- 标题
- 摘要
- 关键词
- 实验方案
- 产品
-
Dictionaries of deep features for land-use scene classification of very high spatial resolution images
摘要： Land-use classification in very high spatial resolution images is critical in the remote sensing field. Consequently, remarkable efforts have been conducted towards developing increasingly accurate approaches for this task. In recent years, deep learning has emerged as a dominant paradigm for machine learning, and methodologies based on deep convolutional neural networks have received particular attention from the remote sensing community. These methods typically utilize transfer learning and/or data augmentation to accommodate a small number of labeled images in the publicly available datasets in this field. However, they typically require powerful computers and/or a long time for training. In this work, we propose a simple and novel method for land-use classification in very high spatial resolution images, which efficiently combines transfer learning with a sparse representation. Specifically, the proposed method performs the classification of land-use scenes using a modified version of the well-known sparse representation-based classification method. While this method directly uses the training images to form dictionaries, which are employed to classify test images, our method utilizes a pre-trained deep convolutional neural network and the Gaussian mixture model to generate more robust and compact 'dictionaries of deep features.' The effectiveness of the proposed method was evaluated on two publicly available datasets: UC Merced and Brazilian Cerrado–Savana. The experimental results suggest that our method can potentially outperform state-of-the-art techniques for land-use classification in very high spatial resolution images.
关键词： Dictionary learning,Land-use classification,Sparse representation,Feature learning,Deep learning
更新于2025-09-23 15:23:52
-
DeeptransMap: a considerably deep transmission estimation network for single image dehazing
摘要： Due to the ill-posed phenomenon of the classical physical model, single image dehazing based on the model has been a challenging vision task. In recent years, applying machine learning techniques to estimate a critical parameter transmission has proven to be an effective solution to this issue. Accordingly, the robustness and accuracy of learning-based transmission estimation model is extremely important, since it does impact on the final dehazing effects. The state-of-the-art dehazing algorithms by this means generally use haze-relevant features as the single input to their transmission estimation models. However, the used haze-relevant features sometimes are not sufficient and reliable in holding real intrinsic information related to haze due to their two shortcomings and ultimately bring about their less effectiveness for some dehazing cases. Based on related efforts on representation learning and deep convolutional neural networks, in this paper, we seek to achieve the robustness and accuracy of transmission estimation model for bolstering the effectiveness of single image dehazing. Specifically, we propose a hybrid model combining unsupervised and supervised learning in a considerably deep neural networks architecture, in order to achieve accurate transmission map from a single image. Experimental results demonstrate that our work performs favorably against several state-of-the-art dehazing methods with the same estimated goal and keeps efficient in terms of the computational complexity of transmission estimation.
关键词： Feature learning,Deep convolutional neural networks (CNNs),Image dehazing,Transmission estimation
更新于2025-09-23 15:23:52
-
A Comprehensive Evaluation of Approaches for Built-Up Area Extraction from Landsat OLI Images Using Massive Samples
摘要： Detailed information about built-up areas is valuable for mapping complex urban environments. Although a large number of classification algorithms for such areas have been developed, they are rarely tested from the perspective of feature engineering and feature learning. Therefore, we launched a unique investigation to provide a full test of the Operational Land Imager (OLI) imagery for 15-m resolution built-up area classification in 2015, in Beijing, China. Training a classifier requires many sample points, and we proposed a method based on the European Space Agency’s (ESA) 38-m global built-up area data of 2014, OpenStreetMap, and MOD13Q1-NDVI to achieve the rapid and automatic generation of a large number of sample points. Our aim was to examine the influence of a single pixel and image patch under traditional feature engineering and modern feature learning strategies. In feature engineering, we consider spectra, shape, and texture as the input features, and support vector machine (SVM), random forest (RF), and AdaBoost as the classification algorithms. In feature learning, the convolutional neural network (CNN) is used as the classification algorithm. In total, 26 built-up land cover maps were produced. The experimental results show the following: (1) The approaches based on feature learning are generally better than those based on feature engineering in terms of classification accuracy, and the performance of ensemble classifiers (e.g., RF) are comparable to that of CNN. Two-dimensional CNN and the 7-neighborhood RF have the highest classification accuracies at nearly 91%; (2) Overall, the classification effect and accuracy based on image patches are better than those based on single pixels. The features that can highlight the information of the target category (e.g., PanTex (texture-derived built-up presence index) and enhanced morphological building index (EMBI)) can help improve classification accuracy. The code and experimental results are available at https://github.com/zhangtao151820/CompareMethod.
关键词： classification,CNN,feature engineering,built-up area,Landsat 8-OLI,accuracy evaluation,feature learning
更新于2025-09-23 15:22:29
-
[IEEE IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium - Valencia (2018.7.22-2018.7.27)] IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium - A Comparative Evaluation of Polarimetric Distance Measures within the Random Forest Framework for the Classification of Polsar Images
摘要： Random Forests have been shown to be able to be applied directly to polarimetric synthetic aperture radar (PolSAR) data instead of to extracted hand-crafted features by adapting the internal node tests. This paper investigates different polarimetric distance measures and their potential to be used by Random Forests for the classification of PolSAR images. The experiments show that using distance measures tailored towards the statistics of PolSAR data outperforms the usage of individual hand-crafted polarimetric features and their combination. However, the differences between accuracies obtained by different suitable distance measures are insignificant allowing to take other aspects into consideration such as computational efficiency.
关键词： Random Forest,PolSAR,Polarimetric Distances,Classification,Feature learning
更新于2025-09-23 15:22:29
-
Canonical Correlation Analysis Regularization: An Effective Deep Multi-View Learning Baseline for RGB-D Object Recognition
摘要： Object recognition methods based on multi-modal data, color plus depth (RGB-D), usually treat each modality separately in feature extraction, which neglects implicit relations between two views and preserves noise from any view to the ?nal representation. To address these limitations, we propose a novel Canonical Correlation Analysis (CCA)-based multi-view Convolutional Neural Network (CNNs) framework for RGB-D object representation. The RGB and depth streams process corresponding images respectively, then are connected by CCA module leading to a common-correlated feature space. In addition, to embed CCA into deep CNNs in a supervised manner, two different schemes are explored. One considers CCA as a regularization term adding to the loss function (CCAR). However, solving CCA optimization directly is neither computationally ef?cient nor compatible with the mini-batch based stochastic optimization. Thus, we further propose an approximation method of CCA regularization (ACCAR), using the obtained CCA projection matrices to replace the weights of feature concatenation layer at regular intervals. Such a scheme enjoys bene?ts of full CCA regularization and is ef?cient by amortizing its cost over many training iterations. Experiments on benchmark RGB-D object recognition datasets have shown that the proposed methods outperform most existing methods using the very same of their network architectures.
关键词： Deep learning,Canonical Correlation Analysis,Multi-view feature learning,RGB-D object recognition
更新于2025-09-23 15:21:01
-
A Low-Light Sensor Image Enhancement Algorithm Based on HSI Color Model
摘要： Images captured by sensors in unpleasant environment like low illumination condition are usually degraded, which means low visibility, low brightness, and low contrast. In order to improve this kind of images, in this paper, a low-light sensor image enhancement algorithm based on HSI color model is proposed. At ?rst, we propose a dataset generation method based on the Retinex model to overcome the shortage of sample data. Then, the original low-light image is transformed from RGB to HSI color space. The segmentation exponential method is used to process the saturation (S) and the specially designed Deep Convolutional Neural Network is applied to enhance the intensity component (I). At the end, we back into the original RGB space to get the ?nal improved image. Experimental results show that the proposed algorithm not only enhances the image brightness and contrast signi?cantly, but also avoids color distortion and over-enhancement in comparison with some other state-of-the-art research papers. So, it effectively improves the quality of sensor images.
关键词： convolutional neural network,Retinex model,image enhancement,color model,batch normalization,feature learning
更新于2025-09-23 15:21:01
-
[IEEE 2019 IEEE 46th Photovoltaic Specialists Conference (PVSC) - Chicago, IL, USA (2019.6.16-2019.6.21)] 2019 IEEE 46th Photovoltaic Specialists Conference (PVSC) - Perovskite solar cell devices on flexible stainless-steel substrate
摘要： Mixed-type categorical and numerical data are a challenge in many applications. This general area of mixed-type data is among the frontier areas, where computational intelligence approaches are often brittle compared with the capabilities of living creatures. In this paper, unsupervised feature learning (UFL) is applied to the mixed-type data to achieve a sparse representation, which makes it easier for clustering algorithms to separate the data. Unlike other UFL methods that work with homogeneous data, such as image and video data, the presented UFL works with the mixed-type data using fuzzy adaptive resonance theory (ART). UFL with fuzzy ART (UFLA) obtains a better clustering result by removing the differences in treating categorical and numeric features. The advantages of doing this are demonstrated with several real-world data sets with ground truth, including heart disease, teaching assistant evaluation, and credit approval. The approach is also demonstrated on noisy, mixed-type petroleum industry data. UFLA is compared with several alternative methods. To the best of our knowledge, this is the first time UFL has been extended to accomplish the fusion of mixed data types.
关键词： fuzzy ART,mixed-type data,unsupervised feature learning,Clustering
更新于2025-09-23 15:19:57
-
Sparse Feature Learning with Label Information for Alzheimer’s Disease Classification Based on Magnetic Resonance Imaging
摘要： Biomedical signal processing data have been used for automatic diagnosis and classification of brain disease, which is an important part of research in smart city. How to select discriminant features from these data is the key that will affect subsequent automatic diagnosis and classification performance. However, in previous manifold regularized sparse regression models, the local neighborhood structure was constructed directly in the traditional Euclidean distance without fully utilizing the label information of the subjects, which leads to the selection of less discriminative features. In this paper, we propose a novel manifold regularized sparse regression model for learning discriminative features. Specifically, we first adopt l2,1-norm regularization to jointly select a relevant feature subset among the samples. Then, to select more discriminative features, a novel manifold regularization term is constructed via the relative distance adjusted by the label information, which can simultaneously maintain the compactness of intra-class samples and the separability of inter-class samples. The proposed feature learning method is further carried out for both the binary classification and the multi-class classification. Experimental results on Alzheimer’s Disease Neuroimaging Initiative database demonstrate the effectiveness of the proposed method, which can be utilized for the diagnosis of Alzheimer’s disease and mild cognitive impairment.
关键词： feature learning,Alzheimer's disease,manifold regularization,sparse regression
更新于2025-09-19 17:15:36
-
[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 - Classification of Hyperspectral Image Based on Hybrid Neural Networks
摘要： Convolutional neural networks (CNN), which are able to extract spatial semantic features, have achieved outstanding performance in many computer vision tasks. In this paper, hybrid neural networks (HNN) are proposed to extract both spatial and spectral features in the same deep networks. The proposed networks consist of different types of hidden layers, including spatial structure layer, spatial contextual layer, and spectral layer. All those layers work as organic networks to explore as much valuable information as possible from hyperspectral data for classification. Experimental results demonstrate competitive performance of the proposed approach over other state-of-the-art neural networks methods. Moreover, the proposed method is a new way to deal with multidimensional data with deep networks.
关键词： supervised classification,feature learning,hyperspectral image (HSI),convolutional neural networks (CNN)
更新于2025-09-10 09:29:36
-
A Local Metric for Defocus Blur Detection Based on CNN Feature Learning
摘要： Defocus blur detection is an important and challenging task in computer vision and digital imaging fields. Previous work on defocus blur detection has put a lot of effort into designing local sharpness metric maps. This paper presents a simple yet effective method to automatically obtain the local metric map for defocus blur detection, which based on the feature learning of multiple convolutional neural networks (ConvNets). The ConvNets automatically learn the most locally relevant features at the super-pixel level of the image in a supervised manner. By extracting convolution kernels from the trained neural network structures and processing it with principal component analysis, we can automatically obtain the local sharpness metric by reshaping the principal component vector. Meanwhile, an effective iterative updating mechanism is proposed to refine the defocus blur detection result from coarse to fine by exploiting the intrinsic peculiarity of the hyperbolic tangent function. The experimental results demonstrate that our proposed method consistently performed better than previous state-of-the-art methods.
关键词： Defocus blur,PCA,local sharpness metric,ConvNets,feature learning
更新于2025-09-10 09:29:36