- 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
-
[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
-
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
-
Adaptive SVD Domain-Based White Gaussian Noise Level Estimation in Images
摘要： Noise level estimation is a challenging area of digital image processing with a variety of applications, including image enhancement, image segmentation, and feature extraction. In this paper, an adaptive estimation of additive white Gaussian noise level based on the singular value decomposition (SVD) of images is proposed. The proposed algorithm aims to improve the performance of noise level estimation in the SVD domain at low noise levels. An initial noise level estimate is used to adjust the parameters of the algorithm in order to increase the accuracy of noise level estimation. The proposed algorithm exhibits the ability to adapt the number of considered singular values and to accordingly adjust the slope of a linear function that describes how the average value of the singular value tail varies with noise levels. Although, for each image, the proposed algorithm performs the noise level estimation twice in two distinct stages, the singular value decompositions are only performed in the first stage of the algorithm. The experimental results demonstrate that the proposed algorithm improves the noise level estimation at low noise levels without a significant increase in computational complexity. At noise level σ = 15, the improvements in the mean square level are about 39% at the expense of slightly higher additional computational time.
关键词： artificial neural networks,singular value decomposition,image analysis,noise level estimation,Digital images,AWGN,least square methods
更新于2025-09-23 15:22:29
-
[IEEE 2018 IEEE 6th Workshop on Advances in Information, Electronic and Electrical Engineering (AIEEE) - Vilnius, Lithuania (2018.11.8-2018.11.10)] 2018 IEEE 6th Workshop on Advances in Information, Electronic and Electrical Engineering (AIEEE) - Deep Neural Network-based Feature Descriptor for Retinal Image Registration
摘要： Feature description is an important step in image registration workflow. Discriminative power of feature descriptors affects feature matching performance and overall results of image registration. Deep Neural Network-based (DNN) feature descriptors are emerging trend in image registration tasks, often performing equally or better than hand-crafted ones. However, there are no learned local feature descriptors, specifically trained for human retinal image registration. In this paper we propose DNN-based feature descriptor that was trained on retinal image patches and compare it to well-known hand-crafted feature descriptors. Training dataset of image patches was compiled from nine online datasets of eye fundus images. Learned feature descriptor was compared to other descriptors using Fundus Image Registration dataset (FIRE), measuring amount of correctly matched ground truth points (Rank-1 metric) after feature description. We compare the performance of various feature descriptors applied for retinal image feature matching.
关键词： artificial neural networks,biomedical imaging,machine learning,image registration,retinal images,feature descriptors
更新于2025-09-23 15:22:29
-
[IEEE 2018 25th IEEE International Conference on Image Processing (ICIP) - Athens, Greece (2018.10.7-2018.10.10)] 2018 25th IEEE International Conference on Image Processing (ICIP) - Perception Preserving Decolorization
摘要： Decolorization is a basic tool to transform a color image into a grayscale image, which is used in digital printing, stylized black-and-white photography, and in many single-channel image processing applications. While recent researches focus on retaining as much as possible meaningful visual features and color contrast. In this paper, we explore how to use deep neural networks for decolorization, and propose an optimization approach aiming at perception preserving. The system uses deep representations to extract content information based on human visual perception, and automatically selects suitable grayscale for decolorization. The evaluation experiments show the effectiveness of the proposed method.
关键词： Color-to-gray conversion,perception preserving,deep neural networks
更新于2025-09-23 15:22:29