- 标题
- 摘要
- 关键词
- 实验方案
- 产品
-
Learning Deep Conditional Neural Network for Image Segmentation
摘要： Combining Convolutional Neural Networks (CNNs) with Conditional Random Fields (CRFs) achieve great success among recent object segmentation methods. There are two advantages by such usage. First, CNNs can extract low-level features, which are very similar to the extracted features in primates’ primary visual cortex (V1). Second, CRFs can set up the relationship between input features and output labels in a direct way. In this paper, we extend the first advantage by using CNNs for low-level feature extraction and Structured Random Forest (SRF) based border ownership detector for high-level feature extraction, which are similar to the outputs of primates secondary visual cortex (V2). Compared to the CRF model, an improved Conditional Boltzmann Machine (CBM) which has a multi-channel visible layer are proposed to model the relationship between predicted labels, local and global contexts of objects with multi-scale and multilevel features. Besides, our proposed CBM model is extended for object parsing by using multi visible branches instead of a single visible layer of CBM, which can not only segment the whole body but also the parts of the body under. These visible branches use each branch for the segmentation of the whole body or one of the body parts. All the branches share the same hidden layers of CBM and train the branches under an iterative way. By exploiting object parsing, the whole body segmentation performance of object is improved. To refine the segmentation output, two kinds of optimization algorithms are proposed. The superpixel based algorithm can re-label the overlapped regions of multi-kinds of objects. The other curve correction algorithm corrects the edges of segmented object parts by using smooth edges under a curve similarity criterion. Experiments demonstrate that our models yield competitive results for object segmentation on PASCAL VOC 2012 dataset and for object parsing on PennFudan Pedestrian Parsing dataset, Pedestrian Parsing Surveillance Scenes dataset, Horse-Cow parsing dataset, PASCAL Quadrupeds dataset.
关键词： Convolutional Neural Networks,Conditional Boltzmann Machines,Segmentation,object parsing
更新于2025-09-23 15:23:52
-
Adaptive Decentralized Control of Residential Storage in PV-Rich MV-LV Networks
摘要： The rapid adoption of residential-scale photovoltaic (PV) systems in low voltage (LV) networks combined with the falling prices of residential-scale battery energy storage (BES) systems is paving the way for a future in which customers could locally supply most of their energy needs. However, off-the-shelf (OTS) storage systems operate for the sole benefit of the customer (reducing grid imports). This means that charging might not occur during times of high PV generation, resulting in technical issues on LV and medium voltage (MV) networks. This work proposes an adaptive decentralized control strategy for residential-scale BES systems to reduce voltage and thermal issues whilst still benefiting customers. With this strategy, the power charging and discharging rates constantly adapt throughout the day based on clear-sky irradiance, PV generation, demand, and state of charge; significantly reducing reverse power flows and ensuring adequate storage capacity the next morning. A real Australian MV feeder with realistically modelled LV networks is studied using smart meter data. Results demonstrate that the proposed control strategy overcomes the limitations of the OTS BES. It is also shown it can be as effective as an ideal optimization-based approach, being able to manage all technical issues without significantly affecting customers.
关键词： PV Systems,Self-Sufficiency,Distribution Networks,Battery Energy Storage Systems
更新于2025-09-23 15:23:52
-
[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 - Environmental Monitoring Using Drone Images and Convolutional Neural Networks
摘要： Recently, drone images have been used in a number of applications, mainly for pollution control and surveillance purposes. In this paper, we introduce the well-known Convolutional Neural Networks in the context of environmental monitoring using drone images, and we show their robustness in real-world images obtained from uncontrolled scenarios. We consider a transfer learning-based approach and compare two neural models, i.e., VGG16 and VGG19, to distinguish four classes: 'water', 'deforesting area', 'forest', and 'buildings'. The results are analyzed by experts in the field and considered pretty much reasonable.
关键词： Land-use classification,Convolutional Neural Networks,Drones
更新于2025-09-23 15:23:52
-
Bidirectional Recurrent Auto-Encoder for Photoplethysmogram Denoising
摘要： Photoplethysmography (PPG) has become ubiquitous with the development of smartwatches and the mobile healthcare market. However, PPG is vulnerable to various types of noises which are ever-present in uncontrolled environments, and the key to obtaining meaningful signals depends on successful denoising of PPG. In this context, algorithms have been developed to denoise PPG, but many were validated in controlled settings or are reliant on multiple steps that must all work correctly. This paper proposes a novel PPG denoising algorithm based on bidirectional recurrent denoising auto-encoder (BRDAE) which requires minimal pre-processing steps and have the benefit of waveform feature accentuation beyond simple denoising. The BRDAE was trained and validated on a dataset with artificially augmented noise, and was tested on a large open-database of PPG signals collected from patients enrolled in intensive care units (ICUs) as well as from PPG data collected intermittently during the daily routine of 9 subjects over 24-hours. Denoising with the trained BRDAE improved signal-to-noise ratio of the noise-augmented data by 7.9dB during validation. In the test datasets, the denoised PPG showed statistically significant improvement in heart rate detection as compared to the original PPG in terms of correlation to reference and root-mean-squared error. These results indicate that the proposed method is an effective solution for denoising the PPG signal, and promises values beyond traditional denoising by providing PPG feature accentuation for pulse waveform analysis.
关键词： auto-encoder (AE),denoising,recurrent neural networks (RNN),photoplethysmography (PPG)
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
-
Dense Semantic Labeling with Atrous Spatial Pyramid Pooling and Decoder for High-Resolution Remote Sensing Imagery
摘要： Dense semantic labeling is significant in high-resolution remote sensing imagery research and it has been widely used in land-use analysis and environment protection. With the recent success of fully convolutional networks (FCN), various types of network architectures have largely improved performance. Among them, atrous spatial pyramid pooling (ASPP) and encoder-decoder are two successful ones. The former structure is able to extract multi-scale contextual information and multiple effective field-of-view, while the latter structure can recover the spatial information to obtain sharper object boundaries. In this study, we propose a more efficient fully convolutional network by combining the advantages from both structures. Our model utilizes the deep residual network (ResNet) followed by ASPP as the encoder and combines two scales of high-level features with corresponding low-level features as the decoder at the upsampling stage. We further develop a multi-scale loss function to enhance the learning procedure. In the postprocessing, a novel superpixel-based dense conditional random field is employed to refine the predictions. We evaluate the proposed method on the Potsdam and Vaihingen datasets and the experimental results demonstrate that our method performs better than other machine learning or deep learning methods. Compared with the state-of-the-art DeepLab_v3+ our model gains 0.4% and 0.6% improvements in overall accuracy on these two datasets respectively.
关键词： dense semantic labeling,encoder-decoder,superpixel-based DenseCRF,remote sensing imagery,fully convolutional networks,atrous spatial pyramid pooling
更新于2025-09-23 15:23:52
-
Machine Learning of Two-Dimensional Spectroscopic Data
摘要： Two-dimensional electronic spectroscopy has become one of the main experimental tools for analyzing the dynamics of excitonic energy transfer in large molecular complexes. Simplified theoretical models are usually employed to extract model parameters from the experimental spectral data. Here we show that computationally expensive but exact theoretical methods encoded into a neural network can be used to extract model parameters and infer structural information such as dipole orientation from two dimensional electronic spectra (2DES) or reversely, to produce 2DES from model parameters. We propose to use machine learning as a tool to predict unknown parameters in the models underlying recorded spectra and as a way to encode computationally expensive numerical methods into efficient prediction tools. We showcase the use of a trained neural network to efficiently compute disordered averaged spectra and demonstrate that disorder averaging has non-trivial effects for polarization controlled 2DES.
关键词： Neural Networks,excitonic energy transfer,light-harvesting complexes,ML numerical methods
更新于2025-09-23 15:23:52
-
Rapid tomographic reconstruction through GPU-based adaptive optics
摘要： Large telescopes have important challenges in the near future. Increasing the size of mirrors and sensors suppose not only a design issue, but also new computational techniques are needed to deal with the large amount of data. Adaptive Optics is an essential part of extremely large telescopes, and it uses reference stars and a tomographic reconstructor to compensate the aberrations introduced by the atmosphere during observation. The Complex Atmospheric Reconstructor based on Machine lEarNing (CARMEN) is a tomographic reconstructor based on neural networks which has been used during on-sky observations. In this paper CARMEN will be implemented in two different neural network frameworks, which use a Graphics Processing Unit to improve their performance. To time the training and execution will provide results of which framework is faster for its implementation in a real telescope and will supply new tools to keep improving the reconstruction ability of CARMEN.
关键词： Adaptive Optics,Torch,Neural Networks,TensorFlow
更新于2025-09-23 15:23:52
-
Spatiotemporal Adaptive Nonuniformity Correction Based on BTV Regularization
摘要： The residual nonuniformity response, ghosting artifacts, and over-smooth effects are the main defects of the existing nonuniformity correction (NUC) methods. In this paper, a spatiotemporal feature-based adaptive NUC algorithm with bilateral total variation (BTV) regularization is presented. The primary contributions of the innovative method are embodied in the following aspects: BTV regularizer is introduced to eliminate the nonuniformity response and suppress the ghosting effects. The spatiotemporal adaptive learning rate is presented to further accelerate convergence, remove ghosting artifacts, and avoid over-smooth. Moreover, the random projection-based bilateral filter is proposed to estimate the desired target image more accurately which yields more details in the actual scene. The experimental results validated that the proposed algorithm achieves outstanding performance upon both simulated data and real-world sequence.
关键词： infrared image sensors,Infrared imaging,neural networks,image denoising
更新于2025-09-23 15:23:52
-
Evaluation of Signal Regeneration Impact on the Power Efficiency of Long-Haul DWDM Systems
摘要： Due to potential economic benefits and expected environmental impact, the power consumption issue in wired networks has become a major challenge. Furthermore, continuously increasing global Internet traffic demands high spectral efficiency values. As a result, the relationship between spectral efficiency and energy consumption of telecommunication networks has become a popular topic of academic research over the past years, where a critical parameter is power efficiency. The present research contains calculation results that can be used by optical network designers and operators as guidance for developing more power efficient communication networks if the planned system falls within the scope of this paper. The research results are presented as average aggregated traffic curves that provide more flexible data for the systems with different spectrum availability. Further investigations could be needed in order to evaluate the parameters under consideration taking into account particular spectral parameters, e.g., the entire C-band.
关键词： DWDM,phase shift keying,differential phase shift keying,power consumption,spectral efficiency,sub-band spacing,WDM networks,single-line rate,optical fibre networks,power efficiency,energy efficiency
更新于2025-09-23 15:22:29