- 标题
- 摘要
- 关键词
- 实验方案
- 产品
-
[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 - Semi-Supervised Object Detection in Remote Sensing Images Using Generative Adversarial Networks
摘要： Object detection is a challenging task in computer vision. Now many detection networks can get a good detection result when applying large training dataset. However, annotating sufficient amount of data for training is often time-consuming. To address this problem, a semi-supervised learning based method is proposed in this paper. Semi-supervised learning trains detection networks with few annotated data and massive amount of unannotated data. In the proposed method, Generative Adversarial Network is applied to extract data distribution from unannotated data. The extracted information is then applied to improve the performance of detection network. Experiment shows that the method in this paper greatly improves the detection performance compared w1ith supervised learning using only few annotated data. The results prove that it is possible to achieve acceptable detection result when only few target object is annotated in the training dataset.
关键词： generative adversarial networks (GAN),convolutional neural networks (CNN),Semi-supervised learning,object detection
更新于2025-09-10 09:29:36
-
[IEEE 2018 7th International Conference on Agro-geoinformatics (Agro-geoinformatics) - Hangzhou (2018.8.6-2018.8.9)] 2018 7th International Conference on Agro-geoinformatics (Agro-geoinformatics) - Fine Classification of Typical Farms in Southern China Based on Airborne Hyperspectral Remote Sensing Images
摘要： In the southern part of China, peculiar land fragmentation so that crop planting is characterized by small planting area of a single block, alternate cropping in multiple plots and diversified planting in space. Based on the unique crop planting characteristics in southern part of China, this paper take typical southern farm in Honghu City, Hubei Province as an example, adopting the platform of unmanned aerial vehicle imaging spectrometer to obtain the “double high” (high spectral and high spatial resolution) images at the same time. To complete the crop fine classification of 'double high' images , the CNN- CRF algorithm is proposed. The CNN-CRF algorithm acquires 91.5% accuracy with only 1% train samples on remote sensing images, which performs far better than most traditional classification approaches.
关键词： Conditional Random Fields (CRF),Convolutional Neural Network (CNN),Fine Classification,Airborne hyperspectral
更新于2025-09-10 09:29:36
-
Convolution neural network-based time-domain equalizer for DFT-Spread OFDM VLC system
摘要： This paper presents a novel time-domain equalizer for visible light communication (VLC) system using machine learning (ML) method. In this work, we employ discrete Fourier transform spread orthogonal frequency division multiplexing (DFT-S-OFDM) as modem scheme and convolution neural network (CNN) as kernel processing unit of equalizer. After estimating channel state information (CSI) from training sequence, the proposed equalizer recovers transmitted symbols according to the estimated CSI. Numerical simulations indicate that the equalizer can significantly enhance bit error rate (BER) performance. For example, when signal-to-noise ratio (SNR) is 20dB and 16/32/64-quadrature amplitude modulation (QAM) is exploited, original BER is about 0.5 while the BER after recovery achieves 10?5, which is much lower than forward error correction (FEC) limit 3.8×10?3. This work promotes the application of ML in VLC domain. To the best of our knowledge, this is the first time a CNN-based equalizer has been explored.
关键词： Machine learning (ML),Discrete Fourier transform spread orthogonal frequency division multiplexing (DFT-S-OFDM),Visible light communication (VLC),Convolution neural network (CNN)
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 - Crops Classification from Sentinel-2A Multi-spectral Remote Sensing Images Based on Convolutional Neural Networks
摘要： Deep learning technology such as convolutional neural networks (CNN) can extract the distinguishable and representative features of different land cover from remote sensing images in a hierarchical way to classify. However, in the field of agriculture, there are few application of crops classification from multi-spectral remote sensing images based on deep learning. In this context, we compared the classification methods of CNN and support vector machines (SVM) in extracting the spatial distribution of crops planting area from Sentineal-2A multi-spectral remote sensing images in Yuanyang county, China. For the region of study, both methods obtained reasonable spatial distribution of different crops, the verification results show that the overall accuracy of CNN is 95.6% which is superior to SVM.
关键词： multi-spectral,remote sensing,crops classification,Sentinel-2A,CNN
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 - Deep Tensor Factorization for Hyperspectral Image Classification
摘要： High-dimensional spectral feature and limited training samples have caused a range of difficulties for hyperspectral image (HSI) classification. Feature extraction is effective to tackle this problem. Specifically, tensor factorization is superior to some prominent methods such as principle component analysis (PCA) and non-negative matrix factorization (NMF) because it takes spatial information into consideration. Recently, deep learning has gotten more and more attention for efficiently extracting hierarchical features for various tasks. In this paper, we propose a novel feature extraction method, deep tensor factorization (DTF), to extract hierarchical and meaningful features from observed HSI. This method takes advantage of tensor in representing HSI and the merits of convolutional neural network (CNN) in hierarchical feature extraction. Specifically, a convolution operation is firstly applied in the spectral dimension of HSI to suppress the effect of noise. Then, the convolved HSI is fed into tensor factorization to learn a low rank representation of data. After that, the above two process are repeated to learn a hierarchical representation of HSI. Experimental results on two real hyperspectral datasets show the superiority of the proposed method.
关键词： Hyperspectral image (HSI) classification,feature extraction,convolutional neural network (CNN),tensor decomposition
更新于2025-09-10 09:29:36
-
Convolutional Neural Network Trained by Joint Loss for Hyperspectral Image Classification
摘要： In this letter, is proposed the hyperspectral image classification method based on the convolutional neural network, which is trained jointly by the reconstruction and discriminative loss functions. In the network, small convolutional kernels are cascaded with the pooling operator to perform feature abstraction, and a decoding channel composed of the deconvolutional and unpooling operators is established. The unsupervised reconstruction, performed by the decoding channel, not only introduces priors to the network training but also is made use to enhance the discriminability of the abstracted features by the control gate. By the experiments, it is shown that the proposed method performs better than the state-of-the-art neural network-based classification methods.
关键词： Control gate,unsupervised reconstruction,convolutional neural network (CNN),joint loss (JL),hyperspectral image (HSI) classification
更新于2025-09-10 09:29:36
-
Automated phenotyping of epicuticular waxes of grapevine berries using light separation and convolutional neural networks
摘要： The epicuticular wax represents the outer layer of the grape berry skin and is known as trait that is significantly correlated to resilience towards Botrytis bunch rot. Traditionally this trait is classified using the OIV descriptor 227 (berry bloom) in a time consuming way resulting in subjective and error-prone phenotypic data. In the present study an objective, fast and sensor-based approach was developed to monitor epicuticular waxes. From the technical point-of-view, it is known that the measurement of different illumination components conveys important information about observed object surfaces. A Light-Separation-Lab is proposed in order to capture illumination-separated images of grapevine berries for phenotyping the distribution of epicuticular waxes (berry bloom). For image analysis, an efficient convolutional neural network approach is used to derive the uniformity and intactness of waxes on berries. Method validation over six grapevine cultivars shows accuracies up to 97.3%. In addition, electrical impedance of the cuticle and its epicuticular waxes (described as an indicator for the thickness of berry skin and its permeability) was correlated to the detected proportion of waxes with r = 0.76. This novel, fast and non-invasive phenotyping approach facilitates enlarged screenings within grapevine breeding material and genetic repositories regarding berry bloom characteristics and its impact on resilience towards Botrytis bunch rot.
关键词： Botrytis cinerea,Berry bloom,Convolutional Neural Networks (CNN),Vitis vinifera,Direct and global illumination
更新于2025-09-10 09:29:36
-
Near Infrared Nighttime Road Pedestrians Recognition Based on Convolutional Neural Network
摘要： Pedestrian recognition is the core technology of pedestrian detection in pedestrian protection systems. This paper compares and analyzes, visible and infrared images obtained via visible-spectrum, near-infrared, short-wave infrared, and long-wave infrared cameras. The results show that near-infrared camera was the best for nighttime pedestrian detection when device cost and pedestrian imaging quality were considered. This paper reports on the first time use of a self-learning softmax with a 9-layer Convolutional Neural Network (CNN) model to identify near-infrared nighttime pedestrians. 267,000 samples obtained from the near-infrared images were employed to optimize the CNN recognition model. Collected near-infrared nighttime samples had 3 categories (background, pedestrian, and cyclist or motorcyclist) and will be made publicly available for researchers use. Testing results indicated that the optimized CNN model using self-learning softmax had a competitive accuracy and potential in real-time pedestrian recognition.
关键词： softmax,pedestrian recognition,CNN,nighttime,near infrared
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 - 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
-
[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