Adaptive Automatic Target Recognition with SVM Boosting for Outlier Detection

Camera arrays can enhance the signal-to-noise ratio (SNR) between dim targets and backgrounds through multi-view synthesis. This is crucial for the detection of dim targets. To this end, we design and develop an infrared camera array system with a large baseline. The multi-view synthesis of camera arrays relies heavily on the calibration accuracy of relative poses in the sub-cameras. However, the sub-cameras within a camera array lack strict geometric constraints. Therefore, most current calibration methods still consider the camera array as multiple pinhole cameras for calibration. Moreover, when detecting distant targets, the camera array usually needs to adjust the focal length to maintain a larger depth of field (DoF), so that the distant targets are located on the camera’s focal plane. This means that the calibration scene should be selected within this DoF range to obtain clear images. Nevertheless, the small parallax between the distant sub-aperture views limits the calibration. To address these issues, we propose a calibration model for camera arrays in distant scenes. In this model, we first extend the parallax by employing dual-array frames (i.e., recording a scene at two spatial locations). Secondly, we investigate the linear constraints between the dual-array frames, to maintain the minimum degrees of freedom of the model. We develop a real-world light field dataset called NUDT-Dual-Array using an infrared camera array to evaluate our method. Experimental results on our self-developed datasets demonstrate the effectiveness of our method. Using the calibrated model, we improve the SNR of distant dim targets, which ultimately enhances the detection and perception of dim targets.

An optimal nonlinear Bayesian TBD (track-before-detect) algorithm based on particle filter for dim targets detection and tracking in cluttered background is proposed. To make full use of the targets a priori information, a table of possible target movements and their transition probabilities among these base states are introduced. Furthermore, the TBD technology is exploited for the target detection in cluttered image sequences with low SNR. Here particle filter is provided to implement the Bayesian regression and estimate the target's state model at each step.

“Track-before-detection” (TBD) is well suitable for radar detection of dim targets because it takes advantage of the gains of time integration. Dynamic programming algorithm (DPA) is one of the traditional TBD techniques, and has been applied to sea dim target detection. In this paper, the expression of DPA applied to air dim target detection is given firstly. Important differences between air dim target and sea dim target is introduced in the application of DPA. In the end, numerical simulations show that air dim target detection based on DPA is limited in radar performance enhancement. (3 pages)

Small and dim target detection is a critical challenge in hyperspectral remote sensing, particularly in complex, large-scale scenes where spectral variability across diverse land cover types complicates the detection process. In this paper, we propose a novel target reasoning algorithm named Adaptive Global Dense Nested Reasoning Network (AGDNR). This algorithm integrates spatial, spectral, and domain knowledge to enhance the detection accuracy of small and dim targets in large-scale environments and simultaneously enables reasoning about target categories. The proposed method involves three key innovations. Firstly, we develop a high-dimensional, multi-layer nested U-Net that facilitates cross-layer feature transfer, preserving high-level features of small and dim targets throughout the network. Secondly, we present a novel approach for computing physicochemical parameters, which enhances the spectral characteristics of targets while minimizing environmental interference. Thirdly, we construct a geographic knowledge graph that incorporates both target and environmental information, enabling global target reasoning and more effective detection of small targets across large-scale scenes. Experimental results on three challenging datasets show that our method outperforms state-of-the-art approaches in detection accuracy and achieves successful classification of different small targets. Consequently, the proposed method offers a robust solution for the precise detection of hyperspectral small targets in large-scale scenarios.

Research on Infrared Dim and Small Target Detection Algorithm Based on Low-Rank Tensor Recovery

In the field of infrared remote sensing, the problem of IR small target detection is still an important component part. Concerning infrared dim small target (IRDST) detection, firstly the infrared image is processed with DWT method to get the wavelet coefficients image, but the distribution characteristics, such as scales, frequencies, orientations of wavelet coefficients in different sub-bands are various, so wavelet image denoised by a single threshold criterion can not give a satisfying estimation. Based on this motivation, a spatially adaptive multi-model de-noising strategy (SAMMDS) based IRDST detection method is proposed in this paper, which can adjust thresholding strategy according to the distribution of noise in different scales and directions. Spatially adaptive BayesShrink (SABS) thresholding, traditional BayesShrink (BS) thresholding and generalized cross validation (GCV) thresholding are all adopted here to process each sub-band separately. After reconstructing the denoised wavelet image, a simple global thresholding is used to separate the background and target finally. Experimental results demonstrate that the proposed algorithm performs better than other typical wavelet methods for small target detection with various complex backgrounds.

We describe the development and the implementation of a new nonlinear image processing methodology to detect dim targets in infrared images. The methodology is based on mathematical morphology. In a first phase, the image is filtered in order to enhance positively contrasted, isotropic objects with a specified size. Then, a simple motion analysis is carried out, and finally, detection is performed by thresholding. A complete study of the algorithm performance on NATO test sequences is presented. A comparison is made with the Holmes filter and the scale-subtraction filter, a wavelet-based method.

Automatic target recognition (ATR) is a challenging task for several computer vision applications. It requires efficient, accurate, and robust methods for target detection and target identification. Deep learning has shown great success in many computer vision applications involving color RGB images. However, the performance of these networks in ATR with infrared sensor data needs further investigation. In this paper, we propose a multistage automatic target detection and recognition (ATDR) system that performs both target detection and target classification on infrared (IR) imagery using deep learning. Our system processes large IR image frames where targets take <1 % of the total number of pixels. First, we train a state-of-the-art object detector you only look once (YOLO) to localize all potential targets in the input image frame. Then, we train a convolutional neural network (CNN) to identify these detections as targets or false alarms. In this second phase, we adapt and analyze the performance of three CNN architectures: a compact and fully connected CNN, VGG16 with batch normalization, and a wide residual neural network (WRN). We also explore the use of a loss function that optimizes directly the area under the receiver operating characteristic (ROC) curve (AUC), and adapt it to our ATR application. To enhance the robustness of the proposed ATR to perturbation and variations introduced during the detection stage, we train our CNN classifiers on automatically detected targets using YOLO, in addition to ground truth bounding boxes and apply selected data augmentation techniques. To simulate real testing environments, where the spatial location of the targets within the image frame is unknown, only YOLO-detected boxes are used during validation. We evaluate our ATDR on a real benchmark dataset that includes different vehicles captured at different resolutions. Our experiments have shown that YOLO can detect most of the targets at the expense of generating a high number of false alarms. We show that the VGG-16 network with batch normalization, which is the best performing model, can correctly identify the classes of the targets, as well as classify the majority of YOLO’s false detections into an additional nontarget class. We also show that the proposed training modification to optimize an AUC-based loss function for ATR proved to be advantageous mainly in identifying difficult targets.

This paper deals with the detection of dim point targets in infrared images. Dim point targets detection is always a difficulty in information processing. Researchers have proposed many effective methods; this paper introduces a new method. Whereas difference method has obtained good result in one dimensional signal processing, this paper manages to apply it to two dimensional signal processing, that is to say, dim point targets detection in infrared images of low SNR. The image background is color noise, and its column correlation is strong. So, ordinary methods probably lose the true targets because of the strong color noise, but unlike them, difference method can overcome this shortcoming, it can eliminate correlation noise and enhance useful information, finally pick out the probable targets from noise background. In the paper, the method was given a more extensive account. In order to improve the detection effect, we utilize prefilter. The prefilter is realized by the alpha filter. Because the same targets have same location in more than three frames, using alpha filter can utilize the information of adjacent frames, increase the SNR of the raw data and reduce the noise of the images. >

The development of effective knowledge discovery techniques has become a very active research area in recent years due to the important impact it has had in several relevant application domains. One interesting task therein is that of singling out anomalous individuals from a given population, for example, to detect rare events in time-series analysis settings, or to identify objects whose behavior is deviant w.r.t. a codified standard set of rules. Such exceptional individuals are usually referred to as outliers in the literature. In this article, the concept of outlier is formally stated in the context of knowledge-based systems, by generalizing that originally proposed in Angiulli et al. [2003] in the context of default theories. The chosen formal framework here is that of logic programming, wherein potential applications of techniques for outlier detection are thoroughly discussed. The proposed formalization is a novel one and helps to shed light on the nature of outliers occurring in logic bases. Also the exploitation of minimality criteria in outlier detection is illustrated. The computational complexity of outlier detection problems arising in this novel setting is also thoroughly investigated and accounted for in the paper. Finally, rewriting algorithms are proposed that transform any outlier detection problem into an equivalent inference problem under stable model semantics, thereby making outlier computation effective and realizable on top of any stable model solver.

With the widespread use of closed-circuit television (CCTV) surveillance systems in public areas, crowd anomaly detection has become an increasingly critical aspect of the intelligent video surveillance system. It requires workforce and continuous attention to decide on the captured event, which is hard to perform by individuals. The available literature on human action detection includes various approaches to detect abnormal crowd behavior, which is articulated as an outlier detection problem. This paper presents a detailed review of the recent development of anomaly detection methods from the perspectives of computer vision on different available datasets. A new taxonomic organization of existing works in crowd analysis and anomaly detection has been introduced. A summarization of existing reviews and datasets related to anomaly detection has been listed. It covers an overview of different crowd concepts, including mass gathering events analysis and challenges, types of anomalies, and surveillance systems. Additionally, research trends and future work prospects have been analyzed.

Dim target detection in infrared image with complex background and low signal-ratio (SCR) is a significant and difficult task in the infrared target tracking system, this paper proposes a real time dim target detection algorithm based on fractional differential algorithm. An improved top-hat operator is adopted to process the original image which can restrain the background well. After we enhance the target based on a fractional differential algorithm, to further eliminate residual clutter and gain the saliency map, we process the enhanced image with a spectral residual method. The pipeline filter can reduce the false alarm rate further at last. The algorithm is tested on three different infrared image sequences, and the experimental results show that the algorithm is efficient and robust, which would be very useful for infrared dim small target detection. In particular, the proposed method can improve the SNR of the image significantly.

The outlier detection problem has important applications in the field of fraud detection, network robustness analysis, and intrusion detection. Most such applications are high dimensional domains in which the data can contain hundreds of dimensions. Many recent algorithms use concepts of proximity in order to find outliers based on their relationship to the rest of the data. However, in high dimensional space, the data is sparse and the notion of proximity fails to retain its meaningfulness. In fact, the sparsity of high dimensional data implies that every point is an almost equally good outlier from the perspective of proximity-based definitions. Consequently, for high dimensional data, the notion of finding meaningful outliers becomes substantially more complex and non-obvious. In this paper, we discuss new techniques for outlier detection which find the outliers by studying the behavior of projections from the data set.

Restricted default theories: Expressive power and outlier detection tasks

The detection of dim targets in heavy clutter requires large gains in the SCR. Gains of the required magnitude have been obtained with space-temporal processing. However, in many cases these gains are either difficult or expensive to realize. If the range to the clutter is small relative to the clutter velocity, the temporal processing will need to include scene registration and optical flow correction. Scene registration is computationally expensive especially for large search volumes. The correction of optical flow is both expensive and typically less than satisfactory. The spectral dimension provides an alternative to the temporal dimension. Since the data in each of the spectral bands is collected simultaneously or nearly so, the problems of registration and optical flow are eliminated. This paper considers the performance of the multi-spectral IR bands. Dual band performance results comparing space spectral processing with space temporal will be shown. An analytic model of the probability of false alarm as a function of the number of spectral bands is presented. A comparison of this model to experimental result using multi-spectral IRST data is given.© (1998) COPYRIGHT SPIE--The International Society for Optical Engineering. Downloading of the abstract is permitted for personal use only.