- 标题
- 摘要
- 关键词
- 实验方案
- 产品
-
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
-
Semisupervised Scene Classification for Remote Sensing Images: A Method Based on Convolutional Neural Networks and Ensemble Learning
摘要： The scarcity of labeled samples has been the main obstacle to the development of scene classification for remote sensing images. To alleviate this problem, the efforts have been dedicated to semisupervised classification which exploits both labeled and unlabeled samples for training classifiers. In this letter, we propose a novel semisupervised method that utilizes the effective residual convolutional neural network (ResNet) to extract preliminary image features. Moreover, the strategy of ensemble learning (EL) is adopted to establish discriminative image representations by exploring the intrinsic information of all available data. Finally, supervised learning is performed for scene classification. To verify the effectiveness of the proposed method, it is further compared with several state-of-the-art feature representation and semisupervised classification approaches. The experimental results show that by combining ResNet features with EL, the proposed method can obtain more effective image representations and achieve superior results.
关键词： remote sensing (RS) images,Semi-supervised classification,ensemble learning (EL),scene classification,Convolutional neural networks (CNNs)
更新于2025-09-23 15:23:52
-
A Sample Update-Based Convolutional Neural Network Framework for Object Detection in Large-Area Remote Sensing Images
摘要： This letter addresses the issue of accurate object detection in large-area remote sensing images. Although many convolutional neural network (CNN)-based object detection models can achieve high accuracy in small image patches, the models perform poorly in large-area images due to the large quantity of false and missing detections that arise from complex backgrounds and diverse groundcover types. To address this challenge, this letter proposes a sample update-based CNN (SUCNN) framework for object detection in large-area remote sensing images. The proposed framework contains two stages. In the first stage, a base model—single-shot multibox detector—is trained with the training data set. In the second stage, artificial composite samples are generated to update the training set. The parameters of the first-stage model are fine-tuned with the updated data set to obtain the second-stage model. The first- and second-stage models are evaluated using the large-area remote sensing image test set. Comparison experiments show the effectiveness and superiority of the proposed SUCNN framework for object detection in large-area remote sensing images.
关键词： large-area remote sensing images,sample update,object detection,Convolutional neural networks (CNNs)
更新于2025-09-23 15:22:29
-
Ship Classification in High-Resolution SAR Images via Transfer Learning with Small Training Dataset
摘要： Synthetic aperture radar (SAR) as an all-weather method of the remote sensing, now it has been an important tool in oceanographic observations, object tracking, etc. Due to advances in neural networks (NN), researchers started to study SAR ship classification problems with deep learning (DL) in recent years. However, the limited labeled SAR ship data become a bottleneck to train a neural network. In this paper, convolutional neural networks (CNNs) are applied to ship classification by using SAR images with the small datasets. To solve the problem of over-fitting which often appeared in training small dataset, we proposed a new method of data augmentation and combined it with transfer learning. Based on experiments and tests, the performance is evaluated. The results show that the types of the ships can be classified in high accuracies and reveal the effectiveness of our proposed method.
关键词： ship classification,deep learning (DL),convolutional neural networks (CNNs),synthetic aperture radar (SAR)
更新于2025-09-23 15:22:29
-
A High-Performance Deep Learning Algorithm for the Automated Optical Inspection of Laser Welding
摘要： The battery industry has been growing fast because of strong demand from electric vehicle and power storage applications.Laser welding is a key process in battery manufacturing. To control the production quality, the industry has a great desire for defect inspection of automated laser welding. Recently, Convolutional Neural Networks (CNNs) have been applied with great success for detection, recognition, and classi?cation. In this paper, using transfer learning theory and pre-training approach in Visual Geometry Group (VGG) model, we proposed the optimized VGG model to improve the e?ciency of defect classi?cation. Our model was applied on an industrial computer with images taken from a battery manufacturing production line and achieved a testing accuracy of 99.87%. The main contributions of this study are as follows: (1) Proved that the optimized VGG model, which was trained on a large image database, can be used for the defect classi?cation of laser welding. (2) Demonstrated that the pre-trained VGG model has small model size, lower fault positive rate, shorter training time, and prediction time; so, it is more suitable for quality inspection in an industrial environment. Additionally, we visualized the convolutional layer and max-pooling layer to make it easy to view and optimize the model.
关键词： defect classi?cation,optimized VGG model,laser welding,convolutional neural networks (CNNs),automatic optical inspection
更新于2025-09-23 15:19:57
-
[IEEE 2019 International Conference on Internet of Things (iThings) and IEEE Green Computing and Communications (GreenCom) and IEEE Cyber, Physical and Social Computing (CPSCom) and IEEE Smart Data (SmartData) - Atlanta, GA, USA (2019.7.14-2019.7.17)] 2019 International Conference on Internet of Things (iThings) and IEEE Green Computing and Communications (GreenCom) and IEEE Cyber, Physical and Social Computing (CPSCom) and IEEE Smart Data (SmartData) - Tropical Cyclone Maximum Wind Estimation from Infrared Satellite Data with Integrated Convolutional Neural Networks
摘要： Tropical cyclone (TC) maximum wind is an important parameter for estimating TC risks such as wind potential damage and storm surge. Previous work has shown that the estimation of TC maximum wind through a series of empirical rules based on the cloud characteristics shown in the satellite cloud image. Deep learning like convolutional neural networks (CNNs) has this ability of extracting and understanding these cloud features like the eye, the spiral rainbands that closely associated with its maximum wind. However, CNNs are used for object recognition and classification, CNS has less application in regression. We proposed an integrated architecture based on Convolutional Neural Network for the estimation of the TC maximum wind with higher accuracy. More specifically, it includes input layer, convolutional layers, activation functions and pooling layers for training and capturing non-linear relationships between cloud image and its wind, and a fully connection for the estimation task. We evaluate the state of the art for regression between infrared image and its TC maximum wind, discussing the necessity of different components. It demonstrates an improvement on the ability to estimate the TC intensity.
关键词： infrared cloud image,Convolutional Neural Networks (CNNs),TC Maximum wind
更新于2025-09-16 10:30:52
-
Ensemble of Multi-View Learning Classifiers for Cross-Domain Iris Presentation Attack Detection
摘要： The adoption of large-scale iris recognition systems around the world has brought the importance of detecting presentation attack images (textured contact lenses and printouts). This work presents a new approach in iris Presentation Attack Detection (PAD), by exploring combinations of Convolutional Neural Networks (CNNs) and transformed input spaces through binarized statistical image features (BSIF). Our method combines lightweight CNNs to classify multiple BSIF views of the input image. Following explorations on complementary input spaces leading to more discriminative features to detect presentation attacks, we also propose an algorithm to select the best (and most discriminative) predictors for the task at hand. An ensemble of predictors makes use of their expected individual performances to aggregate their results into a final prediction. Results show that this technique improves on the current state of the art in iris PAD, outperforming the winner of LivDet-Iris 2017 competition both for intra- and cross-dataset scenarios, and illustrating the very difficult nature of the cross-dataset scenario.
关键词： Convolutional Neural Networks (CNNs),Ensemble Learning,Binarized Statistical Image Features (BSIF),Presentation Attack Detection (PAD),Iris recognition
更新于2025-09-11 14:15:04
-
[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 - Joint Feature Network for Bridge Segmentation in Remote Sensing Images
摘要： This paper proposes a novel convolutional neural network architecture for semantic segmentation of bridges with various scales in optical remote sensing images. In the context of RSI analysis on objects with irregular shapes, it is necessary to get dense, pixelwise classification maps. To address the issue, a new network architecture for producing refined shapes is required instead of image categorization labels. In our end-to-end framework, a ResNet is used as a backbone model to extract semantic features, then a cascaded top-down path is added to fuse these features as different scales. Joint features are obtained by stacking different layers of feature maps. Experiments show our proposed architecture has the ability to combine rich multi-scale contextual information to produce semantic segmentation maps with high accuracy.
关键词： remote sensing images (RSIs),semantic segmentation,convolutional neural networks (CNNs),pixelwise classification
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 - The Influence of Sampling Methods on Pixel-Wise Hyperspectral Image Classification with 3D Convolutional Neural Networks
摘要： Supervised image classification is one of the essential techniques for generating semantic maps from remotely sensed images. The lack of labeled ground truth datasets, due to the inherent time effort and cost involved in collecting training samples, has led to the practice of training and validating new classifiers within a single image. In line with that, the dominant approach for the division of the available ground truth into disjoint training and test sets is random sampling. This paper discusses the problems that arise when this strategy is adopted in conjunction with spectral-spatial and pixel-wise classifiers such as 3D Convolutional Neural Networks (3D CNN). It is shown that a random sampling scheme leads to a violation of the independence assumption and to the illusion that global knowledge is extracted from the training set. To tackle this issue, two improved sampling strategies based on the Density-Based Clustering Algorithm (DBSCAN) are proposed. They minimize the violation of the train and test samples independence assumption and thus ensure an honest estimation of the generalization capabilities of the classifier.
关键词： DBSCAN,clustering,sampling strategies,Convolutional Neural Networks (CNNs),deep learning,Hyperspectral image classification
更新于2025-09-10 09:29:36