Classical Constant False Alarm Rate Research Articles

Target Detection in Single-Photon Lidar Using CNN Based on Point Cloud Method

To enhance the detection capability of weak targets and reduce the dependence of single-photon lidar target detection on the number of the time-correlated single-photon counting detection cycles, a convolutional neural network (CNN) based on the point cloud (CNN-PC) method is proposed in this paper for detecting targets in single-photon lidar. This approach utilizes the exceptional feature extraction capabilities offered by CNN. The CNN-PC method utilizes the feature extraction module of the trained CNN to simultaneously extract features from two-dimensional point cloud slices. Subsequently, it combines these features and feeds them into the classification module of the trained CNN for final target detection. By training the CNN using point cloud slices generated with a minimal number of detection cycles and employing a parallel structure to extract features from multiple point cloud slices, the CNN-PC method exhibits remarkable flexibility in adapting to varying numbers of detection cycles. Both simulation and experimental results demonstrate that the CNN-PC method outperforms the classical constant false alarm rate method in terms of the target detection probability at the same signal-to-noise ratio and in terms of the imaging rate and error rate at the same number of detection cycles.

Ship Detection in SAR Images via Kullback-Leibler Divergence-Based Matrix Information Geometry Detector

Ship detection in synthetic aperture radar (SAR) imagery is an important application in the field of marine remote sensing. As the most common method in ship detection, classical constant false alarm rate (CFAR) methods rely on the target-to-clutter contrast and accurate estimates of distribution models, making it difficult to adapt to complex and variable sea surface backgrounds. Considering the limitations of the CFAR methods, this paper proposes a new detector for ship detection based on matrix information geometry (MIG) theory. The proposed detector models each SAR sample data as a Hermitian positive-definite (HPD) matrix, and uses the geometric mean of all HPD matrices corresponding to the background window to estimate the clutter, thus transforming the target detection problem into a measure of the Kullback-Leibler divergence (KLD) between two points on the matrix manifold. Different from the traditional CFAR detectors which use intensity information to differentiate between targets and clutter, the proposed detector utilizes the intrinsic geometry of the matrix manifold and employs KLD with good differentiation to measure the variance from targets to clutter.

Variable False Alarm Rate Detection Framework for Phased Array Radar

This paper considers a low signal-to-noise ratio (SNR) target detection problem for phased array radar, where classical constant false alarm rate (CFAR) detection framework would cause missed detection. To overcome this problem, we propose a variable false alarm rate (VFAR) detection framework for phased array radar to ensure the detection performance for low-SNR targets in multi-stage target detection. First, exploiting the previous detected results, the searching area of interest is divided into multiple sub-areas, while automatically reducing the false alarm probability of each range section of each frame. Then, a joint allocation strategy of beam and time resources accounting for maximizing the weighted sum of SNRs of spatial sectors in the whole surveillance area of the phased array radar along with some practical coupled constraints, is proposed. Next, the fuzzy analytic hierarchy process and convex optimization methods are, respectively, developed to obtain beam and time resource allocation scheme. Finally, the effectiveness and superiority of the proposed framework are highlighted and evaluated by numerical simulations.

Ship Target Detection in SAR Imagery Based on Maximum Eigenvalue Detector

Ship target detection in synthetic aperture radar (SAR) imagery is of great significance in the field of ocean monitoring. Classical constant false alarm rate (CFAR) detectors and emerging information geometry methods are model-driven essentially, requiring precise modeling of the sea clutter distribution. In the complex and changeable ocean scenes, the performance of these two types of detectors is limited. To solve this problem, a ship target detection algorithm in SAR imagery based on the maximum eigenvalue of the sample covariance matrix is proposed in this letter. Without seeking the distribution model of clutter backgrounds, the difference between the target and the clutter background is fully captured by constructing the sample covariance matrix, and its maximum eigenvalue is utilized as the test statistic. Experimental results on measured SAR images show that the proposed method achieves better detection performance and faster calculation speed compared with the existing typical methods.

GPU-Oriented Designs of Constant False Alarm Rate Detectors for Fast Target Detection in Radar Images

Constant false alarm rate (CFAR) detector is a class of widely used methods for target detection in radar images. Classical CFAR detectors perform target detection on a pixel-by-pixel basis using certain sliding windows for estimating clutter statistics, which run fast for small images. However, as the image size gets large, the time cost of these detectors will increase significantly since the time complexity with respect to <i>N</i> &#x00D7; <i>N</i>-pixel image is <i>O</i>(<i>N</i>²). In practice, radar images, such as those in synthetic aperture radar (SAR), usually have very large numbers of pixels (which can be on the order of 10000 &#x00D7; 10000), making the classical CFAR detectors very time-consuming when applied to these images. In this paper, we present graphics processing unit (GPU)-oriented Designs for speeding up CFAR detectors, including smallest/greatest-of CFAR and order-statistic CFAR. The proposed designs implement CFAR detectors via tensor operations, including tensor convolution, shift, and boolean operation, which can be fast operated by GPU. Experiment results show that the proposed GPU-oriented CFAR detectors running on a high-performance Nvidia RTX 3090 GPU can be thousands of times faster than the classical CFAR detectors, and realize real-time target detection in large-size radar images. Examples using SAR and range-Doppler images are provided as illustrative applications of the proposed GPU CFAR detectors to target detection in radar images.

Clutter map detector for active diver detection sonar

This study presents a temporal approach based on the clutter map for the automatic detection of divers in the active sonar system. The noisy and non-stationary surrounding environment of shallow water makes the statistical parameters estimation of classical constant false alarm rate (CFAR) detectors more difficult. In the authors' system, they take advantage of the fixed positions of the transmitting and receiving arrays in order to improve the statistical parameters estimation over time. The resulting detection algorithm is analysed on simulated data for slow-moving targets and compared with classical spatial CFAR techniques on real data. The authors show that the proposed technique based on the clutter map provides better results than the classical CFAR techniques, particularly due to a reduction in false alerts. They finally analyse the spatial distribution of false alarms for which randomness is important for the performance of the tracking algorithm. They show that this distribution is more random with the clutter map detector than with classical CFAR techniques.

Neural network-based adaptive selection CFAR for radar target detection in various environments

Constant false alarm rate (CFAR), a target detection method commonly used in the radar systems, has an inconsistent performance against various environments. For improving the radar detectability, this paper proposes a novel scheme of radar target detection using neural network-based adaptive selection CFAR. The proposed method employs cell-averaging, ordered-statistic, greatest-of and smallest-of CFAR thresholds as the basis of references. The pattern of those threshold values combined with the cell under test signal value will be identified and classified by the neural network to compute the raw threshold. Then, the final threshold is selected depending on the nearest value between raw and four referenced CFARs. The performance of the proposed method is examined against three possible cases of the radar systems including homogeneous background, multiple targets and clutter boundary. The result of this research shows that the proposed method outperforms the classical CFARs due to the adaptive selection algorithm can select properly among referenced CFARs against the given cases particularly in the homogeneous and multiple target environments.

Superpixel-Level CFAR Detectors for Ship Detection in SAR Imagery

Synthetic aperture radar (SAR) is one of the most widely employed remote sensing modalities for large-scale monitoring of maritime activity. Ship detection in SAR images is a challenging task due to inherent speckle, discernible sea clutter, and the little exploitable shape information the targets present. Constant false alarm rate (CFAR) detectors, utilizing various sea clutter statistical models and thresholding schemes, are near ubiquitous in the literature. Very few of the proposed CFAR variants deviate from the classical CFAR topology; this letter proposes a modified topology, utilizing superpixels (SPs) in lieu of rectangular sliding windows to define CFAR guardbands and background. The aim is to achieve better target exclusion from the background band and reduced false detections. The performance of this modified SP-CFAR algorithm is demonstrated on TerraSAR-X and SENTINEL-1 images, achieving superior results in comparison to classical CFAR for various background distributions.

Joint Energy Detection and Massive Array Design for Localization and Mapping

The adoption of massive arrays for simultaneous localization and mapping or personal radar applications enables the possibility to detect and localize surrounding objects through an accurate beamforming procedure. Unfortunately, when a classical constant false alarm rate approach accounting for ideal-pencil beam pattern is adopted, ambiguities in signal detection could arise due to the presence of side-lobes which can cause non-negligible errors in target detection and ranging. To counteract such effect, in this paper we propose a joint threshold-array design approach, where the antenna characteristics are taken into account to best set the threshold and to guarantee the desired detection and ranging performance at the non-coherent receiver section. In order to consider realistic arrays impairments, we focus our attention on the number of antenna elements and of phase shifter bits used for beamforming as key players in defining a trade-off between structural complexity, well-defined radiation pattern, and localization performance. Simulation and measurement results show that the number of bits per phase shifter can be relaxed in favor of a simpler array design, if the number of antennas is sufficiently high and the side-lobes are kept within a suitable level allowing a desired robustness to interference signals.

The constant false alarm rate property in transformed noncoherent detection processes

Recently a transformation approach for noncoherent radar detector design has been introduced, where the classical constant false alarm rate detectors for Exponentially distributed clutter are modified to operate in any clutter intensity model of interest. Recent applications of this approach have introduced new decision rules for target detection in Pareto and Weibull distributed clutter. These transformed detectors tended to lose the constant false alarm rate property with respect to one of the clutter parameters. A closer examination of this transformation process yields conditions under which the constant false alarm rate property can be retained. Based upon this, a new model for X-band maritime radar returns is investigated, and corresponding detectors are developed. The relative merits of this new development are investigated with synthetic and real X-band data.

Multi-Chromatic Analysis of SAR Images for Coherent Target Detection

This work investigates the possibility of performing target analysis through the Multi-Chromatic Analysis (MCA), a technique that basically explores the information content of sub-band images obtained by processing portions of the range spectrum of a synthetic aperture radar (SAR) image. According to the behavior of the SAR signal at the different sub-bands, MCA allows target classification. Two strategies have been experimented by processing TerraSAR-X images acquired over the Venice Lagoon, Italy: one exploiting the phase of interferometric sub-band pairs, the other using the spectral coherence derived by computing the coherence between sub-band images of a single SAR acquisition. The first approach introduces the concept of frequency-persistent scatterers (FPS), which is complementary to that of the time-persistent scatterers (PS). FPS and PS populations have been derived and analyzed to evaluate the respective characteristics and the physical nature of the targets. Spectral coherence analysis has been applied to vessel detection, according to the property that, in presence of a random distribution of surface scatterers, as for open sea surfaces, spectral coherence is expected to be proportional to sub-band intersection, while in presence of manmade structures it is preserved anyhow. First results show that spectral coherence is well preserved even for very small vessels, and can be used as a complementary information channel to constrain vessel detection in addition to classical Constant False Alarm Rate techniques based on the sole intensity channel.

Knowledge-based detection method for SAR targets

When the classical constant false-alarm rate(CFAR)combined with fuzzy C-means(FCM) algorithm is applied to target detection in synthetic aperture radar(SAR) images with complex background, CFAR requires block-by-block estimation of clutter models and FCM clustering converges to local optimum. To address these problems, this paper pro-poses a new detection algorithm: knowledge-based combined with improved genetic algorithm-fuzzy C-means(GA-FCM) algorithm. Firstly, the algorithm takes target region’s maximum and average intensity, area,length of long axis and long-to-short axis ratio of the external ellipse as factors which influence the target appearing probability. The knowledge-based detection algorithm can produce preprocess results without the need of estimation of clutter models as CFAR does. Afterward the GA-FCM algorithm is improved to cluster pre-process results. It has advantages of incorporating global optimizing ability of GA and local optimizing ability of FCM, which will further eliminate false alarms and get better results. The effectiveness of the proposed technique is experimentally validated with real SAR images.

Ship detection based on morphological component analysis of high-frequency surface wave radar images

In this study, high-frequency surface wave radar (HFSWR) is considered for target detection. These systems, commonly used for oceanographic purposes, are of interest in maritime surveillance because of their long range detection capabilities compared with conventional microwave radar. Unfortunately, the received signals are strongly polluted by different noises. In this contribution a target detection method based on morphological component analysis (MCA) is investigated. Basically, MCA is a source separation technique based on multiscale transforms and the sparsity representation. The authors goal is to extract the target signatures from the range-Doppler image and then to take the final decision through a simple rule. This study introduces the issue of ship detection from HFSWR images and gives an overview of the MCA approach. Then, the algorithm used for target detection is depicted. Comparisons with a classical constant false-alarm rate (CFAR) detection method, the so-called greatest of cell averaging-CFAR, are given through receiver operating characteristic curves computed from simulated data.

Kernel wavelet-Reed–Xiaoli: an anomaly detection for forward-looking infrared imagery

This paper describes a new kernel wavelet-based anomaly detection technique for long-wave (LW) forward-looking infrared imagery. The proposed approach called kernel wavelet-Reed-Xiaoli (wavelet-RX) algorithm is essentially an extension of the wavelet-RX algorithm (combination of wavelet transform and RX anomaly detector) to a high-dimensional feature space (possibly infinite) via a certain nonlinear mapping function of the input data. The wavelet-RX algorithm in this high-dimensional feature space can easily be implemented in terms of kernels that implicitly compute dot products in the feature space (kernelizing the wavelet-RX algorithm). In the proposed kernel wavelet-RX algorithm, a two-dimensional wavelet transform is first applied to decompose the input image into uniform subbands. A number of significant subbands (high-energy subbands) are concatenated together to form a subband-image cube. The kernel RX algorithm is then applied to this subband-image cube. Experimental results are presented for the proposed kernel wavelet-RX, wavelet-RX, and the classical constant false alarm rate (CFAR) algorithm for detecting anomalies (targets) in a large database of LW imagery. The receiver operating characteristic plots show that the proposed kernel wavelet-RX algorithm outperforms the wavelet-RX as well as the classical CFAR detector.

Wavelet-RX anomaly detection for dual-band forward-looking infrared imagery

This paper describes a new wavelet-based anomaly detection technique for a dual-band forward-looking infrared (FLIR) sensor consisting of a coregistered longwave (LW) with a midwave (MW) sensor. The proposed approach, called the wavelet-RX (Reed-Xiaoli) algorithm, consists of a combination of a two-dimensional (2D) wavelet transform and a well-known multivariate anomaly detector called the RX algorithm. In our wavelet-RX algorithm, a 2D wavelet transform is first applied to decompose the input image into uniform subbands. A subband-image cube is formed by concatenating together a number of significant subbands (high-energy subbands). The RX algorithm is then applied to the subband-image cube obtained from a wavelet decomposition of the LW or MW sensor data. In the case of the dual band, the RX algorithm is applied to a subband-image cube constructed by concatenating together the high-energy subbands of the LW and MW subband-image cubes. Experimental results are presented for the proposed wavelet-RX and the classical constant false alarm rate (CFAR) algorithm for detecting anomalies (targets) in a single broadband FLIR (LW or MW) or in a coregistered dual-band FLIR sensor. The results show that the proposed wavelet-RX algorithm outperforms the classical CFAR detector for both single-band and dual-band FLIR sensors.

Ll-CFAR: a flexible and robust alternative

A new family of constant false alarm rate (CFAR) processors is introduced. An Ll-CFAR forms its noise power estimate by linearly filtering ranked samples from the reference set; the weights of this combination, however, depend not only on the rank, but also on the relative proximity of the sample to the cell under test. From the class of Ll-CFARs may be chosen members which effectively censor spurious targets; members which exhibit impressive control of false alarm in the presence of a clutter edge; and members which are robust against both such inhomogeneities. While the design of such schemes is involved, their implementation is not significantly more burdensome than that of plain ordered statistic CFAR (OS-CFAR). After a discussion of the stochastic training of Ll-CFAR, the performance is thoroughly assessed under the most commonly encountered instances of environmental conditions, and compared with those of classical CFAR techniques. >