- 标题
- 摘要
- 关键词
- 实验方案
- 产品
-
[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 - Self-Supervised Learning for Stereo Reconstruction on Aerial Images
摘要： Recent developments established deep learning as an inevitable tool to boost the performance of dense matching and stereo estimation. On the downside, learning these networks requires a substantial amount of training data to be successful. Consequently, the application of these models outside of the laboratory is far from straightforward. In this work we propose a self-supervised training procedure that allows us to adapt our network to the specific (imaging) characteristics of the dataset at hand, without the requirement of external ground truth data. We instead generate interim training data by running our intermediate network on the whole dataset, followed by conservative outlier filtering. Bootstrapped from a pre-trained version of our hybrid CNN-CRF model, we alternate the generation of training data and network training. With this simple concept we are able to lift the completeness and accuracy of the pre-trained version significantly. We also show that our final model compares favorably to other popular stereo estimation algorithms on an aerial dataset.
关键词： CNN,dense matching,large scale 3D
更新于2025-09-10 09:29:36
-
Convolutional Neural Network Based Feature Extraction for IRIS Recognition
摘要： Iris is a powerful tool for reliable human identification. It has the potential to identify individuals with a high degree of assurance. Extracting good features is the most significant step in the iris recognition system. In the past, different features have been used to implement iris recognition system. Most of them are depend on hand-crafted features designed by biometrics specialists. Due to the success of deep learning in computer vision problems, the features learned by the Convolutional Neural Network (CNN) have gained much attention to be applied for iris recognition system. In this paper, we evaluate the extracted learned features from a pre-trained Convolutional Neural Network (Alex-Net Model) followed by a multi-class Support Vector Machine (SVM) algorithm to perform classification. The performance of the proposed system is investigated when extracting features from the segmented iris image and from the normalized iris image. The proposed iris recognition system is tested on four public datasets IITD, iris databases CASIA-Iris-V1, CASIA-Iris-thousand and, CASIA-Iris- V3 Interval. The system achieved excellent results with the very high accuracy rate.
关键词： Iris,Recognition,Feature extraction (FE),Convolutional Neural Network (CNN),Deep learning,Biometrics
更新于2025-09-10 09:29:36
-
[IEEE 2018 IEEE 20th International Conference on e-Health Networking, Applications and Services (Healthcom) - Ostrava, Czech Republic (2018.9.17-2018.9.20)] 2018 IEEE 20th International Conference on e-Health Networking, Applications and Services (Healthcom) - Deep Learning Based Automated Extraction of Intra-Retinal Layers for Analyzing Retinal Abnormalities
摘要： Extraction of retinal layers from optical coherence tomography (OCT) scans is critical for analyzing retinal anomalies and manual segmentation of these retinal layers is a very cumbersome task. Recently, deep learning has gained much popularity in medical image analysis due to its underlying precision and robustness. Many researchers have utilized deep learning for extracting retinal layers from OCT images. However, to the best of our knowledge, there is no literature available that presents a robust segmentation framework that is able to extract retinal layers from OCT scans having different retinal pathological syndromes. Therefore, this paper presents a deep convolutional neural network and structure tensor-based segmentation framework (CNN-STSF) for the fully automated segmentation of up to eight retinal layers from normal as well as diseased OCT scans. First of all, the proposed framework computes coherent tensor from the candidate scan through which retinal layers are extracted. Afterwards, the pixels representing the layers are further classified using cloud based deep convolutional neural network (CNN) model trained on 1,200 retinal layers patches. CNN model in the proposed framework computes the probability of each layer pixels and assign it to be part of that layer for which it has the highest probability. The proposed framework was tested and validated on more than 39,000 retinal OCT scans from different publicly available datasets and from local Armed Forces Institute of Ophthalmology (AFIO) dataset where it outperformed all the existing solutions by achieving the overall layer segmentation accuracy of 0.9375.
关键词： Transfer learning,Convolutional neural network (CNN),Deep learning,AlexNet
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 - Deconv R-CNN for Small Object Detection on Remote Sensing Images
摘要： Small object detection has drawn increasing interest in computer vision and remote sensing image processing. The Region Proposal Network (RPN) methods (e.g., Faster R-CNN) have obtained promising detection accuracy with several hundred proposals. However, due to the pooling layers in the network structure of the deep model, precise localization of small-size object is still a hard problem. In this paper, we design a network with a deconvolution layer after the last convolution layer of base network for small target detection. We call our model DeconvR-CNN. In the experiment on a remote sensing image dataset, DeconvR-CNN reaches a much higher mean average precision (mAP) than Faster R-CNN.
关键词： Object detection,Small object,Convolutional neural network,R-CNN,Deconvolution
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 - Flooded Area Detection from Uav Images Based on Densely Connected Recurrent Neural Networks
摘要： The emergence of small unmanned aerial vehicles (UAV) along with inexpensive sensors presents the opportunity to collect thousands of images after each natural disaster with high flexibility and easy maneuverability for rapid response and recovery. Despite the ease of data collection, data analysis of the big datasets remains a significant barrier for scientists and analysts. Here we propose an integration of densely connected CNN and RNN networks, which is able to accurately segment out semantically meaningful object boundaries with end-to-end learning. The proposed network is applied on UAV aerial images of flooded areas in Houston, TX. We achieved 96% accuracy in detecting flooded areas on a large UAV dataset.
关键词： semantic segmentation,RNN,flooded area detection,UAV,CNN
更新于2025-09-09 09:28:46
-
[IEEE 2018 37th Chinese Control Conference (CCC) - Wuhan (2018.7.25-2018.7.27)] 2018 37th Chinese Control Conference (CCC) - Target Detection of Hyperspectral Image Based on Convolutional Neural Networks
摘要： Convolutional neural networks (CNN) has been applied in image classification and target detection successfully, however, it is rarely introduced to the field of hyperspectral image (HSI) target detection. Therefore, in this paper, a hyperspectral image (HSI) target detection method based on CNN is proposed. Firstly, the raw HSI data is preprocessed and the spectral information could be obtained. Secondly, to extract the feature information, a CNN is trained and the parameters of the network are adjusted according to a HSI. Finally, the targets will be calibrated according to the extracted features. To estimate the target detection performance of the proposed method, deep belief network (DBN) and SVM methods are compared in the experiment of the real world AVIRIS HSI experiment. Numerical results show that the proposed method has promising prospect in the field of HSI target detection.
关键词： Target recognition,Remote sensing image,DBN,Deep learning,CNN
更新于2025-09-09 09:28:46
-
[IEEE 2018 International Symposium ELMAR - Zadar, Croatia (2018.9.16-2018.9.19)] 2018 International Symposium ELMAR - Bright Lesions Detection on Retinal Images by Convolutional Neural Network
摘要： This paper is focused on automatic detection and classification of diabetic retinopathy symptoms, more specifically on the bright lesions (soft and hard exudates) as one of the primary signs suitable for diabetic retinopathy screening. We use a convolutional neural network (CNN) for bright lesions detection and evaluate achieved results using criterion based on proper comparison of each lesion with ground truth images scored by the ophthalmologist. As input data we use original and geometrically transformed retinal images from Messidor database divided into smaller blocks. In that way we enlarge the training dataset and increase classification accuracy.
关键词： Soft and hard exudates classification,Evaluation method,Retinal image,CNN,Messidor database
更新于2025-09-09 09:28:46
-
[IEEE 2018 Condition Monitoring and Diagnosis (CMD) - Perth, WA (2018.9.23-2018.9.26)] 2018 Condition Monitoring and Diagnosis (CMD) - Pattern Recognition of Partial Discharge Image Based on One-dimensional Convolutional Neural Network
摘要： Big data platforms and centers are ubiquitous today where a large amount of unstructured data on site such as is accumulated. For structured data, partial discharge pattern recognition method has been extensively studied, whereas traditional methods can not be directly applied to unstructured data. To this end, a time-domain waveform pattern recognition method based on one- dimensional convolutional neural network (CNN) is proposed. Image processing techniques are applied to obtain one- dimensional characteristics of the waveform. Based on deep learning, the network is constructed for pattern recognition straight forwardly. Through on site detection and simulation experiments, image data sets of five partial discharge defects are established and comparative experiments are conducted. Experimental results show that the proposed method can successfully perform pattern recognition with applications in work of data mining and data utilization. Under the same complexity, it is also with higher accuracy comparing to two- dimensional CNN. Furthermore, the method autonomously extrapolates features without manual extraction, which achieves low experimental complexity and robustness simultaneously.
关键词： pattern recognition,image,partial discharge,convolutional neural network(CNN)
更新于2025-09-09 09:28:46
-
[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 - Feature Learning For SAR Images Using Convolutional Neural Network
摘要： Convolutional neural network (CNN) has been widely used in many research areas due to its powerful ability of feature learning. In this paper, the powerful ability of feature learning in CNN is explored by constructing a novel convolutional network (ConvNet) for SAR image processing. The proposed ConvNet is firstly trained under classification task, in which effective features can be learned automatically from the training data. Specifically, data argument is adopted to overcome the small-sample-problem in SAR images. When well-trained, the proposed ConvNet can be directly used for feature extraction of other images, even though their classes may be not used in the training. Experimental results on benchmark MSTAR dataset demonstrate that the proposed ConvNet is effective for classification of SAR images, and the features learned from it are more effective than traditional hand-crafted features in SAR image processing.
关键词： Synthetic Aperture Radar (SAR),feature learning,convolutional neural network (CNN),feature extraction,classification
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 SAR Terrain Classification Using 3D Convolutional Neural Network
摘要： Terrain classification is an important application of polarimetric SAR (PolSAR) data. Traditional classification methods need to extract the feature and then classify by classifiers. Besides, it should consider the influence of speckle noise. As a new method for image processing, convolutional neural network (CNN) has attracted more and more attention because of its good performance in image processing. It can deal with the original image directly with a higher classification accuracy without considering the impact of speckle noise. Moreover, three-dimensional convolutional neural network (3D CNN) has stronger feature extraction capability compared with traditional two-dimensional convolutional neural network (2D CNN). In this paper, the application of 3D CNN in terrain classification is studied, in which a new convolutional neural network architecture is designed and the elements of polarimetric coherency matrix are used as the input data of this network. The experiments of two real PolSAR data are conducted to verify the performance of the proposed network.
关键词： terrain classification,three-dimensional convolutional neural network (3D CNN),polarmetric SAR
更新于2025-09-09 09:28:46