- 标题
- 摘要
- 关键词
- 实验方案
- 产品
-
A Generative Discriminatory Classified Network for Change Detection in Multispectral Imagery
摘要： Multispectral image change detection based on deep learning generally needs a large amount of training data. However, it is difficult and expensive to mark a large amount of labeled data. To deal with this problem, we propose a generative discriminatory classified network (GDCN) for multispectral image change detection, in which labeled data, unlabeled data, and new fake data generated by generative adversarial networks are used. The GDCN consists of a discriminatory classified network (DCN) and a generator. The DCN divides the input data into changed class, unchanged class, and extra class, i.e., fake class. The generator recovers the real data from input noises to provide additional training samples so as to boost the performance of the DCN. Finally, the bitemporal multispectral images are input to the DCN to get the final change map. Experimental results on the real multispectral imagery datasets demonstrate that the proposed GDCN trained by unlabeled data and a small amount of labeled data can achieve competitive performance compared with existing methods.
关键词： Change detection,deep learning,multispectral imagery,generative adversarial networks (GANs)
更新于2025-09-23 15:23:52
-
Imbalanced Learning-Based Automatic SAR Images Change Detection by Morphologically Supervised PCA-Net
摘要： Change detection is a quite challenging task due to the imbalance between unchanged and changed class. In addition, the traditional difference map generated by log-ratio is subject to the speckle, which will reduce the accuracy. In this letter, an imbalanced learning-based change detection is proposed based on PCA network (PCA-Net), where a supervised PCA-Net is designed to obtain the robust features directly from given multitemporal synthetic aperture radar (SAR) images instead of a difference map. Furthermore, to tackle with the imbalance between changed and unchanged classes, we propose a morphologically supervised learning method, where the knowledge in the pixels near the boundary between two classes is exploited to guide network training. Finally, our proposed PCA-Net can be trained by the data sets with available reference maps and applied to a new data set, which is quite practical in change detection projects. Our proposed method is veri?ed on ?ve sets of multiple temporal SAR images. It is demonstrated from the experiment results that with the knowledge in training samples from the boundary, the learned features bene?t change detection and make the proposed method outperform than supervised methods trained by randomly drawing samples.
关键词： Change detection,imbalance learning,synthetic aperture radar (SAR) images,PCA network (PCA-Net)
更新于2025-09-23 15:23:52
-
Face Detection and Verification Using Lensless Cameras
摘要： Camera-based face detection and verification have advanced to the point where they are ready to be integrated into myriad applications, from household appliances to Internet of Things (IoT) devices to drones. Many of these applications impose stringent constraints on the form-factor, weight, and cost of the camera package that cannot be met by current-generation lens-based imagers. Lensless imaging systems provide an increasingly promising alternative that radically changes the form-factor and reduces the weight and cost of a camera system. However, lensless imagers currently cannot offer the same image resolution and clarity of their lens-based counterparts. This paper details a first-of-its-kind evaluation of the potential and efficacy of lensless imaging systems for face detection and verification. We propose the usage of existing deep learning techniques for face detection and verification that account for the resolution, noise, and artifacts inherent in today's lensless cameras. We demonstrate that both face detection and verification can be performed with high accuracy from the images acquired from lensless cameras, which paves the way to their integration into new applications. A key component of our study is a dataset of 24,112 lensless camera images captured using FlatCam of 88 subjects in a range of different operating conditions.
关键词： coded aperture,face verification,lensless imaging,deep learning,machine vision,face detection
更新于2025-09-23 15:23:52
-
Human gait recognition based on deterministic learning and data stream of Microsoft Kinect
摘要： Gait is an important biometric technology for human identification at a distance. This study focuses on gait features obtained by Kinect and proposes a new model-based gait recognition method by combining deterministic learning theory and data stream of Microsoft Kinect. Deterministic learning theory is employed to capture the gait dynamics underlying Kinect-based gait parameters. Spatial-temporal gait features can be represented as the gait dynamics underlying the trajectories of spatial-temporal parameters, which can implicitly reflect the temporal changes of silhouette shape. Kinematic gait features can be represented as the gait dynamics underlying the trajectories of kinematic parameters, which can represent the temporal changes of body structure and dynamics. Both spatial-temporal and kinematic cues can be used separately for gait recognition using smallest error principle. They are fused on the decision level to improve the gait recognition performance. Additionally, we discuss how to eliminate the effect of view angle on the proposed method. Experimental results indicate that encouraging recognition accuracy can be achieved.
关键词： deterministic learning,Kinect-based gait features,Gait recognition,biometrics
更新于2025-09-23 15:23:52
-
A CNN With Multiscale Convolution and Diversified Metric for Hyperspectral Image Classification
摘要： Recently, researchers have shown the powerful ability of deep methods with multilayers to extract high-level features and to obtain better performance for hyperspectral image classification. However, a common problem of traditional deep models is that the learned deep models might be suboptimal because of the limited number of training samples, especially for the image with large intraclass variance and low interclass variance. In this paper, novel convolutional neural networks (CNNs) with multiscale convolution (MS-CNNs) are proposed to address this problem by extracting deep multiscale features from the hyperspectral image. Moreover, deep metrics usually accompany with MS-CNNs to improve the representational ability for the hyperspectral image. However, the usual metric learning would make the metric parameters in the learned model tend to behave similarly. This similarity leads to obvious model’s redundancy and, thus, shows negative effects on the description ability of the deep metrics. Traditionally, determinantal point process (DPP) priors, which encourage the learned factors to repulse from one another, can be imposed over these factors to diversify them. Taking advantage of both the MS-CNNs and DPP-based diversity-promoting deep metrics, this paper develops a CNN with multiscale convolution and diversified metric to obtain discriminative features for hyperspectral image classification. Experiments are conducted over four real-world hyperspectral image data sets to show the effectiveness and applicability of the proposed method. Experimental results show that our method is better than original deep models and can produce comparable or even better classification performance in different hyperspectral image data sets with respect to spectral and spectral–spatial features.
关键词： deep metric learning,determinantal point process (DPP),image classification,multiscale features,Convolutional neural network (CNN),hyperspectral image
更新于2025-09-23 15:23:52
-
Dynamic Behavioral Modeling of RF Power Amplifier Based on Time-Delay Support Vector Regression
摘要： A new, dynamic behavioral modeling technique, based on a time-delay support vector regression (SVR) method, is presented in this paper. As an advanced machine learning algorithm, the SVR method provides an effective option for behavioral modeling of radio frequency (RF) power amplifiers (PAs), taking into account the effects of both device nonlinearity and memory. The basic theory of the proposed modeling technique is given, along with a detailed model extraction procedure. Unlike traditional artificial neural network (ANN) techniques, which take time to determine the best configuration of the model, the SVR method can obtain the optimal model in short time, using the grid-search technique. An example of an optimal SVR model selection applied to an RF PA is also given; the performance of the selected model presents a big improvement when compared with the default SVR model. Experimental validation is performed using an LDMOS PA, a single device gallium nitride (GaN) PA, and a Doherty GaN PA, revealing that the new modeling methodology provides very efficient and extremely accurate prediction. Compared with traditional Volterra models, canonical piecewise linear models, and ANN-based models, the proposed SVR model gives improved performance with reasonable complexity. In addition, it is shown that the model can predict accurately the behavior of the PA under input power levels that are different from those under which it is extracted.
关键词： time delay,radio frequency (RF) power amplifiers (PAs),machine learning,Dynamic behavioral model,support vector regression (SVR)
更新于2025-09-23 15:23:52
-
[IEEE 2018 24th International Conference on Pattern Recognition (ICPR) - Beijing, China (2018.8.20-2018.8.24)] 2018 24th International Conference on Pattern Recognition (ICPR) - Scale and Orientation Aware EPI-Patch Learning for Light Field Depth Estimation
摘要： Epipolar Plane Image (EPI) implies some important depth cues for light field depth estimation. Intuitively, the EPI patches with different spatial scales and orientations may exhibit different features and result in different estimation precision. In this paper, we discuss this issue and present a scale and orientation aware EPI-Patch learning model for depth estimation. We take the multi-orientation EPI patches of each pixel as input, and design two types of network structures for adaptive scale selection and orientation fusion. One type is a scale-aware structure, which feeds one orientation patch into a multi-layer feed-forward network with long and short skip connections. The other type is a shared-weight network for fusing the multi-orientation features. We demonstrate the effectiveness of our model by experiments on 4D Light Field Benchmark.
关键词： scale-aware,orientation-aware,depth estimation,deep learning,EPI,light field
更新于2025-09-23 15:23:52
-
Semisupervised Scene Classification for Remote Sensing Images: A Method Based on Convolutional Neural Networks and Ensemble Learning
摘要： The scarcity of labeled samples has been the main obstacle to the development of scene classification for remote sensing images. To alleviate this problem, the efforts have been dedicated to semisupervised classification which exploits both labeled and unlabeled samples for training classifiers. In this letter, we propose a novel semisupervised method that utilizes the effective residual convolutional neural network (ResNet) to extract preliminary image features. Moreover, the strategy of ensemble learning (EL) is adopted to establish discriminative image representations by exploring the intrinsic information of all available data. Finally, supervised learning is performed for scene classification. To verify the effectiveness of the proposed method, it is further compared with several state-of-the-art feature representation and semisupervised classification approaches. The experimental results show that by combining ResNet features with EL, the proposed method can obtain more effective image representations and achieve superior results.
关键词： remote sensing (RS) images,Semi-supervised classification,ensemble learning (EL),scene classification,Convolutional neural networks (CNNs)
更新于2025-09-23 15:23:52
-
Optical Character Recognition System for Nastalique Urdu-Like Script Languages using Supervised Learning
摘要： There are two main techniques to convert written or printed text into digital format. The first technique is to create an image of written/printed text, but images are large in size so they require huge memory space to store, also text in image form cannot be further processed like edit, search, copy etc. The second technique is to use an Optical Character Recognition (OCR) system. OCR’s can read documents and convert manual text documents into digital text and this digital text can be processed to extract knowledge. A huge amount of Urdu language’s data is available in handwritten or in printed form that needs to be converted into digital format for knowledge acquisition. Highly cursive, complex structure, bi-directionality, and compound in nature etc. make the Urdu language too complex to obtain accurate OCR results. In this study supervised learning based OCR system is proposed for Nastalique Urdu language. The proposed system’s evaluations under variety of experimental settings apprehend 98.4 % accuracy, which is highest recognition rate ever achieved by any Urdu language OCR system. The proposed system is simple to implement especially in software front of OCR system also the proposed technique is useful for printed text as well as handwritten text and it will help for developing more accurate Urdu OCR’s software systems in the future.
关键词： Optical Character Recognition (OCR),Image Processing,Urdu Nastalique,Supervised Learning,Pattern Recognition
更新于2025-09-23 15:23:52
-
Learning to reconstruct shape and spatially-varying reflectance from a single image
摘要： Reconstructing shape and reflectance properties from images is a highly under-constrained problem, and has previously been addressed by using specialized hardware to capture calibrated data or by assuming known (or highly constrained) shape or reflectance. In contrast, we demonstrate that we can recover non-Lambertian, spatially-varying BRDFs and complex geometry belonging to any arbitrary shape class, from a single RGB image captured under a combination of unknown environment illumination and flash lighting. We achieve this by training a deep neural network to regress shape and reflectance from the image. Our network is able to address this problem because of three novel contributions: first, we build a large-scale dataset of procedurally generated shapes and real-world complex SVBRDFs that approximate real world appearance well. Second, single image inverse rendering requires reasoning at multiple scales, and we propose a cascade network structure that allows this in a tractable manner. Finally, we incorporate an in-network rendering layer that aids the reconstruction task by handling global illumination effects that are important for real-world scenes. Together, these contributions allow us to tackle the entire inverse rendering problem in a holistic manner and produce state-of-the-art results on both synthetic and real data.
关键词： rendering layer,global illumination,deep learning,SVBRDF,single image,flash light,cascade network
更新于2025-09-23 15:23:52