Infrared Image Enhancement Research Articles

Color Transfer Algorithm between Images Based on a Two-Stage Convolutional Neural Network.

A color transfer algorithm between images based on two-stage convolutional neural network (CNN) is proposed. The first stage network is based on VGG19 architecture as the backbone. The reference image-based color transfer (RICT) model was used to extract the features of the reference image and the target image, so as to realize the color transfer between them. The second stage is based on progressive convolutional neural network (PCNN) as its backbone. The palette-based emotional color enhancement (PECE) model is adopted to enhance the emotional coloring of the resulting image by comparing the palette, emotional value and the proportion of each color of the reference image. Through five sets of experiments, it is proved that the visual effect processed by our model is obviously better than several main colorization methods in both subjective evaluation and objective data. It can be applied to various complex scenes, and in the near future, it can also be better applied to the fields of digital restoration of old image archives, medical image coloring, art restoration, remote sensing image enhancement, infrared image enhancement and other fields.

Progressive Fusion Network Based on Infrared Light Field Equipment for Infrared Image Enhancement

Dear Editor, Infrared imaging, generally, of low quality, plays an important role in security surveillance and target detection. In this letter, we improve the quality of infrared images by combining both hardware and software. To this end, an infrared light field imaging enhancement system is built for the first time, including a 3× 3 infrared light field imaging device, a large-scale infrared light field dataset (IRLF-WHU), and a progressive fusion network for infrared image enhancement (IR-PFNet). The proposed algorithm leverages rich angular views among the infrared light field image to explore and fuse auxiliary information for infrared image enhancement. Given an infrared light field image, multiple views are first divided into four groups according to the angle and each group contains parallax shifts along the same direction. As strong spatial-angular correlations are existing in each group, we customize a progressive pyramid deformable fusion (PPDF) module for intra-group fusion without explicit alignment. In the PPDF module, the deformation and parallax are modeled in a progressive pyramid way. To integrate the supplementary information from all directions, we further propose a recurrent attention fusion (RAF) module, which constructs attention fusion block to learn the residual recurrently and provides several intermediate results for multi-supervision. Experiments on our proposed IRLF-WHU dataset demonstrate that IR-PFNet can achieve state-of-the-art performance on different degradations, yielding satisfying results. The dataset is available at: https://github.com/wxywhu/IRLF-WHU, and the code is available at: https://github.com/wxywhu/IR-PFNet.

Image Enhancement of Maritime Infrared Targets Based on Scene Discrimination.

Infrared image enhancement technology can effectively improve the image quality and enhance the saliency of the target and is a critical component in the marine target search and tracking system. However, the imaging quality of maritime infrared images is easily affected by weather and sea conditions and has low contrast defects and weak target contour information. At the same time, the target is disturbed by different intensities of sea clutter, so the characteristics of the target are also different, which cannot be processed by a single algorithm. Aiming at these problems, the relationship between the directional texture features of the target and the roughness of the sea surface is deeply analyzed. According to the texture roughness of the waves, the image scene is adaptively divided into calm sea surface and rough sea surface. At the same time, through the Gabor filter at a specific frequency and the gradient-based target feature extraction operator proposed in this paper, the clutter suppression and feature fusion strategies are set, and the target feature image of multi-scale fusion in two types of scenes are obtained, which is used as a guide image for guided filtering. The original image is decomposed into a target and a background layer to extract the target features and avoid image distortion. The blurred background around the target contour is extracted by Gaussian filtering based on the potential target region, and the edge blur caused by the heat conduction of the target is eliminated. Finally, an enhanced image is obtained by fusing the target and background layers with appropriate weights. The experimental results show that, compared with the current image enhancement method, the method proposed in this paper can improve the clarity and contrast of images, enhance the detectability of targets in distress, remove sea surface clutter while retaining the natural environment features in the background, and provide more information for target detection and continuous tracking in maritime search and rescue.

Research on Vehicle Detection and Recognition Based on Infrared Image and Feature Extraction

Vehicle detection and identification and safe distance keeping technology have become the main content of current intelligent transportation system research. Among them, vehicle detection and recognition is one of the most important research contents, and it is also crucial to the safe driving of vehicles. Real-time detection and recognition of current vehicles can effectively prevent the occurrence of malignant traffic accidents such as rear-end collision. Because the infrared image has some shortcomings such as poor contrast, loud noise, and blurred edge, this paper mainly studies the color space preprocessing of the image and uses threshold segmentation method and infrared image enhancement to segment the front vehicle and background. That is to say, by analyzing the infrared image captured by infrared CCD, we use median filter to remove noise from the collected infrared image and then use the improved histogram equalization to enhance the contrast of the image. Vertical Sobel operator is selected to enhance the vertical edge of the image, and the image is segmented by binary segmentation method. Finally, vehicle detection and recognition are realized by vertical edge symmetry, aspect ratio, and gray-scale symmetry. The experimental image and experimental data analysis results show that the image processing technology studied in this paper has achieved the intended research purpose.

(Retracted) Infrared image filtering and enhancement processing method based upon image processing technology

Due to the processing method used in many existing image enhancement algorithms, some inherent noise in the image is amplified when the image is enhanced globally or locally. The quality of infrared images directly affects the wide application of infrared imaging technology, yet the quality of infrared image depends largely on the advanced nature and correct application of infrared image processing technology (IPT). This research mainly discusses the infrared image filtering enhancement processing method based on IPT. We briefly summarize the research significance, application fields and research status of the image registration and enhancement. We summarize the commonly used methods. We use a contrast saliency filter to obtain the region of interest and perform statistical segmentation on the region to make it more suitable for observation and subsequent processing. No matter what the background environment is, the image detail enhancement algorithm enhances all the details in the image in a balanced manner. Therefore, we adopt the scheme of separating the background and the details to avoid the influence of the background difference on the detail display effect in other enhancement methods. Objective experiments have also proved that it is difficult to achieve consistency between subjective and objective evaluation of image quality. Therefore, the evaluation of processed image quality still needs to combine subjective visual effects and objective evaluation. We use optimized hierarchical differential expression theory to solve the acquired saliency region and obtain the differential vector that realizes the gray difference amplification of this region. The dynamic range of the original image is very narrow, roughly concentrated in [0, 50]. The gray range of the image processed by the enhancement algorithm has been well expanded, basically covering [0, 255]. The proposed infrared image enhancement method achieves a better visual enhancement effect.

An adaptive bilateral filtering method based on improved convolution kernel used for infrared image enhancement

An adaptive bilateral filtering method based on improved convolution kernel used for infrared image enhancement

Research and analysis of infrared image enhancement algorithm based on fractional differentiation

Due to the inherent defects of infrared imaging systems and the influence of the external complex environment, infrared images have low contrast, blurred edge details, low signal-to-noise ratio and poor visual effects compared with visible images, which have a great impact on the subsequent feature extraction, detection and identification and target tracking, and cannot meet the requirements in military, medical and civilian fields. The current technical deficiencies of infrared imaging devices at the hardware level cannot fundamentally solve these problems, so it is especially necessary to enhance infrared images from the perspective of algorithms. We propose an improved fractional differentiation algorithm that enhances the contrast of infrared images and the contrast of the images is controlled by the fractional order. Experiments and analysis show that the proposed method has good feedback for enhancing the contrast of dark images, and it can effectively enhance the edge information and detail information.

Parallel multifeature extracting network for infrared image enhancement

Parallel multifeature extracting network for infrared image enhancement

基于RetinexNet红外图像增强算法的优化

基于RetinexNet红外图像增强算法的优化

Infrared image enhancement algorithm using local entropy mapping histogram adaptive segmentation

The traditional histogram equalization algorithm may cause problems such as local over-enhancement and noise amplification while enhancing the image. To solve these problems, this paper proposes an infrared image enhancement method using local entropy mapping histogram adaptive segmentation. Firstly, a local entropy mapping histogram is built through the modified ‘sigmoid’ function to describe the detailed distribution of the infrared image. Then the LOESS algorithm and local minimum examination are used to adaptively segment the local entropy mapping histogram into multiple sub-histograms. And follow, the double plateau constraint of shape preservation is adopted, and the double plateau thresholds of each interval of the local entropy mapping histogram are adaptively optimized according to the genetic algorithm. Finally, multiple sub-histograms are equalized to obtain an enhanced image. Comparative experiments on real infrared images show that our method is ahead of other superior methods in qualitative and quantitative evaluation.

Infrared imaging enhancement through local window‐based saliency extraction with spatial weight

Infrared image enhancement is an effective way to solve contrast reduction or details degradation in infrared imagery. An infrared enhancement approach based on local saliency extraction is proposed here. First, saliency maps are extracted within a local window by combining spatial weight. Second, with the change of the window size, potential targets and details in different sizes can be extracted. Considering window sizes as the scales, the saliency maps are obtained and infrared images are enhanced at different scales, and finally, multi-scale fusion is used to achieve the enhancement. Eight popular infrared enhancement approaches are introduced for comparison. Subjective qualitative observation experiments show that our strategy based on local saliency analysis and multi-scale fusion can well extract potential targets and areas of varying size from the source images with different sizes, to obtain a good enhancement effect. Meanwhile, we introduce six objective evaluation methods to measure the results, and the evaluation data to prove the effectiveness of the proposed algorithm. The experiments also indicate the real-time processing capability of the proposed method. The proposed method is finally well applied in the hardware system and shows its good performance.

Target attention deep neural network for infrared image enhancement

The inherent high background radiation and low contrast of infrared images severely cripple the precision of target detection and recognition. However, existing infrared image enhancement methods still struggle to balance the target enhancement and background suppression. To further address this issue, we present an innovative target attention deep neural network (TADNN) to realize a discriminative enhancement in an end-to-end manner. In this framework, a joint convolution unit (JCU) is constructed to comprehensively excavate the complementary multi-scale spatial features, followed that, a target attention unit (TAU) is designed to further refine the features from JCU for particularly enhancing the targets. Besides, an improved S-curve response model is put forward to generate the task-oriented training set for pursuing a superior fitting solution. Extensive experiments validate that the proposed method outperforms the competitive approaches on both of subjective visual effect and quantitative assessments.

Spatial fusion enhancement of thermal infrared images based on multi-resolution analysis and low-rank guided filter

Spatial fusion enhancement of thermal infrared images based on multi-resolution analysis and low-rank guided filter

Improved multi-scale Retinex infrared image enhancement

Improved multi-scale Retinex infrared image enhancement

A Method of Infrared Image Pedestrian Detection with Improved YOLOv3 Algorithm

The principle of infrared image is thermal imaging technology. Infrared pedestrian detection technology can be applied to the safety monitoring of the elderly, which can not only protect personal privacy, but also realize pedestrian identification at night, which has strong application value and social significance. A method of infrared image pedestrian detection with improved YOLOv3 algorithm is proposed to increase the detection accuracy and solve the problem of low detection accuracy caused by infrared pedestrian target edge blurring. And according to the characteristics of infrared pedestrian, a complex sample data set is established which is applied to infrared pedestrian detection. The infrared image enhancement method with WDSR-B is adopted to improve the clarity of the data set. In addition, based on YOLOv3 algorithm, the output of the 4-time down-sampling layer is added to obtain richer context information for small targets and improve the detection performance of the network for small-target pedestrians. And the improved YOLOv3 network is trained by the enhanced infrared data set. Experimental results show that the scheme precision of pedestrian detection is higher than that of YOLOv3 algorithm. Therefore, this method can be applied to the detection of pedestrians at night and the safety monitoring of the elderly.

Research on Infrared Temperature Measurement Image Enhancement Technology of Transmission Line

It is one of the important means to ensure the safety of transmission line and its equipment to realize the rapid identification and accurate diagnosis of visual defect fault points of transmission line. In this paper, an adaptive infrared image enhancement algorithm is proposed based on the research of infrared image features and various image enhancement algorithms. The algorithm first filters the infrared image to remove the random noise and improve the signal-to-noise ratio of the image; then, based on the histogram analysis of the infrared image, adaptively selects the upper and lower thresholds of the gray histogram, and uses the histogram segmentation to divide the infrared image into three parts: target, target and background aliasing, and background. Finally, through the gray analysis of the three distributions, the algorithm can extract the gray image. Finally, infrared image background suppression and target enhancement are realized. By comparing the effect before and after image enhancement, it is proved that the algorithm has strong practicability.

Adaptive clip-limit-based bi-histogram equalization algorithm for infrared image enhancement.

Infrared (IR) images are basically low-contrast in nature; hence, it is essential to enhance the contrast of IR images to facilitate real-life applications. This work proposes a novel adaptive clip-limit-oriented bi-histogram equalization (bi-HE) method for enhancing IR images. HE methods are simple in implementation but often cause over-enhancement due to the presence of long spikes. To reduce long spikes, this work suggests to apply a log-power operation on the histogram, where the log operation reduces the long spikes, and power transformation regains the shape of the histogram. First, a histogram separation point is generated applying the mean of the multi-peaks of the input histogram. After that, an alteration in the input histogram is done using the log-power process. Subsequently, a clipping operation on the altered histogram followed by redistribution of the clipped portion is performed to restrict over-enhancement. Next, the modified histogram is sub-divided using the histogram separation point. Finally, the modified sub-histograms are equalized independently. Simulation results show that the suggested method effectively improves the contrast of IR images. Visual quality evaluations and quantitative assessment demonstrate that the suggested method outperforms the state-of-the-art algorithms.

Infrared Image Adaptive Enhancement Guided by Energy of Gradient Transformation and Multiscale Image Fusion

The detail enhancement and dynamic range compression of infrared (IR) images is an important issue and a necessary practical application in the domain of IR image processing. This paper provides a novel approach to displaying high dynamic range infrared images on common display equipment with appropriate contrast and clear detail information. The steps are chiefly as follows. First, in order to protect the weak global details in different regions of the image, we adjust the original normalized image into multiple brightness levels by adaptive Gamma transformation. Second, each brightness image is decomposed into a base layer and several detail layers by the multiscale guided filter. Details in each image are enhanced separately. Third, to obtain the image with global details of the input image, enhanced images in each brightness are fused together. Last, we filter out the outliers and adjust the dynamic range before outputting the image. Compared with other conventional or cutting-edge methods, the experimental results demonstrate that the proposed approach is effective and robust in dynamic range compression and detail information enhancement of IR image.

Novel infrared image enhancement optimization algorithm combined with DFOCS

In the paper, the issue about infrared image enhancement is addressed. First a discrete-type fractional order chaotic system (DFOCS) is constructed. Then a kind of chaotic mapping based on the new system is utilized to design an optimization algorithm for the achievement of infrared image enhancement. In the final, some typical experiments are conducted to display the advantage and effectiveness of the given optimization algorithm, which is much suitable for the potential application in fault detection.

Infrared Image Enhancement by Multi-Modal Sensor Fusion in Enhanced Synthetic Vision System

ESVS (Enhanced Synthetic Vision System) employs multi-modal sensor fusion to provide equivalent out-of-cabin view for pilots. By using such device, pilots can identify the runway and obstacles even in low visibility weather condition during approach and landing. Previously, short-wave infrared video was used as real-time image sensor in our developed ESVS. While, compared to visible image, infrared image is not easy to understand. Moreover, the image quality of infrared degrades to a considerable extent in haze weather condition. To improve the infrared image visibility in ESVS, we proposed a multi-modal sensor fusion strategy by combining real-time infrared video and previous recorded visible video in the clear weather condition. During image fusion, considerable color detail of the visible image is injected to infrared image to ameliorate the infrared image quality. Furthermore, the proposed fusion method has two extra advantages. First, the important tagged information including runway and obstacles in visible image are transferred to infrared video, and second, the missing information in infrared vision can be complemented. To evaluate our proposed method, we use the Y-12F aircraft equipped with both visible and infrared video camera for flight test data collection. By collecting visible and infrared video in clear and haze weather conditions, as well as necessary navigation data, we carry out the final image fusion processing. Experimental results show that the fused video frame has enhanced image quality and improved readability for the pilots, which will significantly promote the pilots’ situation awareness during approach and landing. Thus, the proposed idea for fusion of multi-sensor image has the great potential to be applied to other cockpit display systems.