- 标题
- 摘要
- 关键词
- 实验方案
- 产品
-
[IEEE 2018 25th IEEE International Conference on Image Processing (ICIP) - Athens, Greece (2018.10.7-2018.10.10)] 2018 25th IEEE International Conference on Image Processing (ICIP) - Light Field Image Compression Based on Convolutional Neural Networks and Linear Approximation
摘要： Computer vision applications such as refocusing, segmentation and classification become one of the most advanced imaging services. LightField (LF) imaging systems provide a rich semantic information of the scene. Using a dense set of cameras and microlens arrays (Plenoptic camera), the direction of each ray coming from the scene toward the LF capture system can be extracted and represented by spatial and angular coordinates. However, such imaging system induces many drawbacks including the large amount of data produced and complexity increase for scene representation. In this paper, we propose an efficient LF image coding scheme. This scheme first encodes a sparse set of views using the latest hybrid video encoder (JEM). Then, it estimates a second sparse set of views using a linear approximation. At the decoder side, we use a Deep Learning (DL) approach to estimate the whole LF image from the reconstructed sparse sets of views. Experimental results show that the proposed scheme provides higher visual quality and overcomes the state of the art LF image compression solution by 30% bitrate gain.
关键词： LightField,MachineLearning,future video coding,Linear approximation,CNN
更新于2025-09-11 14:15:04
-
Unsupervised Feature Extraction in Hyperspectral Images Based on Wasserstein Generative Adversarial Network
摘要： Feature extraction (FE) is a crucial research area in hyperspectral image (HSI) processing. Recently, due to the powerful ability of deep learning (DL) to extract spatial and spectral features, DL-based FE methods have shown great potentials for HSI processing. However, most of the DL-based FE methods are supervised, and the training of them suffers from the absence of labeled samples in HSIs severely. The training issue of supervised DL-based FE methods limits their application on HSI processing. To address this issue, in this paper, a novel modified generative adversarial network (GAN) is proposed to train a DL-based feature extractor without supervision. The designed GAN consists of two components, which are a generator and a discriminator. The generator can focus on the learning of real probability distributions of data sets and the discriminator can extract spatial–spectral features with superior invariance effectively. In order to learn upsampling and downsampling strategies adaptively during FE, the proposed generator and discriminator are designed based on a fully deconvolutional subnetwork and a fully convolutional subnetwork, respectively. Moreover, a novel min–max cost function is designed for training the proposed GAN in an end-to-end fashion without supervision, by utilizing the zero-sum game relationship between the generator and discriminator. Besides, the proposed modified GAN replaces the original Jensen–Shannon divergence with the Wasserstein distance, aiming to mitigate the unstability and difficulty of the training of GAN frameworks. Experimental results on three real data sets validate the effectiveness of the proposed method.
关键词： Convolutional neural network (CNN),hyperspectral images (HSIs),feature extraction (FE),generative adversarial network (GAN)
更新于2025-09-11 14:15:04
-
Deformable Faster R-CNN with Aggregating Multi-Layer Features for Partially Occluded Object Detection in Optical Remote Sensing Images
摘要： The region-based convolutional networks have shown their remarkable ability for object detection in optical remote sensing images. However, the standard CNNs are inherently limited to model geometric transformations due to the fixed geometric structures in its building modules. To address this, we introduce a new module named deformable convolution that is integrated into the prevailing Faster R-CNN. By adding 2D offsets to the regular sampling grid in the standard convolution, it learns the augmenting spatial sampling locations in the modules from target tasks without additional supervision. In our work, a deformable Faster R-CNN is constructed by substituting the standard convolution layer with a deformable convolution layer in the last network stage. Besides, top-down and skip connections are adopted to produce a single high-level feature map of a fine resolution, on which the predictions are to be made. To make the model robust to occlusion, a simple yet effective data augmentation technique is proposed for training the convolutional neural network. Experimental results show that our deformable Faster R-CNN improves the mean average precision by a large margin on the SORSI and HRRS dataset.
关键词： Faster R-CNN,occluded object detection,data augmentation,Deformable CNN
更新于2025-09-10 09:29:36
-
Fully Connected Conditional Random Fields for High-Resolution Remote Sensing Land Use/Land Cover Classification with Convolutional Neural Networks
摘要： The interpretation of land use and land cover (LULC) is an important issue in the fields of high-resolution remote sensing (RS) image processing and land resource management. Fully training a new or existing convolutional neural network (CNN) architecture for LULC classification requires a large amount of remote sensing images. Thus, fine-tuning a pre-trained CNN for LULC detection is required. To improve the classification accuracy for high resolution remote sensing images, it is necessary to use another feature descriptor and to adopt a classifier for post-processing. A fully connected conditional random fields (FC-CRF), to use the fine-tuned CNN layers, spectral features, and fully connected pairwise potentials, is proposed for image classification of high-resolution remote sensing images. First, an existing CNN model is adopted, and the parameters of CNN are fine-tuned by training datasets. Then, the probabilities of image pixels belong to each class type are calculated. Second, we consider the spectral features and digital surface model (DSM) and combined with a support vector machine (SVM) classifier, the probabilities belong to each LULC class type are determined. Combined with the probabilities achieved by the fine-tuned CNN, new feature descriptors are built. Finally, FC-CRF are introduced to produce the classification results, whereas the unary potentials are achieved by the new feature descriptors and SVM classifier, and the pairwise potentials are achieved by the three-band RS imagery and DSM. Experimental results show that the proposed classification scheme achieves good performance when the total accuracy is about 85%.
关键词： remote sensing,fully connected conditional random fields (FC-CRF),image classification,convolutional neural networks (CNN)
更新于2025-09-10 09:29:36
-
[IEEE 2018 IEEE International Conference on Electro/Information Technology (EIT) - Rochester, MI (2018.5.3-2018.5.5)] 2018 IEEE International Conference on Electro/Information Technology (EIT) - A Survey of Traffic Sign Recognition Systems Based on Convolutional Neural Networks
摘要： In this paper, we briefly discuss the applications of Convolutional Neural Networks (CNNs) model to traffic sign recognition (TSR) systems. Traditionally, the TSRs have used different techniques to detect and classify visual data. The CNNs have been used separately to extract features and train the classifier as well as simultaneously for detection and classification tasks. One model that has been successful is the Fast Branch CNN model, which imitates biological mechanisms to become more efficient. While it is not the most accurate of the ones presented in this paper, the efficiency it exhibits under time-sensitive conditions is worth exploring because of the potential applications of such technology. The Fast Branch CNN model challenged the assumptions of past models, and this technology can only advance further if new models attempt to do the same.
关键词： CNN (Convolutional Neural Network),TSR (Traffic Sign Recognition),Classification,Detection
更新于2025-09-10 09:29:36
-
[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 - Small Sample Learning Optimization for Resnet Based Sar Target Recognition
摘要： Deep convolutional neural network (CNN) is an important branch of deep learning. Due to its strong ability of feature extraction, CNN models have been introduced to solve the problems of synthetic aperture radar automatic target recognition (SAR-ATR). However, labeled SAR images are difficult to acquire. Therefore, how to obtain a good recognition result from a small sample dataset is what we mainly focus on. In theory, a deeper network can bring a better training result. But it also brings more difficulties to the training process, especially with limited labeled training data. The residual learning which proposed in recent years can alleviate this problem effectively. In this paper, we use a deep residual network, and introduce the dropout layer into the building block to alleviate overfitting caused by limited SAR data. In order to improve the training effect, the new loss function center loss is adopted and combined with softmax loss as the supervision signal to train the deep CNN. The experimental results show that our method can achieve the classification accuracy of 99.67% with all training data, without data augmentation or pre-training. When data of the training dataset was reduced to 20%, we can still achieve a recognition result higher than 94%.
关键词： center loss,automatic target recognition (ATR),limited labeled data,Convolutional neural network (CNN),synthetic aperture radar (SAR),residual learning
更新于2025-09-10 09:29:36
-
[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 - Convolutional Neural Networks for Cloud Screening: Transfer Learning from Landsat-8 to Proba-V
摘要： Cloud detection is a key issue for exploiting the information from Earth observation satellites multispectral sensors. For Proba-V, cloud detection is challenging due to the limited number of spectral bands. Advanced machine learning methods, such as convolutional neural networks (CNN), have shown to work well on this problem provided enough labeled data. However, simultaneous collocated information about the presence of clouds is usually not available or requires a great amount of manual labor. In this work, we propose to learn from the available Landsat-8 cloud masks datasets and transfer this learning to solve the Proba-V cloud detection problem. CNN are trained with Landsat images adapted to resemble Proba-V characteristics and tested on a large set of real Proba-V scenes. Developed models outperform current operational Proba-V cloud detection without being trained with any real Proba-V data. Moreover, cloud detection accuracy can be further increased if the CNN are fine-tuned using a limited amount of Proba-V data.
关键词： Proba-V,Transfer Learning,CNN,Cloud detection,Domain Adaptation,Landsat-8
更新于2025-09-10 09:29:36
-
[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
-
[IEEE 2018 25th IEEE International Conference on Image Processing (ICIP) - Athens, Greece (2018.10.7-2018.10.10)] 2018 25th IEEE International Conference on Image Processing (ICIP) - Macro-Pixel Prediction Based on Convolutional Neural Networks for Lossless Compression of Light Field Images
摘要： The paper introduces a novel macro-pixel prediction method based on Convolutional Neural Networks (CNN) for lossless compression of light field images. In the proposed method, each macro-pixel is predicted based on a volume of macro-pixels from its immediate causal neighborhood. The proposed deep neural network operates on these macro-pixel volumes and provides accurate macro-pixel prediction in light field images. The resulting macro-pixel residuals are encoded by a reference codec built based on the CALIC codec. A context modeling method for light field images is proposed. Experimental results on a large light field image dataset show that the proposed prediction method systematically and substantially outperforms state-of-the-art predictors. To our knowledge, the paper is the first to introduce deep-learning based prediction of macro-pixels, enabling efficient lossless compression of light field images.
关键词： CNN-based prediction,Intraprediction,lossless compression,macro-pixel,light field images
更新于2025-09-10 09:29:36
-
[IEEE 2018 International Joint Conference on Neural Networks (IJCNN) - Rio de Janeiro (2018.7.8-2018.7.13)] 2018 International Joint Conference on Neural Networks (IJCNN) - Identification of thyroid nodules in infrared images by convolutional neural networks
摘要： Early detection of thyroid anomalies decreases the chances of disease progression. Imaging examinations consist in an important tool in the diagnostic process. However, most of them are relatively expensive or can expose the patient to excessive radiation. Thermography is an interesting alternative in thyroid diseases diagnosis, especially in the detection of nodules, since some of them tend to present higher temperatures than normal tissues. Image processing techniques can be used to find regions that may indicate thyroid nodules. To select which one of these regions are in fact related to a nodule, a Convolutional Neural Network - CNN can be used. CNNs are widely used in clinical images classification, and some models have shown good results in this kind of problem. In this work, we present a methodology to identify thyroid nodules in thermograms by using simple image processing techniques and CNNs. Three CNNs were tested, the first one based in the GoogLeNet architecture, a second based in the AlexNet and a third one based in the VGG architecture. The GoogLeNet CNN yielded the highest accuracy (86.22%) followed by AlexNet (77.67%) and the VGG (74.96%).
关键词： Imaging examination,Convolutional Neural Networks - CNN,Image classification
更新于2025-09-10 09:29:36