- 标题
- 摘要
- 关键词
- 实验方案
- 产品
-
A New Method for Region-Based Majority Voting CNNs for Very High Resolution Image Classification
摘要： Conventional geographic object-based image analysis (GEOBIA) land cover classification methods by using very high resolution images are hardly applicable due to their complex ground truth and manually selected features, while convolutional neural networks (CNNs) with many hidden layers provide the possibility of extracting deep features from very high resolution images. Compared with pixel-based CNNs, superpixel-based CNN classification, carrying on the idea of GEOBIA, is more efficient. However, superpixel-based CNNs are still problematic in terms of their processing units and accuracies. Firstly, the limitations of salt and pepper errors and low boundary adherence caused by superpixel segmentation still exist; secondly, this method uses the central point of the superpixel as the classification benchmark in identifying the category of the superpixel, which does not allow classification accuracy to be ensured. To solve such problems, this paper proposes a region-based majority voting CNN which combines the idea of GEOBIA and the deep learning technique. Firstly, training data was manually labeled and trained; secondly, images were segmented under multiresolution and the segmented regions were taken as basic processing units; then, point voters were generated within each segmented region and the perceptive fields of points voters were put into the multi-scale CNN to determine their categories. Eventually, the final category of each region was determined in the region majority voting system. The experiments and analyses indicate the following: 1. region-based majority voting CNNs can fully utilize their exclusive nature to extract abstract deep features from images; 2. compared with the pixel-based CNN and superpixel-based CNN, the region-based majority voting CNN is not only efficient but also capable of keeping better segmentation accuracy and boundary fit; 3. to a certain extent, region-based majority voting CNNs reduce the impact of the scale effect upon large objects; and 4. multi-scales containing small scales are more applicable for very high resolution image classification than the single scale.
关键词： remote sensing,region-based classification,very high resolution image,CNN,GEOBIA
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) - Recombined Convolutional Neural Network for Recognition of Macular Disorders in SD-OCT Images
摘要： Macular disorders, such as age-related macular degeneration (AMD) and diabetic macular edema (DME), have plagued humans for many years, yet the traditional recognition methods are often complicated, time-consuming and laborious. Therefore, this paper proposes an effective recombined residual convolutional neural network (CNN) with less computation to recognize AMD, DME and the normal of SD-OCT images. This paper adopts the18-layer Residual CNN as the basis and removes some of convolutional layers in the convolutional groups which extract low-level or high-level features, while add them to the middle part of the CNN, to enhance the ability of extracting mid-level features. This paper also adjusts the kernel size to change the visual receptive fields during convolution calculations. Experiments show that the recombined residual CNN with the kernel size of 3x3 shows better performance than the original one and recently proposed methods on the same dataset, with the highest overall accuracy up to 90%. Moreover, in terms of feature extraction complexity and time consumption, the recombined residual CNN is also more dominant.
关键词： recombined residual CNN,deep learning,Macular disorders,SD-OCT
更新于2025-09-09 09:28:46
-
Data Augmentation for Hyperspectral Image Classification With Deep CNN
摘要： Convolutional neural network (CNN) has been widely used in hyperspectral imagery (HSI) classification. Data augmentation is proven to be quite effective when training data size is relatively small. In this letter, extensive comparison experiments are conducted with common data augmentation methods, which draw an observation that common methods can produce a limited and up-bounded performance. To address this problem, a new data augmentation method, named as pixel-block pair (PBP), is proposed to greatly increase the number of training samples. The proposed method takes advantage of deep CNN to extract PBP features, and decision fusion is utilized for final label assignment. Experimental results demonstrate that the proposed method can outperform the existing ones.
关键词： pattern classification,Convolutional neural network (CNN),hyperspectral imagery (HSI),data augmentation
更新于2025-09-09 09:28:46
-
Self-Supervised Feature Learning With CRF Embedding for Hyperspectral Image Classification
摘要： The challenges in hyperspectral image (HSI) classification lie in the existence of noisy spectral information and lack of contextual information among pixels. Considering the three different levels in HSIs, i.e., subpixel, pixel, and superpixel, offer complementary information, we develop a novel HSI feature learning network (HSINet) to learn consistent features by self-supervision for HSI classification. HSINet contains a three-layer deep neural network and a multifeature convolutional neural network. It automatically extracts the features such as spatial, spectral, color, and boundary as well as context information. To boost the performance of self-supervised feature learning with the likelihood maximization, the conditional random field (CRF) framework is embedded into HSINet. The potential terms of unary, pairwise, and higher order in CRF are constructed by the corresponding subpixel, pixel, and superpixel. Furthermore, the feedback information derived from these terms are also fused into the different-level feature learning process, which makes the HSINet-CRF be a trainable end-to-end deep learning model with the back-propagation algorithm. Comprehensive evaluations are performed on three widely used HSI data sets and our method outperforms the state-of-the-art methods.
关键词： self-supervision,feature learning,convolutional neural network (CNN),Conditional random field (CRF),hyperspectral image (HSI) classification
更新于2025-09-09 09:28:46
-
[IEEE 2018 International Conference on Advances in Computing, Communications and Informatics (ICACCI) - Bangalore, India (2018.9.19-2018.9.22)] 2018 International Conference on Advances in Computing, Communications and Informatics (ICACCI) - Feature level fusion of Face and Iris using Deep Features based on Convolutional Neural Networks
摘要： In this work, we have proposed novel deep CNN framework architectures that effectively represent complex image characteristics which performs feature extraction in just two convolution layers and has successfully proved to be an reliable biometric verification system on employment of physiological face and iris for our system development. Extensive traits experiments in configuring the CNN hyper parameters such as number of convolution layers required, filters and its size in each layer, batch size, epochs, iterations and learning rate is a paramount, determining these factors truly depends on the nature of data and its size. Our work has relinquished our novel idea and has obtained 99% of GAR in unimodal biometric verification system itself and definitely the approach has rendered great results when compared with conventional feature extraction and classification techniques.
关键词： Verification,Multimodal biometric,CNN,Fusion
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) - Cross Modal Multiscale Fusion Net for Real-time RGB-D Detection
摘要： This paper presents a novel multi-modal CNN architecture for object detection by exploiting complementary input cues in addition to sole color information. Our one-stage architecture fuses the multiscale mid-level features from two individual feature extractor, so that our end-to-end net can accept crossmodal streams to obtain high-precision detection results. In comparison to other crossmodal fusion neural networks, our solution successfully reduces runtime to meet the real-time requirement with still high-level accuracy. Experimental evaluation on challenging NYUD2 dataset shows that our network achieves 49.1% mAP, and processes images in real-time at 35.3 frames per second on one single Nvidia GTX 1080 GPU. Compared to baseline one stage network SSD on RGB images which gets 39.2% mAP, our method has great accuracy improvement.
关键词： multi-modal CNN,fusion network,object detection,RGB-D,real-time
更新于2025-09-09 09:28:46
-
[IEEE 2017 IEEE Nuclear Science Symposium and Medical Imaging Conference (NSS/MIC) - Atlanta, GA (2017.10.21-2017.10.28)] 2017 IEEE Nuclear Science Symposium and Medical Imaging Conference (NSS/MIC) - Application of Deep Leaming in Multi-Material Decomposition of Spectral CT
摘要： Multi-material decomposition (MMD) is an important application of spectral Computed Tomography (CT). However, traditional image-domain material decomposition algorithms are based on pixel-wise usually, affected by noise and artifact easily. In order to enlarge the receptive field instead of considering the neighborhood of pixel only, we adopt deep learning technique to solve the multi-material decomposition problem. We build a convolutional neural network (CNN) to solve the MMD problem. Then we simulate some reconstruction images of spectral CT to train the network. After training, the CNN method can reduce the MSE by 1~2 orders in the test samples, comparing to the results of solving linear equations. As the conclusion, we think CNN shows its effectiveness to solve MMD problem, and has some irreplaceable advantages, but there still remains many researches to survey.
关键词： deep learning,spectral CT,CNN,multi-material decomposition
更新于2025-09-09 09:28:46
-
[ACM Press the 2018 ACM International Joint Conference and 2018 International Symposium - Singapore, Singapore (2018.10.08-2018.10.12)] Proceedings of the 2018 ACM International Joint Conference and 2018 International Symposium on Pervasive and Ubiquitous Computing and Wearable Computers - UbiComp '18 - PPG-based Heart Rate Estimation with Time-Frequency Spectra
摘要： PPG-based continuous heart rate estimation is challenging due to the effects of physical activity. Recently, methods based on time-frequency spectra emerged to compensate motion artefacts. However, existing approaches are highly parametrised and optimised for specific scenarios. In this paper, we first argue that cross-validation schemes should be adapted to this topic, and show that the generalisation capabilities of current approaches are limited. We then introduce deep learning, specifically CNN-models, to this domain. We investigate different CNN-architectures (e.g. the number of convolutional layers, applying batch normalisation, or ensemble prediction), and report insights based on our systematic evaluation on two publicly available datasets. Finally, we show that our CNN-based approach performs comparably to classical methods.
关键词： Heart rate,CNN,Evaluation methods,Deep learning,PPG,Time-frequency spectrum
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 - Weed Classification in Hyperspectral Remote Sensing Images Via Deep Convolutional Neural Network
摘要： Automatic weed detection and mapping are critical for site-speci?c weed control in order to reduce the cost of farming as well as the impact of herbicides on human health. In this paper, we investigate patch-based weed identi?cation using hyperspectral images. Convolutional Neural Network (CNN) is evaluated and compared with the Histogram of Oriented Gradients (HoG) for this purpose. Suitable patch sizes are investigated. The limitation of RGB imagery is demonstrated. The experimental results indicate that the overall accuracy of the weed classi?cation using CNN increases with the increasing number of bands used. With more bands, CNN extracts more powerful and discriminative features and leads to improved classi?cation as compared to the traditional HoG feature extraction method. The computational load of CNN, however, is slightly increased with the increasing number of bands.
关键词： Histogram of Oriented Gradients (HoG),weed mapping,Hyperspectral images,Convolutional Neural Network (CNN)
更新于2025-09-09 09:28:46
-
[IEEE 2017 IEEE 7th Annual International Conference on CYBER Technology in Automation, Control, and Intelligent Systems (CYBER) - Honolulu, HI, USA (2017.7.31-2017.8.4)] 2017 IEEE 7th Annual International Conference on CYBER Technology in Automation, Control, and Intelligent Systems (CYBER) - Obstacle avoidance of aerial vehicle based on monocular vision
摘要： Collision-free autonomous navigation is extremely important for quadcopter and other flying robots. The implementation of autonomic moving capabilities can contribute significantly to their promotion and usage in fields such as goods delivering, aerial photos shooting, and monitoring. In order to realize the autonomous flight without crash, the obstacle avoidance problem demands a prompt solution. Also, with the concern of cost and endurance, using only single camera to perform this task would be a better choice for low-cost flying robots. Thus, this paper focuses on achieving quadcopter's collision avoidance in unknown stable (rarely changes, such as high sky or inner room) environment only by single camera. The algorithm proposed by this paper is composed of PTAM (Parallel Tracking and Mapping), DTAM (Dense Tracking and Mapping in Real-Time) algorithm and CNN (Convolutional Neural Network). PTAM is used to create the 3D map of the environment. DTAM is used to obtain the depth map of those image frames. And the CNN is used to train and get a model used for automatically avoidance. Finally, this algorithm is proved to be valid by an experiment.
关键词： Obstacle avoidance,CNN,quadcopter,PTAM,monocular vision,DTAM
更新于2025-09-09 09:28:46