Point Target Detection Research Articles

New Approach in Processing of the Infrared Image Sequence for Moving Dim Point Targets Detection

The development of an efficient moving target detection algorithm in IR-image sequence is considered one of the most critical research fields in modern IRST (Infrared Search and Track) systems, especially when dealing with moving dim point targets. In this paper we propose a new approach in processing of the Infrared image sequence for moving dim point targets detection built on the transformation of the IR-image sequence into 4-vectors for each frame in the sequence. The results of testing the proposed approach on a set of frames having a simple single pixel target performing a different motion patterns show the validity of the approach for detecting the motion, with simplicity in calculation and low time consumption.

Background first- and second-order modeling for point target detection

This paper deals with point target detection in nonstationary backgrounds such as cloud scenes in aerial or satellite imaging. We propose an original spatial detection method based on first- and second-order modeling (i.e., mean and covariance) of local background statistics. We first show that state-of-the-art nonlocal denoising methods can be adapted with minimal effort to yield edge-preserving background mean estimates. These mean estimates lead to very efficient background suppression (BS) detection. However, we propose that BS be followed by a matched filter based on an estimate of the local spatial covariance matrix. The identification of these matrices derives from a robust classification of pixels in classes with homogeneous second-order statistics based on a Gaussian mixture model. The efficiency of the proposed approaches is demonstrated by evaluation on two cloudy sky background databases.

Super resolution reconstruction for infrared dim point target

A super resolution reconstruction method for dim point target detection in infrared image was presented.To achieve this,local descriptor based dense flow calculation is introduced first.Then,the high accuracy flow is used to registrate and fuse two adjacent images to generate the final high resolution image.Experiments show that,after the process,the resolution of small targets can be increased,local signal-to-noise ratio be increased and complex background be surprised.

Infrared point target detection with improved template matching

Detecting point targets in infrared images is a difficult task. Template matching is simple and easy to implement for completing this task. However, it has some shortcomings. We propose an improved template matching method for detecting targets. Different from the classic template matching, the projection coefficients obtained from principal component analysis are used as templates and the nonlinear correlation is proposed to measure the similarity, the matching degree. The correlation in original space can not capture the higher-order statistical property of images. So its detection performance is not satisfying. We introduce the nonlinear correlation, which computes the correlation coefficients in a higher-dimensional feature space or even in an infinite-dimensional feature space, to capture the higher-order statistics. The detection performance is improved greatly. Results of experiments show that the improved method is competent to detect infrared point targets.

LRT-DetSim: Long-Range Airborne Target Detection Simulator for Infra-Red Image Sequences

Early detection of airborne threats is becoming more and more important for advancing attack distance and response speed of modern hi-tech weapons. The targets at longer ranges appear on sensor image plane as point and small targets with low contrast. Therefore, the study and implementation of low contrast point and small target detection algorithms for infra-red image sequences are important for modern hi-tech weapons. Typically, a spatial pre-processing step is performed on the input image to predict the background and consequently enhance the signal-to-clutter-ratio followed by actual detection algorithm. The proposed Long-Range Target Detection Simulator (LRT-DetSim) is a graphical user interface (GUI) based simulator for detection of point and small targets in infra-red image sequences. In the LRT-DetSim, we have implemented five pre-processing algorithms, namely max-median filter, two morphological filters, contour structuring element based (CB) tophat transform and a CB modified top-hat transform, as well as two detection algorithms, the Modified Motion-Analysis (MMA) algorithm and the Adaptive Morphological Clutter Elimination (AMCE) algorithm. From the simulation, we have found that the CB top-hat transform based pre-processing algorithms outperform the other pre-processing algorithms in terms of Mean Absolute value of Residual Background (MARB) as well as Signal to Clutter Ratio (SCR). The MMA algorithm demonstrated higher probability of detection but generates many false alarms for highly clouded background. In contrast to this, the AMCE algorithm is more suitable for highly clouded clutter scenario.

Optimal criterion to select the background estimation algorithm for detection of dim point targets in infrared surveillance systems

A well-established scheme for target detection in infrared (IR) surveillance systems consists of applying a suitable decision rule on the images with background clutter previously removed. Background removal is accomplished by subtracting, from the original image, the estimate of the spatially varying background signal obtained by a background estimation algorithm (BEA). The overall target detection performance is strongly influenced by the effectiveness of the employed BEA. Particularly, the BEA and its design parameters should be chosen so as to get an accurate estimate of the background signal and to avoid biases caused by the possible presence of targets (target leakage). In this work, we present a novel method for the choice and setting of the best performing background removal technique for the detection of dim point targets. The proposed procedure is based on the simulation of dim targets implanted on an acquired sample image representing the scenario of interest. The choice of the best performing BEA is made by exploring the performance of the detection scheme for several configurations of the characteristic parameters of the BEAs. The effectiveness of the BEA selection procedure is evaluated in two case studies where real image sequences acquired by IR cameras are employed. The results confirm the benefits introduced by the proposed technique. Indeed, the performance of the IR detection system with the BEA tuned according to the proposed selection criterion is improved in that the number of false alarms is reduced up to 2 orders of magnitude compared with BEAs in other common configurations.

Spatial and temporal point tracking in real hyperspectral images

Abstract In this article, we consider the problem of tracking a point target moving against a background of sky and clouds. The proposed solution consists of three stages: the first stage transforms the hyperspectral cubes into a two-dimensional (2D) temporal sequence using known point target detection acquisition methods; the second stage involves the temporal separation of the 2D sequence into sub-sequences and the usage of a variance filter (VF) to detect the presence of targets using the temporal profile of each pixel in its group, while suppressing clutter-specific influences. This stage creates a new sequence containing a target with a seemingly faster velocity; the third stage applies the Dynamic Programming Algorithm (DPA) that tracks moving targets with low SNR at around pixel velocity. The system is tested on both synthetic and real data.

A Preprocessing Algorithm of Point Target Detection Based on Temporal-Spatial Bilateral Filter Using Adaptive Neighborhoods

摘要: 该文通过分析点目标的成像原理，提出一种基于自适应邻域时空双边滤波的点目标检测预处理算法。算法针对每个像素建立自适应邻域，对不同类的邻域分别定义其定义域和值域势函数的乘积为滤波模板，并通过限制自适应邻域的大小加快了算法速度。与固定邻域的空域双边滤波算法和时空双边滤波算法相比，该文算法能够快速、有效去除噪声，同时增强点目标和背景的对比度。 关键词: 点目标检测; 预处理; 时空双边滤波; 自适应邻域; 势函数

Homogeneous background prediction algorithm for detection of point target

An algorithm for detection of point target using novel background prediction technique in infrared image that contains drifting and evolving clutter is presented in this paper. It is shown that the better detection performance can be achieved when the background prediction could be done more accurately. From this point of view, the model of the homogeneous background prediction algorithm (HBPA) is developed. This approach makes edge detection first, and then the background is segmented into different areas with different gray distribution features. The probable target pixels in static background are determined by the deviation of the pixels’ intensity from the gray distribution features of the background. Only the selected pixels in the static background and the pixels on the cloud edge are predicted and all of the participation pixels are homogeneous under the weight matrix. The intensity of the unselected pixels in predicted image remains the same as those in original image. Finally, the threshold value is used to make detection in the error image which is the difference between the original image and the predicted image. Experimental results indicated that the method can efficiently suppress the background clutter, protect image details, reduce the adverse influence of heterogeneity backgrounds, and improve the detection performance at low SCR.

Hough transform relative to a four-dimensional parameter space for the detection of constant velocity target

We present a novel Hough transform method for moving point target detection by using a 4-D parameter space. A new representation, which uses four parameters (the distance variable , the angle variable , the velocity variable v, and the distance variable S), is proposed for constant velocity target in the 3-D observation space X-Y-T. By estimating velocity, a target trajectory can be transformed into a 4-D parameter space with a limited range of projection options. Our simulation and analysis show that the new algorithm can produce positive results in suppressing noise points with less computational cost.

Clutter suppression algorithm based on bidirectional local binary pattern for moving point target detection in infrared image sequences

A clutter suppression algorithm called the rectification filter with indications of bidirectional local binary patterns (BDLBP-RF) is proposed as a resolution to the problem of detecting dim targets in infrared (IR) image sequences. First of all, a local binary pattern (LBP) operator with properties of grayscale and rotation invariance is introduced in the application of clutter suppression. Each pixel in the image is estimated by its spatial neighbor pixels and the corresponding LBPs in prior and posterior frames. The approach proposed is based on a spatiotemporal process, in which interframe and intraframe properties of the IR image sequence are both taken into account. The method is evaluated by the comparative experiments, and the LBP operator's optimum values of radius and number of neighbors are discussed. The results of the experiment prove that BDLBP-RF has excellent performance and stability in clutter suppression under various situations. The target point in images processed by our approach received high signal-to-clutter ratio gain, and the detectability of the target is enhanced.

Infrared Point Target Detection with Fisher Linear Discriminant and Kernel Fisher Linear Discriminant

It is a challenging task to detect point targets from an infrared image. Recently, the pattern recognition theory has been used to detect targets. The principal component analysis (PCA) has gained success in this field. We propose a linear subspace detection method based on Fisher linear discriminant (FLD) in this paper. If we consider images are made up of target class data and background class data, the target detection problem can be translated into a two-class classification problem. The FLD as one of pattern recognition algorithms can be used to find potential targets from image background. After classification by FLD, a map function, Gaussian map function, is developed to generate detection images in which the larger target-to-background contrast is obtained. FLD is a linear detection method without taking the higher-order statistics of image data into account. To improve detection performance, we extend this detection method to its nonlinear version, kernel FLD (KFLD) detection. Because the nonlinear subspace is capable of capturing the part of higher-order statistics, the better detection performance can be achieved. The well-devised experiments verify that KFLD detection outperforms FLD and other common used detection methods.

Compression of infrared imagery sequences containing a slow-moving point target

Infrared imagery sequences are used for detecting moving targets in the presence of evolving cloud clutter or background noise. This research concentrates on slow-moving point targets that are less than one pixel in size, such as aircraft at long ranges from a sensor. The infrared (IR) imagery sequences that are captured by ground sensors contain an enormous amount of data. Since transmitting this data to a base unit or storing it consumes considerable time and resources, a compression method that maintains the point target detection capabilities is desired. For this purpose, we developed two temporal compression methods that preserve the temporal profile properties of the point target. We evaluated the proposed compression methods using a signal-to-noise-ratio (SNR)-based measure for point target detection and showed that the compression may improve the SNR results compared to the IR sequence prior to compression.

Sampling-balanced imaging system utilizing whitening matched filter

Imaging systems designed for point target detection and 3D reconstruction must be filtered in order to maximize signal-to-noise ratio and minimize position expectation error. An optimal whitening matched filter (WMF) is derived based on expected spatial target distribution and system colored noise. The expected noise is derived as a weighted combination of clutter aliasing, target aliasing, and detector noise. Further optimization of system performance is achieved by modification of the optical point spread function (PSF), so a sampling-balanced operation is achieved where all noise components are comparable. The improved performance of the optimized system is calculated and compared to the performance of other systems using other known linear postfilters with various optical PSF widths. It is shown that the WMF in a sampling-balanced system is a robust configuration that needs only minor modifications when scenario parameters are varied.

Mixed segmentation-detection-based technique for point target detection in nonhomogeneous sky

This paper deals with point target detection in infrared images of the sky for which there are local variations of the gray level mean value. We show that considering a simple image model with the gray level mean value varying as a linear or a quadratic function of the pixel coordinates can improve mixed segmentation-detection performance in comparison to homogeneous model-based approaches.

Noncausal Adaptive Spatial Clutter Mitigation in Monostatic MIMO Radar: Fundamental Limitations

The problem of a point target detection masked by clutter distributed over range and Doppler, including the range and Doppler of the target, is considered for a multimode propagation scenario commonly encountered in quasimonostatic HF over-the-horizon radars (OTHR). Here, a clutter signal spread in Doppler frequency due to propagation via a disturbed ionospheric layer competes with a target and narrowband clutter returns propagating via a stable ionospheric layer with the same group delay (radar range). Mitigation over all ranges of spread clutter propagating via a ¿mixed mode¿ path with indistinguishable direction-of-arrival (DoA) relative to the target requires (potentially adaptive) transmit beamforming to exploit the direction-of-departure (DoD) difference, which varies as a function of radar range. This range-dependent beamforming can be implemented only via the use of multiple-input multiple-output radar technology. In this paper, we explore the fundamental limitations that exist for the maximal dimension of the area in range-Doppler space occupied by spread clutter and the required properties (cardinality) of the orthogonal waveform set for efficient spread clutter mitigation.

低对比度小目标检测

低对比度小目标检测

基于时空联合滤波技术的缓慢运动红外弱小目标检测算法

基于时空联合滤波技术的缓慢运动红外弱小目标检测算法

Analysis of point-target detection performance based on ATF and TSF

In many real applications such as remote sensing and space surveillance, traditional method based on ideal imaging has already been well-established. It is widely applied to analyze point-target detection performance of electro-optical imaging system, including signal-to-noise ratio (SNR) and noise equivalent temperature difference (NETD). However, this method cannot accurately predict these performance parameters, as it fails to take into account the influence of optical blurring caused by atmospheric turbulence, optics diffraction, optical aberrations, etc. In this sense, the methods, if proposed to thoroughly incorporate degrading factors into object acquisition model, would succeed to describe point-target detection performance to more degree of accuracy. The main focus of this article is to quantitatively analyze the influence of optical blurs upon point-target detection, and to establish close relationship between optical blurring and metrics of point-target acquisition. This point can be interpreted and achieved mathematically: the mathematical analysis based on image acquisition model is to combine Aperiodic Transfer Function (ATF) and Target Size Function (TSF) with analysis of SNR and NETD. In addition, the concept of NETD, traditionally used to describe extended object detection, is generalized and equivalently applied to analyze point-target detection. This refined method can be directly and conveniently used for faithfully predicting detection performance, and provides a more reliable benchmark for improving measurement setup, if we properly estimate the degree of image distortion.

Enhanced detectability of point target using adaptive morphological clutter elimination by importing the properties of the target region

An efficient clutter elimination algorithm will largely enhance the detectability of dim point targets embedded in heavy clutter image. In this paper, a novel point target detectability enhancement algorithm named adaptive morphological clutter elimination which is constructed by importing the properties of the target region is proposed. The consideration of the properties of the target region not only enhances the adaptive ability of the algorithm, but also improves the performances of the algorithm. Experiments indicate that our proposed algorithm on clutter elimination, false alarm reduction and target enhancement are more powerful than some other widely used methods for the purpose of point target detection; thus the detectability of the point target image is greatly enhanced.