utilized first. Subsequently, implementations using native and offload modes on the Intel Xeon Phi 5110p coprocessor are described in detail. In both the host-only and Xeon Phi-based implementations, the OpenMP directives are used. Compared to their single-threaded counterpart, the host-only version is 9.7x faster. By increasing the scalability and vectorization, speedups obtained in the native and offload mode implementations were 13.8x and 13.0x, respectively. Our results show that the Xeon Phi’s performance on calculating the target’s reflected radiance of background radiation is promising in the IR image simulation.

Infrared Image Simulation of Ground Maneuver Target and Scene Based on OGRE

Infrared scene simulation has extensive application value in military and civil fields. According to the specific experiment environment, this paper simulation of an infrared scene and according to the experimental data produced infrared texture library. First of all, through the 3Dmax modeling software to establish the target infrared radiation model, and calculate the relevant radiation data of it. Then analyze the radiation characteristics of the relevant materials, the establishment of infrared texture library for each material. And finally, use OGRE engine image rendering technology and GPU programmable pipeline technique to simulate a complex infrared scene close to the real.

Infrared Image Contrast Enhancement Based on Modified Particle Swarm Optimization

Adaptive infrared image contrast enhancement is presented based on modified particle swarm optimization (PSO) and incomplete Beta Function. On the basis of traditional PSO, modified PSO integrates into the theory of Multi-Particle Swarm and evolution theory algorithm. By using separate search space optimal solution of multiple particles, the global search ability is improved. And in the iteration procedures, timely adjustment of acceleration coefficients is convenient for PSO to find the global optimal solution in the later iteration. Through infrared image simulation, experimental results show that the modified PSO is better than the standard PSO in computing speed and convergence.

Research on Scene Infrared Image Simulation

Vega has been widely used in the Virtual Reality field. Its infrared (IR) module can implement IR simulation, but Vega IR imaging simulation’s general approach does not apply to the complex scene. This article deeps into the scene’s IR simulation method based on Vega. We design and realize a real time scene IR image simulation system in this article. We quantitatively define the scene as a simple and complex scene according to the scene range and whether it includes Digital Elevation Model (DEM) / Digital Surface Model (DSM) data. For the simple scene, we directly process IR image simulation according to the Vega general IR simulation process. While for the complex scene, we propose an IR image simulation method based on image classification and automatic texture material mapping technique. At the aspect of image classification, we develop a coarse to fine K-means clustering method based on the consistency of image color for color image classification and an additional Support Vector Machine (SVM) classification method based on texture features for gray level image classification. The method was tested on different scene’s IR simulation. Experimental results show that the proposed approach can achieve better applicability and greater efficiency than the popular Vega IR simulation method.

OSIrIS: a physically based simulation tool to improve training in thermal infrared remote sensing over urban areas at high spatial resolution

This paper describes an infrared image simulator for remote sensing applications, called OSIrIS (outdoor scene and infrared image simulation). It has been developed partly for training and reproduces with great details the physical phenomena that play a major role in complex urban environment. OSIrIS performs a synthesis of scene based on a 3-D description of the landscape with a high spatial resolution (0.5–10 m). The physical processes are briefly described and their importance with respect to the objectives are discussed. Thermal emission depends on temperature and generally dominates the signal. Temperature is governed by heat equation and is solved by the means of boundary conditions such as in-depth temperature and flux balance at surface. Main parameters are solar and atmospheric radiations, wind, heat conduction and changes in humidity. An innovative approach was developed to take into account variations in time of the interactions between the landscape and the physical processes. OSIrIS aims at simulating situations that are encountered in reality. It enables users self-formation, helping them understanding changes in image radiance as a function of the input parameters and their own simulation requirements. Examples are given that illustrate specific aspects of infrared images.

Passive Visible To Infrared Transducer For Dynamic Infrared Image Simulation

Abstract. A passive visible to infrared image transducer is described which, for the first time, allows practical simulation of high resolution dynamic infrared imagery. A theoretical performance analysis is presented which indicates that an MTF (modulation transfer function) of 50% at 5 cycles/mm is achievable with a time response of less than 20 msec and a required input power of less than 2 mW/cm2 per simulated degree AT. Experimental results on working devices are reported which match theoretical predictions. Successful simulation of high speed real-world infrared imagery is described. Suggestions for future work which should further enhance resolution and dynamic range are presented.