- 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 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 - An Adaptation of Cnn for Small Target Detection in the Infrared
摘要： Due to the low signal to noise ratio and limited spatial resolution, small target detection in an infrared image is a challenging task. Existing methods often have high false alarm rates and low probabilities of detection when infrared small targets submerge in the background clutter. In this paper, the Convolutional Neural Network (CNN) is adapted to extract the hidden features of small targets from infrared imagery with a proposed technique for a large amount of training data generation. The Point Spread Function (PSF) is employed to model the small target data and generate positive samples. The random background image patches are selected as the negative samples. In this way, the detection problem is skillfully converted into a problem of pattern classification using CNN. Extensive synthetic and real small targets were tested to evaluate the performance of this novel small target detection framework. The experimental results indicate that the proposed algorithm is simple and effective with satisfactory detection accuracy.
关键词： Infrared image (IR),Convolutional Neural Network (CNN),Point Spread Function (PSF),small target 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 - Barrage Jamming Detection and Classification Based on Convolutional Neural Network for Synthetic Aperture Radar
摘要： Suppression technology of barrage jamming is an important approach to ensure the normal operation of the synthetic aperture radar (SAR) system. The detection and classification of jamming is a necessary procedure in this technology. Unsuitable thresholds set in the traditional methods may reduce the detection accuracy. In order to avoid it, this paper proposes a new method of barrage jamming detection and classification for SAR based on convolutional neural network (CNN). The signal model is constructed based on the statistical characteristics of the SAR echo signal. Based on this, a data set containing echo signals and interference signals is generated by simulation. Finally, the convolution neural network VGG16 is used to detect whether the signals in the dataset is contaminated by barrage jamming and identify the type of the interference. The experiment result illustrates that the VGG16 network trained by the frequency domain signals can effectively detect and classify the jamming signals.
关键词： convolutional neural network,jamming detection,VGG16,Barrage jamming
更新于2025-09-10 09:29:36
-
Joint residual pyramid for joint image super-resolution
摘要： Joint image super-resolution refers to methods to enhance the resolution of an image with the guidance of a higher resolution image. It is similar to image completion, which is shown to benefit from larger receptive fields in recent deep neural network based methods. However, larger receptive fields increase the depths and parameters of the network, which may cause degradation and large memory consumption. To this end, we propose a joint residual pyramid model by introducing residual blocks and linear interpolation layers into the convolutional neural pyramid (CNP), and adopting the CNP in the joint super-resolution framework. Our model consists of three sub-networks, two for feature extraction concatenated by another for image reconstruction. Experimental results show that our model outperforms existing state-of-the-art algorithms not only on data pairs of RGB/depth images, but also on data pairs like color/saliency and color-scribbles/colorized images, without significantly sacrificing computation efficiency and memory space.
关键词： Neural convolutional pyramid,Residual block,Deep learning,Joint super-resolution
更新于2025-09-10 09:29:36
-
Stereoscopic Image Quality Assessment by Deep Convolutional Neural Network
摘要： In this paper, we propose a no-reference (NR) quality assessment method for stereoscopic images by deep convolutional neural network (DCNN). Inspired by the internal generative mechanism (IGM) in the human brain, which shows that the brain first analyzes the perceptual information and then extract effective visual information. Meanwhile, in order to simulate the inner interaction process in the human visual system (HVS) when perceiving the visual quality of stereoscopic images, we construct a two-channel DCNN to evaluate the visual quality of stereoscopic images. First, we design a Siamese Network to extract high-level semantic features of left- and right-view images for simulating the process of information extraction in the brain. Second, to imitate the information interaction process in the HVS, we combine the high-level features of left- and right-view images by convolutional operations. Finally, the information after interactive processing is used to estimate the visual quality of stereoscopic image. Experimental results show that the proposed method can estimate the visual quality of stereoscopic images accurately, which also demonstrate the effectiveness of the proposed two-channel convolutional neural network in simulating the perception mechanism in the HVS.
关键词： convolutional neural network,Image quality assessment,no reference,stereoscopic images
更新于2025-09-10 09:29:36
-
A multistandard and resource-efficient Viterbi decoder for a multimode communication system
摘要： We present a novel standard convolutional symbols generator (SCSG) block for a multi-parameter reconfigurable Viterbi decoder to optimize resource consumption and adaption of multiple parameters. The SCSG block generates all the states and calculates all the possible standard convolutional symbols corresponding to the states using an iterative approach. The architecture of the Viterbi decoder based on the SCSG reduces resource consumption for recalculating the branch metrics and rearranging the correspondence between branch metrics and transition paths. The proposed architecture supports constraint lengths from 3 to 9, code rates of 1/2, 1/3, and 1/4, and fully optional polynomials. The proposed Viterbi decoder has been implemented on the Xilinx XC7VX485T device with a high throughput of about 200 Mbps and a low resource consumption of 162k logic gates.
关键词： Multi-parameter,Reconfigurable Viterbi decoder,Low resource consumption,Standard convolutional symbols generator (SCSG),Fully optional polynomials
更新于2025-09-10 09:29:36
-
Stereoscopic Image Super-Resolution Method with View Incorporation and Convolutional Neural Networks
摘要： Super-resolution (SR) plays an important role in the processing and display of mixed-resolution (MR) stereoscopic images. Therefore, a stereoscopic image SR method based on view incorporation and convolutional neural networks (CNN) is proposed. For a given MR stereoscopic image, the left view of which is observed in full resolution, while the right view is viewed in low resolution, the SR method is implemented in two stages. In the first stage, a view difference image is defined to represent the correlation between views. It is estimated by using the full-resolution left view and the interpolated right view as input to the modified CNN. Accordingly, a high-precision view difference image is obtained. In the second stage, to incorporate the estimated right view in the first stage, a global reconstruction constraint is presented to make the estimated right view consistent with the low-resolution right view in terms of the MR stereoscopic image observation model. Experimental results demonstrated that, compared with the SR convolutional neural network (SRCNN) method and depth map based SR method, the proposed method improved the reconstructed right view quality by 0.54 dB and 1.14 dB, respectively, in the Peak Signal to Noise Ratio (PSNR), and subjective evaluation also implied that the proposed method produced better reconstructed stereoscopic images.
关键词： view difference,mixed-resolution stereoscopic image,super-resolution,convolutional neural networks,stereoscopic imaging and coding
更新于2025-09-10 09:29:36
-
[Lecture Notes in Computer Science] Intelligence Science and Big Data Engineering Volume 11266 (8th International Conference, IScIDE 2018, Lanzhou, China, August 18–19, 2018, Revised Selected Papers) || Infrared-Visible Image Fusion Based on Convolutional Neural Networks (CNN)
摘要： Image fusion is a process of combing multiple images of the same scene into a single image with the aim of preserving the full content information and retaining the important features from each of the original images. In this paper, a novel image fusion method based on Convolutional Neural Networks (CNN) and saliency detection is proposed. Here, we use the image representations derived from CNN Network optimized for infrared-visible image fusion. Since the lower layers of the network can seize the exact value of the original image, and the high layers of the network can capture the high-level content in terms of objects and their arrangement in the input image, we exploit more low-layer features of visible image and more high-layer features of infrared image in the fusion. And during the fusion procedure, the infrared target of an infrared image is effectively highlighted using saliency detection method and only the salient information of the infrared image will be fused. The method aimed to preserve the abundant detail information from visible image as much as possible, meanwhile preserve the salient information in the infrared image. Experimental results show that the proposed fusion method is rather promising.
关键词： Image fusion,Saliency detection,Convolutional Neural Networks (CNN)
更新于2025-09-10 09:29:36
-
Free-Space Detection with Self-Supervised and Online Trained Fully Convolutional Networks
摘要： Recently, vision-based Advanced Driver Assist Systems have gained broad interest. In this work, we investigate free-space detection, for which we propose to employ a Fully Convolutional Network (FCN). We show that this FCN can be trained in a self-supervised manner and achieve similar results compared to training on manually annotated data, thereby reducing the need for large manually annotated training sets. To this end, our self-supervised training relies on a stereo-vision disparity system, to automatically generate (weak) training labels for the color-based FCN. Additionally, our self-supervised training facilitates online training of the FCN instead of offline. Consequently, given that the applied FCN is relatively small, the free-space analysis becomes highly adaptive to any traffic scene that the vehicle encounters. We have validated our algorithm using publicly available data and on a new challenging benchmark dataset that is released with this paper. Experiments show that the online training boosts performance with 5% when compared to offline training, both for Fmax and AP.
关键词： Self-supervised training,Fully Convolutional Network,Advanced Driver Assist Systems,Online training,Free-space detection
更新于2025-09-10 09:29:36
-
Classification via weighted kernel CNN: application to SAR target recognition
摘要： The conventional convolutional neural network (CNN) has proven to be effective for synthetic aperture radar (SAR) target recognition. However, the relationship between different convolutional kernels is not taken into account. The lack of the relationship limits the feature extraction capability of the convolutional layer to a certain extent. To address this problem, this paper presents a novel method named weighted kernel CNN (WKCNN). WKCNN integrates a weighted kernel module (WKM) into the common CNN architecture. The WKM is proposed to model the interdependence between different kernels, and thus to improve the feature extraction capability of the convolutional layer. The WKM consists of variables and activations. The variable represents the weight of the convolutional kernel. The activation is a mapping function which is used to determine the range of the weight. To adjust the variable adaptively, back propagation (BP) algorithm for the WKM is derived. The training of the WKM is driven by optimizing the cost function according to the BP algorithm, and three training modes are presented and analysed. SAR target recognition experiments are conducted on the moving and stationary target acquisition and recognition (MSTAR) dataset, and the results show the superiority of the proposed method.
关键词： SAR target recognition,weighted kernel module,convolutional neural network,back propagation algorithm,MSTAR dataset
更新于2025-09-10 09:29:36
-
Development of deep learning architecture for automatic classification of outdoor mobile LiDAR data
摘要： This paper proposes a deep convolutional neural network (CNN) architecture for automatic classification of mobile laser scanning (MLS) data obtained for outdoor environment, which are characterized by noise, clutter, large size and larger quantum of information. The developed architecture introduces a look up table (LUT) based approach, which retains the geometry of the input MLS point cloud while rescaling. Further, with the voxelisation of the input MLS sample, the ambiguity of selecting one out of multiple point values within a voxel is resolved. The performance of the architecture is evaluated on MLS data of outdoor environment in two instances, first using tree and non-tree classes (non-tree class has objects like electric pole, wire, low vegetation, wall, house and ground) and then with tree and electric pole classes. Additional testing is carried out by mixing the outdoor MLS data of tree and electric pole classes with three classes of indoor objects, taken from Modelnet dataset, thereby assessing the architecture efficacy over an ensemble of three-dimensional (3D) datasets. Classification of tree and non-tree classes, followed by tree and electric pole classes from MLS samples result in total accuracies of 86.0%, 90.0% respectively and kappa values of 72.0%, 78.7% respectively. Moreover, for the combinations of MLS and Modelnet classes, the classification results are promising, reaching a total accuracy of 95.2% and kappa of 92.5%. The LUT based approach has shown better classification over the traditional rescaling approach for the MLS dataset, resulting in an enhancement up to 9.0% and 18.0% in total accuracy and kappa, respectively. With different varieties of tree, non-tree and electric pole samples, the proposed architecture has shown its potential for automatic classification of MLS data with high accuracy. This study further reveals that the accuracy of classification is improved by introducing more spatial features in the input layer. The accuracies produced in this work can be further improved with the availability of better hardware resources.
关键词： outdoor environment,deep learning,mobile laser scanning,point cloud,convolutional neural network,classification
更新于2025-09-10 09:29:36