The detection of chemical plumes is a challenging task in the field of infrared image detection due to the diffusivity of gas plumes. As a general-purpose segmentation architecture, Mask R-CNN can output high-quality instance segmentation masks while efficiently detecting gases. However, Mask R-CNN cannot achieve accurate segmentation of deformable targets. Therefore, in this paper, an infrared image gas plume detection method based on the attention mechanism Mask R-CNN is proposed, which can effectively detect the gas plume in the image and segment the infrared image. First, the preprocessed image is imported into Feature Pyramid Networks (FPN) to obtain the corresponding feature map. Second, the feature map is sent to the regional offer network (RPN) to obtain candidate RoIs. Then, a ROI Align operation is performed on the candidate ROI. Finally, these ROIs are classified, Bounding-box regression, and Mask generation. And we attach the edge attention mechanism to the mask branch of Mask R-CNN to improve the detection accuracy. The experimental results show that the method is validated on the real infrared gas images, and competitive results with the prior art methods.
Infared ship recognition has many applications in port supervision and management. However, when the imaging distance is long or the target changes are obvious, it is difficult to achieve accurate detection and recognition by traditional methods. In this paper, we designed a single step cascade neural network that consists of three parts: feature extraction module, scale transform module and classification regression module. Firstly, the VGG network is used to extract the different level features of the target images. Then the scale transform module is used to fuse the high-level features and the low-level features to reflect the semantic information and shallow information of the targets more completely. The generated region of interest is input to classification regression module that predicts the targets location and classes. The main contribution of this paper is to combine the specific problems of infrared polymorphic ships detection and recognition. The clustering algorithm is used to generate the appropriate anchors to adapt our targets, and the attention mechanism is introduced into the model training process. Compared with the traditional detection and recognition methods, the proposed single step cascade neural network achieves the better average precision in polymorphic ships.
In order to compensate for the low spatial resolution of laser illumination imaging system due to the single photon detector with small number of pixels. In order to solve this problem, we demonstrated a laser illumination imaging system with compressed coded and introduced the application of deep learning in compressed sensing (CS) image reconstruction based on residual network. Specifically, by considering the priori information of sparsity, the better imaging results with much higher resolution could be obtained with a small amount of observation data. The digital micro-mirror device (DMD) is used to achieve sparse coding in this work. We designed to use two detectors to collect information in two reflection directions of DMD, which can reduce samples by 50%. In addition, considering that the time complexity of traditional CS reconstruction methods is too high, so we introduced CS reconstruction method based on residual network into our work, and did the simulation experiments with our data. According to the experimental results, our method performed better at the perspective of image quality evaluation index PSNR and consumption time in reconstruction process.
Due to the problems of long iteration time and poor image quality in the traditional infrared multispectral image reconstruction method based on compressed sensing(CS), an auto-encoders network based on residuals is proposed. Autoencoders are unsupervised neural networks where the output and input layers share the same number of nodes, and which can reconstruct its own inputs through encoder and decoder functions. using code decoding technique learn from real infrared multispectral image spectrum information, through the fast image reconstruction of auto-encoder, get high quality image. The performance of the method is verified by using multiple infrared multispectral images. The results show that the method has the advantages of high image processing efficiency and high spatial resolution. Compared with the traditional compressed sensing method, the auto-encoder network based on residuals has better effect on infrared multispectral image reconstruction.
Hyperspectral image is a three-dimensional data cube which describes spatial information and spectral information of the scene. The anomaly detection technique can detect the targets which have difference between the image and the background without priori information. Kernel independent component analysis(KICA) is a method of mapping hyperspectral data into the kernel space for feature extraction. In this paper, the hyperspectral image is subjected to abnormal information detection based on KICA. First, we calculate the kernel matrix K in order to map the data to high-dimensional space for whitening and dimension reduction processing. Then we utilize the FastICA algorithm to extract the core independent component (KIC). Finally, the extracted independent components with the most abnormal information are analyzed by RX operator, kernel RX operator and abundance quantization method. Comparing with the simulation result and the detected result by RX method, the representation shows the algorithm based on KICA has better detection performance.
This paper narrates infrared image watermarking based on the discrete Shearlet transform(DST). DST has nice multiresolution and multi-directional[1] analysis ability. This feature of DST can be exploited on image watermarking. the proposed method has two purposes. One is hiding watermark information into multi-direction coefficients of the host infrared image to make the watermark is imperceptibility. The other purpose is dealing with various attacks such as noise addition, enlarging, cropping, median filtering and Gaussian filtering to verify the robustness of this method. The experimental results show that the visual effect is satisfactory because the secret information can’t be distinguished by people’s eyes. In fact, through the correlation calculation also shows that the invisible effect is very good.
To reduce the influence of noise in infrared spectral signal measurement, a topological derivative improved partial differential equation method for infrared spectral data denoising is proposed. As an indicator function, topological derivative through a minimization process to find the best position to introduce disturbance, where are spectral edge points, then select the most excellent diffusion coefficient, so the cost of the minimum functional value. Based on the idea of topological optimization, it makes the lowest topological derivative to be optimum one. Then the diffusion is applied by using partial differential equation. Several simulated infrared spectral sequences are utilized to verify the performance of the proposed method. The experiment results show that our method is better in denoising.
Because of the platform motion and system internal asymmetric structure, Satellite-borne infrared imaging system will generate image geometric distortions such as translation, rotation, distortion and scaling, which make the subsequent target detection result not accurate. Therefore, we propose an image distortion method and deeply analyze the influence of infrared image distortion on the SNR of infrared weak small targets, detection probability and false alarm probability. The simulation results show that the image distortion directly affects the subsequent performance of the infrared target detection and tracking algorithm by changing target geometric imaging and signal to noise ratio. The research result in this paper would have great application value in the satellite-borne infrared alarm/warning system.
In traditional scene-based non-uniformity correction methods, ghosting artifacts and image blurring affect the response uniformity of the infrared focal plane array imaging system seriously and decrease the image quality. In order to suppress artifacts ghosting and improve image quality, this paper proposed a new based on kernel regression nonuniformity correction method for infrared image, because of its powerful ability to estimating. The main purpose of proposed method is to obtain reliable estimations of gain and offset parameters. Firstly, in order to suppress the ghost artifacts normally introduced by the strong edge effectively, this paper employs the kernel regression method to estimate the desired pixel value of each detector uint. Then the two correction parameters are achieved with the steepest descent method for the purpose of updating these two parameters synchronously. Finally, more accurate estimations of the two correction parameters can be obtained. Several simulated infrared image sequences are utilized to verify the performance of the proposed method. The results show that our method performs better than other compared methods.
In order to solve the problem of ghost artifacts in the traditional nonuniformity correction(NUC) method, a new scene-based guided bilateral filter(GBF) nonuniformity correction was proposed. In this paper, the original input image sequences are processed by the guided bilateral filter firstly, then the expected output imagine with the boundary information was estimated recursively only by using high spatial-frequency part of the image which contains most of the noise and nonuinformity. The method was verified with several infrared image sequences, and several experimental results show that the proposed method can significantly reduce the ghosting artifacts in temporal high-pass filter(THPF) and achieve a better nonunifotmity correction effect.
Traditional histogram equalization method always leads to the gray level reduction and loss of details. In this paper, an efficient and self-adaptive image enhancement algorithm is proposed based on canny operator and histogram equalization. The canny operator is used to extract the detail information which could be preserved in the enhanced image. The shortcomings of histogram equalization can thus be overcome. The experimental results with infrared images show that our method can preserve more image details and improve the image contrast and suppress noise effectively, which indicates a better performance for infrared image enhancement.
High dynamic range infrared image detail enhancement is an important processing procedure in the field of infrared (IR) imaging. Because of the dynamic range of natural scene image far beyond the human vision system, display equipment, and the high dynamic image transformed directly from high dynamic to low dynamic will cause detail information lost, it is essential to compress dynamic range of image and enhance detail. Aiming at the disadvantages of existing methods, high dynamic infrared image compressive enhancement based on fast local Laplacian filters were proposed. First, the fast local Laplacian filters are utilized to separate the image into a base layer and detail layer. Second, the dynamic range of base layer was compressed by using gamma correction in order to improve contrast. The detail layer is stretched by utilizing sigmoid function. Finally, the enhanced output image is obtained by recombining the detail layer and base layer. Compared with other methods such as histogram equalization, bilateral filtering, the experimental results demonstrated that the proposed method have a better performance in term of enhancing details and improving contrast by using evaluation index of image detail enhancement.
In the processing of infrared small target image which has low signal-to-noise ratio and complex background, the target detection and recognition are very hard. So, how to suppress infrared complex background in low signal-to-clutter addition becomes the key problem in the detection of infrared small target image. The topological derivative can quantify the sensitivity of a problem when the domain under consideration is perturbed by changing its topology. Considering the idea of topology optimization, a modified topological derivative based background suppression method for infrared dim small target detection was proposed. An appropriate functional and variational problem is related to the cost function. Thus, the corresponding topological derivative can be used as an indicator function leads to the processed image through a minimization process. Firstly, introduce perturbations to each pixel of the infrared image. Secondly, calculate the corresponding topological derivative. These pixels also have the least cost function. Finally, using the modified optimal diffusion coefficient to diffuse the pixels where the topological derivative is negative to make its background smooth and achieve the purpose of removing the background clutter while enhancing the small target. Compared with other several experiment results of existing background suppressing methods in indexes, the method the paper proposed has innovative ideas and gets well effects of background suppressing and are practical methods. All of above have the important research value for the related work in future.
In hyperspectral images, anomaly detection without prior information develops rapidly. Most of the existing methods are based on restrictive assumptions of the background distribution. However, the complexity of the environment makes it hard to meet the assumptions, and it is difficult for a pre-set data model to adapt to a variety of environments. To solve the problem, this paper proposes an anomaly detection method on the foundation of machine learning and graph theory. First, the attributes of vertexes in the graph are set by the reconstruct errors. And then, robust background endmember dictionary and abundance matrix are received by structured sparse representation algorithm. Second, the Euler distances between pixels in lower-dimension are regarded as edge weights in the graph, after the analysis of the low dimensional manifold structure among the hyperspectral data, which is in virtue of manifold learning method. Finally, anomaly pixels are picked up by both vertex attributes and edge weights. The proposed method has higher probability of detection and lower probability of false alarm, which is verified by experiments on real images.
Infrared small target detection is an important research topic in the field of infrared image processing and has a major impact on applications in areas such as remote sensing, infrared imaging precise. Due to atmospheric scattering, refraction and the effect of the lens, the infrared detector to receive the target information very weak, it’s difficult to detect the small target in complex background. In this paper, a novel small target detection method in a single infrared image is proposed based on deep convolutional neural network that is mainly using to extract the features of target, through the method can obtain more discriminative features of infrared image. Firstly, the off-line training of convolution kernel parameters using open data sets and simulated data sets, the result of preliminary training gives an initial convolution kernel, this step can reduce the time required for parameter training. Secondly, the input infrared image is preliminarily processed by the trained parameters to obtain the primary features of the infrared image, through the processing of the convolution kernel, a large number of feature information in different scales of the input image are obtained. Finally, selecting and merging the features, design the efficient characteristic information selection strategy, then fine-tune the convolution parameters with the result information, by merging the feature graph can realize the output of the result target image. The experimental results demonstrated that compared with existing classical methods, the proposed method could greatly improve the quality of the results, more importantly, our method can directly achieve the end-to-end mapping between the input images and target detection results.
Pixel-level image fusion, which is widely used in remote sensing, medical imaging, surveillance and etc., directly combines the original information in the source images. As a pixel-level method, multi-focus image fusion is designed to combine the partially focused images into one fully fused single image, which is expected to be more informative for human or machine perception. To achieve this purpose, an algorithm using spatial frequency (SF) measure and discrete wavelet transform (DWT) for multi-focus image fusion is proposed. In this work, the source images are decomposed into low frequency components and high frequency components by using DWT. Then the spatial frequency of the low frequency components is calculated. The spatial frequency is used to judge the focused regions, followed by the morphological filter and median filter. The fused low frequency can be obtained. And the high frequency components are fused using traditional method. Finally, the fused image is obtained by doing inverse discrete wavelet transform. To do the comparison, the proposed algorithm is compared with several existing fusion algorithms in qualitative and quantitative ways. Experimental results demonstrate that our method can be competitive or even outperforms the methods in comparison.
It is very critical that make full use of the local information for infrared dim and small target tracking. In this paper, an effective and fast algorithm based on the context learning is proposed to track infrared dim moving target. Firstly, the principle of the spatio-temporal context learning algorithm is described and the tracking deviation is analyzed. Then, a correlation filter is utilized to get a rational context prior for the dim moving target, the advantage is that the prior considers the image intensity information between a target and its surround pixels. Furthermore, a Gaussian high-pass filter is introduced to extract an accurate spatial context, which has little influence caused by the cluttered background. At last, the tracking problem is posed by computing a confidence map which takes into account sufficient information of a dim target and its surround background. Since the proposed algorithm is realized using fast Fourier transform, it is easy to be real-time. The experiments on various clutter background sequences have validated the tracking capability of the proposed method. The experimental results show that the proposed method can provide a higher accuracy and speed than several classical algorithms, including the improved Template Matching algorithm, the Temporal-Spatial Fusion Filtering algorithm and the Moving Pipeline Filtering algorithm.
The existence of non-uniformity is almost universal in the imaging process of the infrared system. By analyzing the mechanism of the non-uniformity, a temporal non-uniformity correction algorithm is proposed in this paper. First, the non-uniform image is filtered by the bilateral filter. Second, the filtered image is corrected using the moment match method. Finally, the corrected infrared images are acquired by iterating the moment matching image sequence in the time domain. Experiment shows that the proposed algorithm is superior to some existing methods both in experimental data and vision quality.
The target is moving and changing in infrared image sequences captured from the airborne platform infrared imaging system. To adaptively track the infrared target which changes from small target to surface target, an algorithm based on Second-Order Differential (SOD) and improved Template Matching (TM) tracking algorithm was proposed. The SOD filter makes full use of the brightness of the infrared dim and small target, the gradient and distance information of neighborhood pixels used for spatial domain filter. The TM makes full use of infrared brightness, ambient background and dimension information to complete the tracking. The experimental results show that the proposed algorithm can convert adaptively with infrared target’s size changing information, so tracking stability of infrared target under the ground clutter background is achieved. The tracking accuracy and tracking speed are also better than traditional algorithms. The proposed algorithm can be well applied to airborne platform warning on the ground.
The drawback of temporal high-pass non-uniformity correction algorithm, ghosting and the image blurring, severely degrades the correction quality. In this paper, an improved non-uniformity correction algorithm based on shearlet transform is proposed. First, the proposed algorithm decomposes the original infrared image into one low frequency sub-band and a group of high frequency sub-bands by the shearlet transform. As a powerful mathematical tool, the decomposition of image by shearlet can reveal the detail of the image accurately. As the high frequency sub-bands contain the most of FPN, the FPN is estimated from the high frequency sub-bands by temporal high-pass. Then, the goal of non-uniformity correction can be achieved by subtracting the estimated FPN from the original high frequency sub-bands. At last, the corrected infrared image can be obtained by the inverse shearlet transform. The performance of the proposed algorithm is thoroughly studied with real infrared image sequences. Experimental results indicate that the proposed algorithm can reduce the non-uniformity with less ghosting artifacts but also overcome the problems of image blurring in static areas.
An infrared dim and small tracking is proposed based on an explicit image filter - guided filter. The guided filter utilizes the structure in the guidance image and performs as an edge-preserving smoothing operator. The superior performance depending on the guidance image is critical advantage for target tracking. First, the guided filter can help to preserve the detail of the valuable templates and make the inaccurate ones blurry so that the tracker can distinguish the target from numerous bad templates easily. Besides, the filter can recover the content of the small target being influenced according to the guidance image, helping to alleviate the drifting problem effectively. Finally, the candidate samples are utilized to train an effective Bayes classifier to generate a robust tracker, which is easy to be implemented. Experimental results demonstrate that the presented method can track the target effectively, compared with several classical methods. Experimental results show that the proposed algorithm outperforms relative trackers in the accuracy and the robustness.
In this paper, a curvature filter and PDE based non-uniformity correction algorithm is proposed, the key point of this algorithm is the way to estimate FPN. We use anisotropic diffusion to smooth noise and Gaussian curvature filter to extract the details of original image. Then combine these two parts together by guided image filter and subtract the result from original image to get the crude approximation of FPN. After that, a Temporal Low Pass Filter (TLPF) is utilized to filter out random noise and get the accurate FPN. Finally, subtract the FPN from original image to achieve non-uniformity correction. The performance of this algorithm is tested with two infrared image sequences, and the experimental results show that the proposed method achieves a better non-uniformity correction performance.
Compressed sensing is an arisen and significant theory, which has been widely used in infrared image reconstruction and many methods based on compressed sensing have been proposed. However, the existing methods can hardly accurately reconstruct infrared images. Considering that the sparsity of an infrared image plays a crucial role in compressed sensing to accurately reconstruct image, this paper presents a new sparse representation (MBFSF) that integrates the multiscale bilateral filter with shearing filter to overcome the above disadvantage. Firstly, one approximation subband image and a series of detail subband images at different scales and directions are obtained by the MBFSF. Then, in view of the feature that the most information is preserved in the approximation subband image, the proposed method only measures the detail subband images and preserves the approximation subband image. Subsequently, a very sparse random measurement matrix is used for the measurement at the detail subband images to reduce the computation cost and storage of large random measurement matrices in compressed sensing. Finally, an accelerated iterative hard thresholding algorithm is employed to reconstruct the infrared image. Experimental results show that the proposed method has superior performance in terms of reconstruction accuracy and compares favorably with existing compressed sensing methods, which is an effective method in high-resolution infrared imaging based on compressed sensing.
Due to the limitations of the manufacturing technology, the response rates to the same infrared radiation intensity in each infrared detector unit are not identical. As a result, the non-uniformity of infrared focal plane array, also known as fixed pattern noise (FPN), is generated. To solve this problem, correcting the non-uniformity in infrared image is a promising approach, and many non-uniformity correction (NUC) methods have been proposed. However, they have some defects such as slow convergence, ghosting and scene degradation. To overcome these defects, a novel non-uniformity correction method based on locally adaptive regression filter is proposed. First, locally adaptive regression method is used to separate the infrared image into base layer containing main scene information and the detail layer containing detailed scene with FPN. Then, the detail layer sequence is filtered by non-linear temporal filter to obtain the non-uniformity. Finally, the high quality infrared image is obtained by subtracting non-uniformity component from original image. The experimental results show that the proposed method can significantly eliminate the ghosting and the scene degradation. The results of correction are superior to the THPF-NUC and NN-NUC in the aspects of subjective visual and objective evaluation index.
In this paper, a new temporal high-pass filter nonuniformity correction algorithm based on guided filter is proposed, which address the ghosting artifacts and preserve image details of original image. In this algorithm, the original input image is separated into two parts, which are the high spatial-frequency part that contains most of the nonuniformity and the low spatial-frequency part with well preserved details. Then the fixed pattern noise is estimated from the high spatial-frequency part and subtracted from the original image, which achieves the nonuniformity correction. The performance of this presented algorithm is tested with two infrared image sequences, and the experimental results show that the proposed algorithm can significantly reduce the ghosting artifacts and achieve a better nonuniformity correction performance.
A novel dim small target detection algorithm based on the nonsubsampled contourlet transform (NSCT) and the singular value decomposition (SVD) is proposed in this paper, which is to improve the performance of the dim small target detection under the complex sky cloud background. Firstly, the original infrared image is decomposed with the SVD, and several different numbers of the singular value for reconstruction is chosen to analyze the application of the SVD to the image. The complex sky cloud background in the infrared target image is predicted by choosing a certain number of the singular value to reconstruct the image, and it is subtracted from the original image to suppress the background and enhance the target signal. Secondly, to use the scale and the direction information of the image, the residual image is decomposed by the NSCT into several high-pass directional subbands and a low-pass subband. Thirdly, the SVD filtering is utilized again to those directional subbands to eliminate the noise and the residual background. And the low-pass subband is modified by the local mean removal method. Finally, the refined subbands are reconstructed by the inverse NSCT to fulfill the dim small target detection. The experimental results demonstrate that the proposed algorithm has better subjective vision and objective numerical indicators, and can acquire a better performance of the target detection.
In order to solve the problem that infrared images usually have a poor visual effect with low contrast and weak detail information, an adaptive detail enhancement method for infrared image based on bilateral filter is proposed in this paper. Firstly, adopting the bilateral filter which has a good filtering performance, the original infrared image is effectively derived into the smoothed component and the detail component. Exactly, the detail component is the difference between the original infrared image and the smoothed component. The major merit of using the bilateral filter is that the abundant and subtle detail contents containing a lot of edges and textures of the original infrared image could be obtained via adjusting the parameters flexibly. Further, the detail component plays a key role in obtaining an adaptive detail enhancement weight which is generated by the normalization of the detail component. The weight is in the range [0, 1] and their magnitudes can be regarded as the intensity of the original image details. As a result, this detail enhancement weight is adaptive and effective for the original infrared image. Finally, a kind of linear weighting strategy is utilized to achieve the image sharpness combing the original image and the adaptive weight. The experimental results show that the proposed method outperforms other conventional methods in terms of visual effect and quantitative evaluation, which provides a new approach for infrared image detail enhancement.
Due to the limited depth-of-focus of optical lenses in imaging camera, it is impossible to acquire an image with all parts of the scene in focus. To make up for this defect, fusing the images at different focus settings into one image is a potential approach and many fusion methods have been developed. However, the existing methods can hardly deal with the problem of image detail blur. In this paper, a novel multiscale geometrical analysis called the directional spectral graph wavelet transform (DSGWT) is proposed, which integrates the nonsubsampled directional filter bank with the traditional spectral graph wavelet transform. Through combines the feature of efficiently representing the image containing regular or irregular areas of the spectral graph wavelet transform with the ability of capturing the directional information of the directional filter bank, the DSGWT can better represent the structure of images. Given the feature of the DSGWT, it is introduced to multi-focus image fusion to overcome the above disadvantage. On the one hand, using the high frequency subbands of the source images are obtained by the DSGWT, the proposed method efficiently represents the source images. On the other hand, using morphological filter to process the sparse feature matrix obtained by sum-modified-Laplacian focus measure criterion, the proposed method generates the fused subbands by morphological filtering. Comparison experiments have been performed on different image sets, and the experimental results demonstrate that the proposed method does significantly improve the fusion performance compared to the existing fusion methods.
A dim and small target detection method based on surfacelet transform is proposed to improve the performance of dim and small target detection under the complex clouds background. Firstly, the original infrared image is decomposed by the surfacelet transform to extract and analyze the multi-scale and multi-directional characteristics of the image. Then, the total variation and the local mean removal method are utilized to process the high-frequency and the low-frequency sub-bands respectively, which refines the coefficient value of the decomposed sub-bands. Finally, the refined sub-bands are recostructed to make the dim and small target separate from the background clutter signal, and then the background suppression is achieved and the real target is detected effectively. Theoretical analysis and experimental results show that, compared with the wavelet transform method and the total variation method, values of ISCR and BSF of the experimental result by the proposed method is higher, and the result by the proposed method has better effect both in subjective vision and the objective numerical evaluation.
In order to improve the precision of visible and infrared (VIS/IR) image registration, an image registration method based on visual salient (VS) features is presented. First, a VS feature detector based on the modified visual attention model is presented to extract VS points. Because the iterative, within-feature competition method used in visual attention models is time consuming, an alternative fast visual salient (FVS) feature detector is proposed to make VS features more efficient. Then, a descriptor-rearranging (DR) strategy is adopted to describe feature points. This strategy combines information of both IR image and its negative image to overcome the contrast reverse problem between VIS and IR images, making it easier to find the corresponding points on VIS/IR images. Experiments show that both VS and FVS detectors have higher repeatability scores than scale invariant feature transform in the cases of blurring, brightness change, JPEG compression, noise, and viewpoint, except big scale change. The combination of VS detector and DR registration strategy can achieve precise image registration, but it is time-consuming. The combination of FVS detector and DR registration strategy can also reach a good registration of VIS/IR images but in a shorter time.
As the electronic image stabilization (EIS) algorithm based on SIFT feature matching has the problem of complex computation and time consuming, a modified EIS algorithm based on PCA-SIFT feature matching and self-adaptive high-pass filtering is proposed in this paper. Firstly, feature points are extracted by using PCA-SIFT algorithm in reference frame and current frame. And the corresponding points are matched between these two images. Then the Random Sample Consensus (RANSAC) algorithm is used to eliminate the error matching pairs to reduce the influence of local motion in the scene and improve the estimation accuracy of global motion parameters. Finally, the random dithering parameters obtained by self-adaptive high-pass filtering are used to compensate the current frames. And the size of filter is adjusted automatically according to dithering frequency to prevent the overstabilization or understabilization. Experimental results show that the algorithm proposed in this paper can effectively remove vectors caused by random dithering and obtain a stable video.
A core technology in the infrared warning system is the detection tracking of dim and small targets with
complicated background. Consequently, running the detection algorithm on the hardware platform has highly practical
value in the military field. In this paper, a real-time detection tracking system of infrared dim and small target which is
used FPGA (Field Programmable Gate Array) and DSP (Digital Signal Processor) as the core was designed and the
corresponding detection tracking algorithm and the signal flow is elaborated. At the first stage, the FPGA obtain the
infrared image sequence from the sensor, then it suppresses background clutter by mathematical morphology method and
enhances the target intensity by Laplacian of Gaussian operator. At the second stage, the DSP obtain both the original
image and the filtered image form the FPGA via the video port. Then it segments the target from the filtered image by an
adaptive threshold segmentation method and gets rid of false target by pipeline filter. Experimental results show that our
system can achieve higher detection rate and lower false alarm rate.
Influenced by detectors’ material, related manufacturing technology etc, every detection element’s responsivity in infrared focal plane arrays(IRFPA) is different, which results in non-uniformity of IRFPA. So non-uniformity correction(NUC) is an important technique for IRFPA. The classical two-point NUC algorithm based on reference sources is analyzed in this paper. And a new NUC algorithm based on statistical characteristics of image serial is presented. In this algorithm, the reference images are constructed from image serial, and correction parameters are computed by using the constructed reference images. Then two-point NUC is applied to output images of IRFPA. Experimental results show that the algorithm proposed in this paper is effective and implemented easily.
After a decoy is released, it can fly around the target aircraft in a short period of time. And it can radiate infrared spectral radiation similarly to the target do. So it is difficult to recognize the target aircraft. But in infrared images, decoys and targets have different geometrical features. So an infrared decoys recognition method based on the geometrical features is proposed in this paper. The geometrical features of the candidates in each image are extracted, such as the major axis, the minor axis, the aspect ratio, area etc. Then the differences on these geometrical features can be used to recognize targets and decoys. A simulation was done on a set of images that contain decoys and targets by using this method. The results show that the algorithm proposed in this paper can better distinguish infrared decoys and targets.
For the dual band IR imaging system to track targets in the air, due to the uniform sky background, it is difficult to extract salient features besides the tracked targets. But in the dual band IR image sequence, the target in the air has the same trajectory. So the trajectory can be used as feature to register dual-band IR images. If the target trajectory is uniform, the accuracy of double wave band image registration method based on moving targets’ track will be greatly reduced. In addition to detect the target trajectory, it is necessary to detect other feature points in the background, such as the corners. Therefore, in this paper we first detect the target trajectory in the middle-wave infrared image sequence and long-wave infrared image sequence. Then combined the corners in dual band images, dual-band images are registered. Experimental results shows the effectiveness of this method.
For the sake of effectively alleviating the effect of noise in infrared spectral data, a method of infrared spectral data denoising based on stationary wavelet transform is proposed in this paper. Firstly, stationary wavelet transform is adopted to decompose the original infrared spectral data, which extracts data of multi-scale specific characteristic. Secondly, according to difference between spectral signal and noise in different scales, the improved variational method is introduced to adjust each sub-band coefficients. Finally, denoised signal was reconstructed through inverse stationary wavelet transform. Several groups of experimental results are demonstrated that the proposed method not only effectively extract noise but also decreases Mean Squared Error and preserve character of signal. It can be utilized in the actual infrared spectral data denosing and achieved perfect effectiveness.
Hyperspectral image (HI) contains data in hundreds of narrow contiguous spectral bands, thus it provides a powerful means to distinguish different materials on the basis of their unique spectral signatures. Anomaly detection (AD) is one key part of its application. The shearlet transform (ST) is a new two-dimensional extension of the wavelet transform using multiscale and directional filter banks, which can effectively captures smooth contours that are the dominant feature in natural image. In this paper, ST is used in AD for the HI. Firstly, the raw HI data is decomposed into several directional subband at multiple-scale via ST. Thus, the background signal would be reduced in each subband. Secondly, the fourth partial differential equation method is adopted to modify the coefficient of each sub-band, which is for background suppression and anomaly signal enhancement. Thirdly, the kernel-based RX algorithm is adopted to detect the anomaly in each sub-band. Finally, the anomaly signal image is achieved by reconstructing the image with all modified sub-band. Several experiments with a HYDICE data are fulfilled to validate the performance of the proposed method. Compared with the original RX algorithm, experimental results show that the proposed algorithm has better detection performance and lower false alarm probability.
Complex background suppression is a key problem in the detection of the infrared dim small target at far distance. In this paper, a background suppression method for the dim small target detection based on the combination of the high-order diffusion equation and the RX operator is proposed. Firstly, the high-order diffusion equation is applied to decompose the original infrared image, and the multiscale features of the image are extracted. Then, by the fact that the signal coefficients of target are different with that of background clutter in the decomposed sub-image, the RX operator is utilized to separate the dim small target and the background clutter. Two groups of experimental results demonstrate that the complex background can be suppressed by the presented method effectively, whose performance is better than that of the max median (MMed) method. The proposed method can preserve and enhance the infrared target signal effectively whose SCR is greater than 1.7.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.