Non-uniformity Correction Method Research Articles

PSNet: A non-uniform illumination correction method for underwater images based pseudo-siamese network

Autonomous underwater vehicles (AUVs) based on visual perception play an important role in maritime operations. However, underwater environment often suffers from poor lighting conditions, making the utilization of artificial light sources necessary. This reliance on artificial lighting frequently results in non-uniform illumination. Furthermore, the absorption and scattering effects of water cause further degradation, such as color distortion and blurring of details. To address these challenges, we propose a pseudo-siamese network, named PSNet, designed for underwater optical image enhancement. PSNet separates the non-uniformly illuminated layer from the optimally uniformly illuminated image and utilizes a cascading iteration strategy to enhance the image details. To achieve a better balance prediction quality, we introduce structure loss and residual reconstruction loss as additional guides for model learning. Additionally, we incorporate a color consistency loss to mitigate color distortion. To address the lack of training data, we develop a non-uniform illumination model and generate a dataset that includes both non-uniformly illuminated layers and uniformly illuminated images. Through comprehensive experimental evaluations, PSNet significantly enhances the visual quality of underwater optical images and consistently outperforms state-of-the-art approaches in multiple performance metrics.

Infrared non-uniformity correction method based on binocular detection system without blindsight

The output image of an infrared detector often suffers from non-uniformity due to the inhomogeneity of the device material and limitations in the manufacturing process, which can reduce the detector's capability to detect and identify targets. It is therefore necessary to adequately correct the non-uniformity to fully utilize the high temperature sensitivity of the detector. Calibration-based non-uniformity correction technology is one of the earliest and most effective methods of correcting non-uniformity. Typically, a relatively uniform shutter is used to mask the field of view for calibration correction. However, this process interrupts the observation due to the need for masking, severely limiting its use in real-world projects. In order to maintain the performance superiority of the calibration-based method and eliminate the defect of target loss caused by masking, this paper takes the occlusion calibration as the theoretical basis, which consists of dual detectors to form a binocular detection system, and uses one of the occluded calibration auxiliary detector to assist the other occlusion-free primary detector, and takes advantage of the fact that the radiation is the same when observing the same target at the same time to make the correct response based on the steepest gradient descent learning algorithm, which removes the non-uniformity while achieving detail fidelity, no ghosting and continuous output.

Efficient infrared nonuniform correction method considering optical attenuator and integration time

With the increasing number of optical attenuators and integration times in infrared imaging systems, this paper proposes an efficient nonuniform correction method that addresses drawbacks of complex operations and coefficient storage with traditional two-point nonuniform correction methods. First, the efficient nonuniform correction model was derived through the response model of the infrared imaging system with variable attenuators and integration times, which can achieve nonuniform correction of all attenuators and integration times using a correction equation. Based on the model, the efficient nonuniformity correction algorithm using a small number blackbody images was proposed. Finally, the experimental results show that the method has excellent nonuniformity correction performance. Compared with the two-point correction method, the maximum nonuniformity is reduced from 3.7% for the two-point method to 2.2% for the proposed method. In the meantime, the proposed method can greatly reduce the correction time and the number of blackbody temperature sampling points. Moreover, for the infrared imaging system with five integral times and three attenuators in this paper, the two-point method requires 30 correction coefficients, while the proposed method only requires eight correction coefficients. It reduces the required correction coefficients by about three times, achieving efficient and fast nonuniform correction.

Spatio-temporal deep recurrent convolutional neural network for infrared focal plane arrays non-uniformity correction

The inherent non-uniformity generated in infrared focal plane arrays (IRFPA) due to inconsistent responses of detectors, and it significantly degrades the performance of infrared imaging systems. Traditional Non-Uniformity Correction (NUC) methods mainly leverage the temporal low-frequency property of non-uniformity to remove it. In recent years, Convolutional Neural Network (CNN) has gained attention as a powerful tool for conducting NUC using solely spatial information from a single frame. In this study, we propose a deep neural network with a recurrent spatio-temporal feature fusion module to enhance CNN performance using inter-frame information. Initially, the proposed network uses CNN to coarsely extract FPN features solely from the spatial domain. Subsequently, the network merges it with the historical estimation under the guidance of two gating signals, which calculated from spatio-temporal information with gated convolutional layers. Both stages are jointly trained to ensure that the entire network operates end-to-end and adapts to different scenarios, eliminating complex parameter tuning efforts. Experiments demonstrated that the proposed network shows both the advantages of traditional and CNN-based NUC methods. It has a higher convergence starting point, faster convergence speed, and a 1 ∼ 2 dB improvement in PSNR compared to both types of methods.

Nonuniformity Correction Method of Infrared Detector Based on Statistical Properties

Nonuniformity Correction Method of Infrared Detector Based on Statistical Properties

Scene-Based Nonuniformity Correction Method Using Principal Component Analysis for Infrared Focal Plane Arrays

In this paper, principal component analysis is introduced to form a scene-based nonuniformity correction method for infrared focal plane arrays. The estimation of the gain and offset of the infrared detector and the correction of nonuniformity based on the neural network method with a novel estimation of desired target value are achieved concurrently. The current frame and several adjacent registered frames are decomposed onto a set of principal components, and then the first principal component is extracted to construct the desired target value. It is practical, forms fewer ghosting artifacts, and considerably promotes correction precision. Numerical experiments demonstrate that the proposed method presents excellent performance when dealing with clean infrared data with synthetic pattern noise as well as the real infrared video sequence.

Low-contrast scene feature-based infrared nonuniformity correction method for airborne target detection

The fixed mode noise (FPN) caused by the nonuniform response of the infrared focal plane array (IRFPA) will inevitably affect the image quality, so the nonuniformity correction (NUC) method is needed to eliminate such noise. Most of the traditional NUC methods are suitable for high-contrast scenes but do not work as well in low-contrast scenes such as sky and water. Therefore, this paper proposes an infrared NUC method based on feature extraction and image registration for low-contrast scenes and combines the Kalman filter to accelerate the convergence speed, which achieves a good NUC effect. A threshold gating mechanism of learning rate is proposed to eliminate the influence of discrete defective pixels without losing the details of the target. In simulation, the proposed method can achieve high-precision image registration in low-contrast scenes, and the registration error can be less than 0.5 pixels under the condition of a signal-to-noise ratio (SNR) of 3. The experimental results of real infrared images show that the average roughness index of 0.0563 and the target SNR of 7.99 can be obtained after correcting the real infrared image with the proposed method, both of which are better than other methods, thus verifying the effectiveness and superiority of the proposed method.

Real-time on-orbit image quality improvement for a wide-field imaging system with detector arrays.

Wide-field imaging systems are faced with the problem of massive image information processing and transmission. Due to the limitation of data bandwidth and other factors, it is difficult for the current technology to process and transmit massive images in real-time. With the requirement for fast response, the demand for real-time on-orbit image processing is increasing. In practice, nonuniformity correction is an important preprocessing step to improve the quality of surveillance images. This paper presents a new real-time on-orbit nonuniform background correction method, which only uses the local pixels of a single row output in real-time, breaking the dependence of the traditional algorithm on the whole image information. Combined with the FPGA pipeline design, when the local pixels of a single row are read out, the processing is completed, and no cache is required at all, which saves the resource overhead in hardware design. It achieves microsecond-level ultra-low latency. The experimental results show that under the influence of strong stray light and strong dark current, our real-time algorithm has a better image quality improvement effect compared with the traditional algorithm. It will greatly help the on-orbit real-time moving target recognition and tracking.

Automatic Inhomogeneous Background Correction for Spatial Target Detection Image Based on Partition Processing

High-resolution imaging with wide field of view (FoV) ground-based telescopes is often affected by skylight background and noise due to the detector, resulting in an inhomogeneous background. In this paper, we propose an improved method for spatial image non-uniformity correction based on partition processing. First, an evaluation metric is introduced to evaluate the partition size and automatically iterate a suitable partition value for different scenarios based on the different operating conditions of the telescope. Then, we iteratively calculate the mean and variance in each partitioned region to extract the background of each partitioned region. Finally, after applying bilinear interpolation to the background extracted from each region, the inhomogeneous background is obtained and removed from the original image. The experiments on the simulated and real images show that the proposed method can effectively remove the inhomogeneous background of spatial images and meet the requirements of the real-time processing of high-resolution images under long exposure conditions.

Progressive Nonuniformity Correction for Aero-Optical Thermal Radiation Images via Bilateral Filtering and Bézier Surface Fitting

When a high-speed aircraft flies in the atmosphere, the imaging window is subjected to airflow friction, the kinetic energy of the airflow is converted into thermal energy, which makes the surface temperature of the imaging window rise unevenly, the imaging quality is significantly reduced, called aero-optical thermal radiation effects. The continuously increasing nonuniform thermal radiation bias field is not conducive to the precise identification of the target. To remove the bias field in degraded infrared images, this article proposes a progressive nonuniformity correction method. First, we establish a progressive thermal radiation effects correction model to estimate the thermal radiation bias field based on bilateral filtering and Bézier surface fitting. Then, to avoid overfitting the bias field, the degree of Bézier surface is reduced progressively during the iterative process. Finally, according to the properties of the heat transfer of the aero-optical thermal radiation effects, a gradient orientation prior is imposed for both the thermal radiation bias field and the latent clear image. Experiments on simulated degraded images and real degraded IR images show that our method can reduce the thermal radiation effects residual compared with the current aero-optical thermal radiation effects correction methods.

Visible-Image-Assisted Nonuniformity Correction of Infrared Images Using the GAN with SEBlock

Aiming at reducing image detail loss and edge blur in the existing nonuniformity correction (NUC) methods, a new visible-image-assisted NUC algorithm based on a dual-discriminator generative adversarial network (GAN) with SEBlock (VIA-NUC) is proposed. The algorithm uses the visible image as a reference for better uniformity. The generative model downsamples the infrared and visible images separately for multiscale feature extraction. Then, image reconstruction is achieved by decoding the infrared feature maps with the assistance of the visible features at the same scale. During decoding, SEBlock, a channel attention mechanism, and skip connection are used to ensure that more distinctive channel and spatial features are extracted from the visible features. Two discriminators based on vision transformer (Vit) and discrete wavelet transform (DWT) were designed, which perform global and local judgments on the generated image from the texture features and frequency domain features of the model, respectively. The results are then fed back to the generator for adversarial learning. This approach can effectively remove nonuniform noise while preserving the texture. The performance of the proposed method was validated using public datasets. The average structural similarity (SSIM) and average peak signal-to-noise ratio (PSNR) of the corrected images exceeded 0.97 and 37.11 dB, respectively. The experimental results show that the proposed method improves the metric evaluation by more than 3%.

A Nonuniformity Correction Method Based on 1D Guided Filtering and Linear Fitting for High-Resolution Infrared Scan Images

During imaging, each infrared focal plane linear array scan detector detection unit determines a row of pixels in the image output. This sensor’s nonuniformity appears as horizontal stripes. Correcting nonuniformity in high-resolution images without destroying delicate details is challenging. In this paper, a single-frame-based nonuniformity correction algorithm is proposed. A portion of a single-frame picture is intercepted initially. The 1D column guided filter is applied to smooth the captured image in the vertical direction. Then, the smooth image and high-frequency component with horizontal stripes and texture information are obtained. The subsequent step is to use the smooth portion of the image as the guided image and the high-frequency portion of the image as the input, so that the estimated nonuniformity noise of the image may be extracted using a 1D row guided filter. The segment of the corrected image is then obtained by subtracting the estimated nonuniformity noise from the segment of the raw image. The correction coefficients could be obtained by performing a linear regression fit on the pre- and post-guided filtering image segments. With the correction coefficients, the entire image could be corrected. Based on qualitative and quantitative analysis, the proposed algorithm outperforms other current advanced algorithms in terms of nonuniformity correction and real-time performance.

Nonuniform Correction of Ground-Based Optical Telescope Image Based on Conditional Generative Adversarial Network.

Ground-based telescopes are often affected by vignetting, stray light and detector nonuniformity when acquiring space images. This paper presents a space image nonuniform correction method using the conditional generative adversarial network (CGAN). Firstly, we create a dataset for training by introducing the physical vignetting model and by designing the simulation polynomial to realize the nonuniform background. Secondly, we develop a robust conditional generative adversarial network (CGAN) for learning the nonuniform background, in which we improve the network structure of the generator. The experimental results include a simulated dataset and authentic space images. The proposed method can effectively remove the nonuniform background of space images, achieve the Mean Square Error (MSE) of 4.56 in the simulation dataset, and improve the target's signal-to-noise ratio (SNR) by 43.87% in the real image correction.

Noise Parameter Estimation Two-Stage Network for Single Infrared Dim Small Target Image Destriping

The existing nonuniformity correction methods generally have the defects of image blur, artifacts, image over-smoothing, and nonuniform residuals. It is difficult for these methods to meet the requirements of image enhancement in various complex application scenarios. In particular, when these methods are applied to dim small target images, they may remove dim small targets as noise points due to the image over-smoothing. This paper draws on the idea of a residual network and proposes a two-stage learning network based on the imaging mechanism of an infrared line-scan system. We adopt a multi-scale feature extraction unit and design a gain correction sub-network and an offset correction sub-network, respectively. Then, we pre-train the two sub-networks independently. Finally, we cascade the two sub-networks into a two-stage network and train it. The experimental results show that the PSNR gain of our method can reach more than 15 dB, and it can achieve excellent performance in different backgrounds and different intensities of nonuniform noise. Moreover, our method can avoid losing texture details or dim small targets after effectively removing nonuniform noise.

Real-Time Non-Uniformity Correction without TEC for Microbolometer Array

This paper describes a new readout integrated circuit and non-uniformity correction (NUC) method that ensures that the bolometer array has low non-uniformity over a wide operating temperature range without a thermoelectric cooler (TEC). The proposed NUC minimizes the circuit and memory required for signal processing, making it suitable for compact and power-efficient portable infrared cameras. It corrects the aging phenomenon through start-up calibration and corrects non-uniformities without a TEC through calibration during operation mode. It minimizes the calibration process during operation mode and uses a pixel-level analog-to-digital converter to enable real-time NUC. A 0.18 μm standard CMOS process is applied to the proposed NUC. The frame rate for calibration during the operation mode is approximately 14.3 Hz. The proposed NUC demonstrates excellent uniformity with a non-uniformity of less than 0.12% over a wide operating temperature range (−20 to 50 °C).

Non-uniformity Correction Method of Remote Sensing Images based on Adaptive Moving Window Moment Matching

To improve the quality of optical remote sensing images, this paper proposes an adaptive moving window moment matching method for non-uniformity correction of remote sensing images. First, the scene complexity of the remote sensing image to be corrected is calculated, and the range of the width of the moving window is determined accordingly; Subsequently, the local scene complexity of the image in the window centered on the column to be corrected is calculated, and the width of the moving window is controlled adaptively; the correction gain and offset values of the column to be corrected of the image in the moving window are then calculated, and the correction of the columns to be corrected is performed accordingly; finally, the whole remote sensing image is traversed, and moment matching correction is performed column by column, and the correction of the non-uniformity of the whole remote sensing image is completed. The experimental results show that the non-uniformity correction effect of this algorithm is better than other competing algorithms, and the mean value of non-uniformity coefficient of the corrected image is reduced by more than 0.1802% compared with the minimum value in other comparison algorithms, which effectively eliminates the streak and stripe noise in the image, and better preserves the detailed information of the image.

Adaptive section non-uniformity correction method of short-wave infrared star images for a star tracker.

Using a short-wave infrared (SWIR) camera to improve daytime star detection ability has become a trend for near-ground star trackers. However, the noise of SWIR star images greatly decreases the accuracy of the attitude measurement results. Aiming at a real-time application of the star tracker, an adaptive section non-uniformity correction method based on the two-point correction algorithm for SWIR star images is proposed. The correction parameters of different sections are first calculated after the defective pixels are detected and excluded, and the real-time image is corrected using adaptive section parameters according to its gray value distribution. Finally, the defective pixels are compensated for by their adjacent corrected pixels. The correction results of both simulated and live-shot star images have verified the validity of the proposed method. It adapts to different sky background radiation, which is effective for the application of a star tracker. By comparing with other linear correction methods, it has the advantages of low calculation complexity, better real-time performance, and easier implementation in the hardware.

Colour imaging system response non-uniformity correction based on inverse model and regularization method

The nonlinear response affects the effect of imaging system response non-uniformity correction (NUC) methods. Most of the methods are effective in a certain range of responses. In this paper, a new NUC method is proposed based on the mechanism of imaging system response non-uniformities production. Optical system-related non-uniformity is described as radiation transmission non-uniformity (RTNU) and detector-related non-uniformity is described as radiation conversion non-uniformity (RCNU). The RTNU is removed by inverse operation and RCNU is removed by regularization optimization. We verify the proposed method with respect to visual effect evaluation of actual scene images and three performance metrics evaluation of statistical F ratio, F-norm roughness and chromatic aberration ellipse. The experimental results verify the effect of our method. The proposed method is effective for NUC in a larger range of responses.

A systematic non-uniformity correction method for correlation-based ToF imaging.

Correlation-based time-of-flight (ToF) imaging enables a diverse range of applications for its high frame rate, high resolution and low cost. However, the non-uniformity of the sensor significantly affects the flat-field accuracy of the ToF imaging system. In this paper, we analyze the sources of the non-uniformity and propose a systematic non-uniformity correction (NUC) method. The method utilizes the amplitude image, which can directly reflect the non-uniformity characteristics of the ToF sensor, to conduct NUC. Based on the established NUC system, the effectiveness and feasibility of the proposed NUC method are verified. Compared with the traditional methods, the RMSE was significantly reduced, while the SNR and PSNR were effectively improved. We believe this study provides new insights into the understanding of noise in the correlation-based ToF imaging system, and also provides effective references for the NUC of the three-dimensional measuring instruments.

A comprehensive non-uniformity correction method for EMCCD

The non-uniformity of image directly affects the application of EMCCD in various disciplines. The proposed method can significantly improve the uniformity of EMCCD output image. The correction algorithm of "reverse split and forward recovery" is determined through analyzing the imaging model of EMCCD, and the comprehensive non-uniformity correction function model is established. The 8-tap EMCCD chip CCD220 of British e2v company is used for experimental verification. The results show that after the comprehensive correction the consistencies of the light response characteristic curve and the multiplication gain curve of each channel in EMCCD are obviously improved, and also the photo response non-uniformity (PRNU) of the output image is substantially reduced from 24.5 to 4.1%, which prove the effectiveness of the proposed method.