- 标题
- 摘要
- 关键词
- 实验方案
- 产品
过滤筛选
- 2019
- 2018
- pattern recognition
- image
- partial discharge
- convolutional neural network(CNN)
- Conditional Random Fields (CRF)
- Convolutional Neural Network (CNN)
- Fine Classification
- Airborne hyperspectral
- green tide
- Elegant End-to-End Fully Convolutional Network (E3FCN)
- Optoelectronic Information Science and Engineering
- Shanghai Jiao Tong University
- Ocean University of China
- University of Oulu
- Wuhan University
- Central South University
- Hubei University
-
[IEEE 2018 IEEE 3rd International Conference on Image, Vision and Computing (ICIVC) - Chongqing (2018.6.27-2018.6.29)] 2018 IEEE 3rd International Conference on Image, Vision and Computing (ICIVC) - Change Detection Based on the Combination of Improved SegNet Neural Network and Morphology
摘要： Through the analysis of satellite remote sensing image data, the identification of newly added buildings in the same area can be realized to judge the use of land. The identification of newly added buildings based on remote sensing images, involving image object extraction, semantic segmentation and change detection. The difficulty is not only to identify the changes of remote sensing images in different periods, but also to identify the newly added buildings with the original buildings. Both of the recognition effect and the detection precision of the traditional method based on mathematical modeling need to be improved. SegNet neural network is a kind of deep convolution neural network. It shows good performance in dealing with the task of semantic segmentation of single image, but it is directly applied to building change detection with low accuracy. The simulation results show that the improved SegNet neural network method improves the accuracy of the quantitative evaluation index F1 score by 8.6% compared with the conventional SegNet network in the newly added building detection effect in the same area in 2015 and 2017. In addition, the situation that the change detection result will produce a large number of noise, a combination of improved SegNet network and morphological method is adopted to eliminate the noise and reduce the misjudgment. The simulation results show that the F1 index increased further by 1.4% on the basis of 8.6%.
关键词： convolutional neural network,deep learning,remote sensing images,building change detection,morphology
更新于2025-09-09 09:28:46
-
[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) - Fully convolutional network and graph-based method for co-segmentation of retinal layer on macular OCT images
摘要： Retinal layer segmentation in optical coherence tomography (OCT) images is crucial for the diagnosis and study of retinal diseases. Graph-based methods are commonly used in layer segmentation. However, most of these methods require a lot of human efforts for determining an appropriate model to compute good edge weights. In this paper, we propose a novel automatic method for segmenting retinal layers in macular OCT images. Specially, we propose a new fully convolutional deep learning architecture with a side output layer to directly learn optimal graph-edge weights from raw pixels. The architecture can automatically learn multi-scale and multi-level features to generate accurate boundary probabilities as good edge weights without hand-crafted appropriate models. The boundaries are finalized by using graph segmentation method. The proposed method is evaluated on a dataset with 130 OCT B-scans. The experimental results show the mean absolute boundary positioning differences are 1.48±0.34 pixel.
关键词： fully convolutional network,retinal layer segmentation,graph-based framework,Optical coherence tomography (OCT)
更新于2025-09-09 09:28:46
-
[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) - Improving Image Classification Performance with Automatically Hierarchical Label Clustering
摘要： Image classi?cation is a common and foundational problem in computer vision. In traditional image classi?cation, a category is assigned with single label, which is dif?cult for networks to learn better features. On the contrary, hierarchical labels can depict the structure of categories better, which helps network to learn more hierarchical features and improve the classi?cation performance. Though many datasets contain images with multi-labels, the labels in these datasets usually lack of hierarchy. To overcome this problem, we propose a new method to improve image classi?cation performance with Automatically Hierarchical Label Clustering (AHLC). Firstly, AHLC calculates the similarity between each pair of original categories by how easily they are misclassi?ed with a pre-trained classi?er. Secondly, AHLC obtains hierarchical labels by merging similar categories using hierarchical clustering. Finally, AHLC trains a new classi- ?er with hierarchial labels to improve the original classi?cation performance. We evaluate our method on MNIST and CIFAR-100 datasets and the results demonstrate the superiority of our method. The main contribution of this work is that we can simply improve an existing classi?cation network by AHLC without extra information or heavy architecture redesign.
关键词： hierarchical labels,AHLC,Image classification,deep learning,convolutional neural networks
更新于2025-09-09 09:28:46
-
[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) - Lightweight Deep Residue Learning for Joint Color Image Demosaicking and Denoising
摘要： Color demosaicking and image denoising each plays an important role in digital cameras. Conventional model-based methods often fail around the areas of strong textures and produce disturbing visual artifacts such as aliasing and zippering. Recently developed deep learning based methods were capable of obtaining images of better qualities though at the price of high computational cost, which make them not suitable for real-time applications. In this paper, we propose a lightweight convolutional neural network for joint demosaicking and denoising (JDD) problem with the following salient features. First, the densely connected network is trained in an end-to-end manner to learn the mapping from the noisy low-resolution space (CFA image) to the clean high-resolution space (color image). Second, the concept of deep residue learning and aggregated residual transformations are extended from image denoising and classification to JDD supporting more efficient training. Third, the design of our end-to-end network architecture is inspired by a rigorous analysis of JDD using sparsity models. Experimental results conducted for both demosaicking-only and JDD tasks have shown that the proposed method performs much better than existing state-of-the-art methods (i.e., higher visual quality, smaller training set and lower computational cost).
关键词： Convolutional neural network,Joint demosaicking and denoising,Residue Learning
更新于2025-09-09 09:28:46
-
[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) - A Novel Model for Multi-label Image Annotation
摘要： Multi-label image annotation is one of the most important open problems in machine learning and computer vision. In this paper, we propose a novel model for image annotation. Unlike existing works that usually use conventional visual features to annotate images, this paper adopts features based on convolutional neural network (CNN), which have shown potential to achieve outstanding performance. In particular, we use CNN to extract image features with higher semantic meaning and apply them to the image annotation method – Tag Propagation (TagProp). Experimental results on four challenging datasets indicate that our model makes a marked improvement as compared to the current state-of-the-art.
关键词： image annotation,convolutional neural network,Multi-label learning,Tag Propagation
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 - Urban Land Use/Land Cover Classification Based on Feature Fusion Fusing Hyperspectral Image and Lidar Data
摘要： Hyperspectral images have been widely used in classification because of the abundant spectral information. But it can’t distinguish the objective with similar spectral character but different elevation. However, LiDAR data can obtain elevation information. Therefore, it will obtain better classification maps if fusing the two data. In recent years, CNN has attracted much attention due to its powerful ability to excavate the potential representation and features of the raw data. However, it’s difficult to distinguish the objects with different spectral information but similar surface character. Unlike CNN features, the traditional manual features, such as the normalized vegetation index (NDVI), have a certain characteristic expression significance. In order to consider both the semantic information of traditional manual features and the advanced features of CNN features, this paper proposes a fusion algorithm of hyperspectral and LiDAR fusion based on feature fusion. The proposed algorithm has achieved a good fusion classification effect on the MUUFL Gulfport Hyperspectral and LiDAR Data set.
关键词： convolutional neural network,land-use/land-cover classification,Hyperspectral,deep learning,feature fusion,LIDAR
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 - A CNN-Based Fusion Method for Super-Resolution of Sentinel-2 Data
摘要： Sentinel-2 data represent a rich source of information for the community due to the free access and to the temporal-spatial coverage assured. However, some of the spectral bands are sensed at reduced resolution due to a compromise between technological limitations and Copernicus program's objectives. For this reason in this work we present a new super-resolution method based on Convolutional Neural Networks (CNNs) to rise the resolution of the shortwave infra-red (SWIR) band from 20 to 10 meters, that is the highest resolution provided. This is accomplished by fusing the target band with the finer-resolution ones. The proposed solution compares favourably against several alternative methods according to different quality indexes. In addition we have also tested the use of the super-resolved band from an applicative perspective by detecting water basins through the Modified Normalized Difference Water Index (MNDWI).
关键词： convolutional neural network,Deep learning,Sentinel-2,pansharpening,normalized difference water index
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
-
[IEEE 2018 37th Chinese Control Conference (CCC) - Wuhan (2018.7.25-2018.7.27)] 2018 37th Chinese Control Conference (CCC) - Real-Time Fire Detection Based on Deep Convolutional Long-Recurrent Networks and Optical Flow Method
摘要： A new ?re monitoring method was proposed in this paper, which proposed a Neural Network of Deep Convolutional Long-Recurrent Networks (DCLRN), and combining DCLRN network and optical ?ow method for ?re monitoring in open space environment in real time. This is achieved by utilizing the static and dynamic characteristics of the ?re, converting ?re RGB images to optical ?ow images in real-time, and use convolutional neural network for spatial learning, a class of recurrent convolutional architectures for sequence learning, eventually achieve the purpose of ?re monitoring. Which is end-to-end trainable and suitable for large-scale visual understanding tasks of ?re monitoring. Our novelties are: ?rstly, our method is the ?rst to our knowledge to put forward DCLRN, and combining DCLRN with optical ?ow method for ?re monitoring. Secondly, our method has the ability that can detect the smoke as well as the ?ames. Finally, in this way the ?re can be detected as soon as it occurs, achieved early detection of ?re. The experiments have proved that DCLRN combined with optical ?ow images have good accuracy and reliability in the detection and recognition of ?re monitoring videos, and give good performance on a more challenging dataset.
关键词： sequence learning,optical ?ow method,Fire monitoring,Deep Convolutional Long-Recurrent Networks
更新于2025-09-09 09:28:46