- 标题
- 摘要
- 关键词
- 实验方案
- 产品
-
Multiple Instance Choquet Integral Classifier Fusion and Regression for Remote Sensing Applications
摘要： In classifier (or regression) fusion, the aim is to combine the outputs of several algorithms to boost overall performance. Standard supervised fusion algorithms often require accurate and precise training labels. However, accurate labels may be difficult to obtain in many remote sensing applications. This paper proposes novel classification and regression fusion models that can be trained given ambiguously and imprecisely labeled training data in which the training labels are associated with sets of data points (i.e., “bags”) instead of individual data points (i.e., “instances”) following a multiple-instance learning framework. Experiments were conducted based on the proposed algorithms on both synthetic data and applications such as target detection and crop yield prediction given remote sensing data. The proposed algorithms show effective classification and regression performance.
关键词： remote sensing,multiple-instance regression (MIR),multiple-instance learning (MIL),target detection,Choquet integral (CI),classifier fusion
更新于2025-09-10 09:29:36
-
[IEEE 2018 IEEE 3rd Optoelectronics Global Conference (OGC) - Shenzhen, China (2018.9.4-2018.9.7)] 2018 IEEE 3rd Optoelectronics Global Conference (OGC) - Infrared Target Detection Based on Local Contrast Method and LK Optical Flow
摘要： A robust and effective small dim object detection algorithm is the key to the success of an infrared tracking system. To help solve practical tracking problems, a detecting algorithm based on local contrast method (LCM) and Lucas– Kanade method (LK) is put forward. Firstly, the local contrast map of the input image is obtained using the local contrast measure which measures the dissimilarity between the current location and its neighborhoods. In this way, target signal enhancement and background clutter suppression are achieved simultaneously. Secondly, an adaptive threshold is applied to extract the suspected object regions. Finally, the central points of obtained regions are used as characteristic points, then LK optical flow algorithm to calculate optical flow at these points, and through the instantaneous velocity calculation and selection targets are detected. The experimental result shows that this method works perfectly and can effectively detect infrared targets under complex backgrounds.
关键词： target detection,infrared image,lucas–kanade method (LK),local contrast method (LCM)
更新于2025-09-10 09:29:36
-
Hyperspectral Target Detection via Adaptive Information—Theoretic Metric Learning with Local Constraints
摘要： By using the high spectral resolution, hyperspectral images (HSIs) provide significant information for target detection, which is of great interest in HSI processing. However, most classical target detection methods may only perform well based on certain assumptions. Simultaneously, using limited numbers of target samples and preserving the discriminative information is also a challenging problem in hyperspectral target detection. To overcome these shortcomings, this paper proposes a novel adaptive information-theoretic metric learning with local constraints (ITML-ALC) for hyperspectral target detection. The proposed method firstly uses the information-theoretic metric learning (ITML) method as the objective function for learning a Mahalanobis distance to separate similar and dissimilar point-pairs without certain assumptions, needing fewer adjusted parameters. Then, adaptively local constraints are applied to shrink the distances between samples of similar pairs and expand the distances between samples of dissimilar pairs. Finally, target detection decision can be made by considering both the threshold and the changes between the distances before and after metric learning. Experimental results demonstrate that the proposed method can obviously separate target samples from background ones and outperform both the state-of-the-art target detection algorithms and the other classical metric learning methods.
关键词： target detection,hyperspectral image,local constraints,metric learning
更新于2025-09-10 09:29:36
-
Distributed Target Detection Exploiting Persymmetry in Gaussian Clutter
摘要： In this paper, we consider the distributed target detection problem in Gaussian clutter with unknown covariance matrix. By exploiting the persymmetry of the covariance matrix, an adaptive detector is proposed according to the two-step design method. The probabilities of detection and false alarm of the proposed detector are derived in closed form, which are veri?ed through Monte Carlo simulations. The expression for the probability of false alarm reveals that the proposed detector bears constant false alarm rate against the covariance matrix. Numerical examples illustrate that the proposed detector outperforms its counterparts, especially in the limited training data environment.
关键词： constant false alarm rate,persymmetry,Adaptive detection,distributed target detection
更新于2025-09-09 09:28:46
-
[IEEE IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium - Valencia, Spain (2018.7.22-2018.7.27)] IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium - Target detection in remote sensing image based on saliency computation of spiking neural network
摘要： Target detection is a-priori conditions for target tracking, classification, recognition, and scene understanding in Remote Sensing Image (RSI) analysis. However, the many traditional algorithms for target detection cannot perform well when the image resolution, especially for high-resolution RSIs, is change. Therefore, in this paper, we introduce a novel target detection algorithm based on the visual saliency of Spiking Neural Networks (SNN), which can efficiently detect the discriminative information from high-resolution RSIs to find targets by a saliency computing. As a result of this, it can provide an efficient and fast calculation method. The proposed visual saliency algorithm was applied to extensive experiments to detect the ship, and experimental results showed the outstanding performance for target detection on the optical RSI and synthetic aperture image.
关键词： visual saliency,target detection,spiking neural network,high-resolution RSI,saliency computation
更新于2025-09-09 09:28:46
-
[IEEE IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium - Valencia, Spain (2018.7.22-2018.7.27)] IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium - Polarimetric Coherence Optimization as a Multidimensional Polarimetric SAR Signal Processing Tool
摘要： This paper summarizes a set of studies led on the topic of polarimetric coherence optimization for the coherent processing of stacks of polarimetric SAR images. It is shown that coherence maximization may be understood differently depending on the application at hand. Extracting polarimetric coherent signals embedded in noise or in a severe background requires to use polarimetric diversity as a supplementary mean for discovering organized speckles patterns, whereas classical MB-PolInSAR coherence optimization gives more importance to the polarimetric scattering mechanisms that extremize coherence values. This paper reviews different techniques able to cope with an arbitrary number of images and that are characterized by their low degree of computational complexity, conferred by the favored use of analytical solutions. The usefulness of these techniques is demonstrated using various kinds of applications to real spaceborne and airborne datasets.
关键词： Polarimetric SAR Tomography (PolTomSAR),PolSAR,coherence optimization,coherent target detection,3-D imaging
更新于2025-09-09 09:28:46
-
[IEEE IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium - Valencia, Spain (2018.7.22-2018.7.27)] IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium - CNN-Based Target Detection in Hyperspectral Imagery
摘要： This paper proposes a hyperspectral target detection framework with convolutional neural network (CNN). The number of training samples is first sufficiently enlarged by subtraction method to maximize the advantages of the multilayer CNN. Next, the CNN is given a target detection function by labelling the new pixels subtracted between target and background classes as 1, and the pixels subtracted between pixels within both the same and different background classes as 0. Finally, for each testing pixel, the difference between the central pixel and its adjacent pixels is input into the framework. If the testing pixel belongs to the target, the output score is close to the target label. Aircrafts and vehicles are selected as targets of interest in the experiment conducted to validate the proposed method. The experiment results show that the proposed method has an advantage over classic hyperspectral target detection algorithms in terms of precision and robustness.
关键词： Deep Learning,Convolutional Neural Network,Target Detection,Remote Sensing,Hyperspectral
更新于2025-09-09 09:28:46
-
[IEEE 2018 2nd IEEE Advanced Information Management,Communicates, Electronic and Automation Control Conference (IMCEC) - Xi'an (2018.5.25-2018.5.27)] 2018 2nd IEEE Advanced Information Management,Communicates,Electronic and Automation Control Conference (IMCEC) - Hyperspectral Target Detection with CNN Using Subtraction Model
摘要： Recently, the convolutional neural network (CNN) has been widely used in the fields of hyperspectral image (HSI) processing. In this paper, a CNN-based hyperspectral target detection framework is presented. And subtraction model is used to sufficiently enlarge the number of training samples. The subtraction model is built from twenty-eight manually selected objects in several AVIRIS date following three aspects: 1) The new pixel made by subtraction of any two pixels between 27 different classes is labelled as 0; 2) the new pixel made by subtraction of any two pixels within per class is labelled as 0; 3) the new pixel made by subtraction of any two pixels, in which one pixel is from the target class and the other is from background classes, is labelled as 1. Theoretically, if the pixel under test belongs to the target class, the output label of the CNN will be the same as the label of the target class. The experiment results on three images all indicate that the proposed CNN-based detector outperforms the classical hyperspectral target detection algorithms.
关键词： target detection,convolutional neural network,deep learning,hyperspectral imagery
更新于2025-09-09 09:28:46
-
Quantum Illumination with Noiseless Linear Amplifier
摘要： Quantum illumination, that is, quantum target detection, is to detect the potential target with two-mode quantum entangled state. For a given transmitted energy, the quantum illumination can achieve a target-detection probability of error much lower than the illumination scheme without entanglement. We investigate the usefulness of noiseless linear amplification (NLA) for quantum illumination. Our result shows that NLA can help to substantially reduce the number of quantum entangled states collected for joint measurement of multi-copy quantum state. Our analysis on the NLA-assisted scheme could help to develop more efficient schemes for quantum illumination.
关键词： noiseless linear amplification,quantum target detection,quantum illumination
更新于2025-09-09 09:28:46
-
A New Target Detector Based on Subspace Projections Using Polarimetric SAR Data
摘要： Most applications of radar imagery require processing techniques which achieve one fundamental goal: characterize and detect the constituent scatterers for each pixel in the scene. In this paper, we take a new look at the target detection issue in polarimetric synthetic aperture radar data and assume several canonical scattering mechanisms as our signal sources whose combination of them with appropriate weight fractions formed the scattering vector of each pixel. The presence of speckle as a consequence of coherent processing of the scattered signals is modeled as signal-dependent additive noise. The set of the scattering mechanisms is divided into two groups: objected scattering mechanism belonging to the target, and nonobjected scattering mechanisms. Then, we make use of two techniques based on subspace projections for speckle reduction and the nonobjected scattering mechanisms annihilation, followed by detecting the presence of the scattering mechanism of interest. In the problem formulation scenario, a novel feature space is proposed consisting of two subspaces—the objected subspace and the nonobjected subspace. Then, the detection approach under this scenario is derived. An orthogonal subspace projection technique is utilized for speckle reduction. Moreover, in order to annihilate the nonobjected subspace, each pixel’s feature vector is obliquely projected onto the objected subspace. With the annihilation of the nonobjected subspace and using the polarimetric information of the objected subspace, the detectability of the target scattering mechanism is therefore enhanced. Finally, evaluation against C-, L-, and P-band fully polarimetric SAR data sets is provided with a significant agreement with the expected results.
关键词： synthetic aperture radar (SAR),subspace projection,Polarimetry,target detection,scattering vector
更新于2025-09-09 09:28:46