Dynamic aurora sequence recognition using Volume Local Directional Pattern with local and global features
8
Citation
23
Reference
10
Related Paper
Citation Trend
Keywords:
Sequence (biology)
Pyramid (geometry)
Feature (linguistics)
Pyramid (geometry)
Feature (linguistics)
Convolution (computer science)
Semantic feature
Cite
Citations (11)
In this paper, we study the effect of discriminative feature learning for face alignment. We claim that features of the same facial landmarks on different images should share similarities at the feature-level. Thus, we propose the Discriminative Feature Learning method (DFL) for face alignment based on the Fully Convolutional Network (FCN). First, the face image is aligned frontal to eliminate the effect of pose and scale. Second, landmark-specific features are extracted from feature maps of the FCN. A distance constraint on landmark features is added to learn discriminative landmark features. Our experiment results show that DFL can effectively improve the performance of face alignment.
Discriminative model
Landmark
Feature (linguistics)
Feature Learning
Cite
Citations (5)
According to the common principle for the feature based image fusion, multi resolution image segmentation and multi scale feature extraction are realized, the feature level image fusion is studied using CCD and thermal images, then the object classification is performed using the fused feature. At last, the experiment results are analysed and some conclusions are got for the feature level image fusion and object classification.
Feature (linguistics)
Cite
Citations (1)
Several algorithms for target recognition in infrared images were proposed by reasearchers to develop an efficient advanced driver assistance systems. In this paper, an approach based on bag of features framework, SIFT and SVM, is evaluated for target recognition problem. First, SIFT extractor is applied to all the training set. Then, features were clustered by K-means; the cluster centers are regarded as visual words to form a visual vocabulary. For each image, a histogram of quantized local descriptors is computed according to the frequency of visual words in each sub-region, which are obtained by the spatial pyramid matching technique. The generated feature vector will be mapped for later use as an input to SVM. Extensive experiments are carried out in FLIR dataset. Our experimental results show that the proposed method exceeds the-state-of-art in target recognition on two class FLIR dataset with 3% improvement in accuracy classification.
Scale-invariant feature transform
Pyramid (geometry)
Feature (linguistics)
Bag-of-words model
Extractor
Cite
Citations (5)
Single-mode recognition method remains a difficulty problem in target detection and recognition of road vehicle targets in complex urban situations. Hence, using the advantages of obtaining different feature information from infrared and visible images in different situations is considered. We propose a feature level infrared and visible image fusion target detection method based on deep learning. This method first obtains the registered infrared visible image, extracts the image features respectively through two main feature extraction networks, passes through the feature fusion layer, passes into the feature pyramid network to obtain the effective feature layer, and then carries out classification prediction and regression prediction. On the test set, the mAP of the fusion method is 0.89, which is higher than that using only visible images (the mAP is 0.82) and only infrared images (the mAP is 0.79) on the same test set. At the same time, in the night environment, the mAP of the fusion method is much higher than other deep learning frameworks. The experimental results show that the infrared and visible image fusion target detection method realized in this paper has certain advantages over the traditional methods and has a good application prospect.
Feature (linguistics)
Pyramid (geometry)
Night vision
Cite
Citations (1)
The safety of building worker is important in construction industry. In order to realize the worker intelligent management, a novel building worker detection based on cross feature pyramid network is proposed to come true the real-time detection of workers. The proposed cross feature pyramid network uses cross feature of different layers to obtain robust feature of workers. The extracted feature may include high-level and low-level features. Experimental results indicate that the proposed algorithm obtain better performance than the traditional feature pyramid network.
Pyramid (geometry)
Feature (linguistics)
Cite
Citations (0)
Performance of hyperspectral image classification depends on feature extraction. Compared with conventional hand-crafted feature extraction, deep learning can learn feature with more discriminative information. In this paper, a two-channel deep convolutional neural network (Two-CNN) is proposed to learn jointly spectral-spatial feature from hyperspectral image. The proposed model is composed of two channels of CNN, each of which learns feature from spectral domain and spatial domain respectively. The learned spectral feature and spatial feature are then concatenated and fed to fully connected layer to extract joint spectral-spatial feature for classification. When number of training samples is limited, we propose to train the deep model using transfer learning to improve the performance. Low-layer and mid-layer features of the deep model are learned and transferred from other scenes, only top-layer feature is learned using the limited training samples of the current scene. Experiment results on real data demonstrate the effectiveness of the proposed method.
Discriminative model
Feature (linguistics)
Feature Learning
Cite
Citations (125)
A new scene classification method is proposed based on the combination of local Gabor features with a spatial pyramid matching model. First, new local Gabor feature descriptors are extracted from dense sampling patches of scene images. These local feature descriptors are embedded into a bag-of-visual-words (BOVW) model, which is combined with a spatial pyramid matching framework. The new local Gabor feature descriptors have sufficient discrimination abilities for dense regions of scene images. Then the efficient feature vectors of scene images can be obtained byK -means clustering method and visual word statistics. Second, in order to decrease classification time and improve accuracy, an improved kernel principal component analysis (KPCA) method is applied to reduce the dimensionality of pyramid histogram of visual words (PHOW). The principal components with the bigger interclass separability are retained in feature vectors, which are used for scene classification by the linear support vector machine (SVM) method. The proposed method is evaluated on three commonly used scene datasets. Experimental results demonstrate the effectiveness of the method.
Pyramid (geometry)
Feature (linguistics)
Kernel (algebra)
Feature vector
Gabor filter
Cite
Citations (4)
A novel convolutional neural network based on spatial pyramid for image classification is proposed. The network exploits image features with spatial pyramid representation. First, it extracts global features from an original image, and then different layers of grids are utilized to extract feature maps from different convolutional layers. Inspired by the spatial pyramid, the new network contains two parts, one of which is just like a standard convolutional neural network, composing of alternating convolutions and subsampling layers. But those convolution layers would be averagely pooled by the grid way to obtain feature maps, and then concatenated into a feature vector individually. Finally, those vectors are sequentially concatenated into a total feature vector as the last feature to the fully connection layer. This generated feature vector derives benefits from the classic and previous convolution layer, while the size of the grid adjusting the weight of the feature maps improves the recognition efficiency of the network. Experimental results demonstrate that this model improves the accuracy and applicability compared with the traditional model.
Pyramid (geometry)
Feature (linguistics)
Convolution (computer science)
Feature vector
Representation
Cite
Citations (4)
In this paper, the shift-invariant complex directional filter bank (CDFB) is proposed for texture image retrieval. By combining the Laplacian pyramid and the CDFB, a new image representation with an overcomplete ratio of less than 8/3 is obtained. The direction subbands' coefficients are used to form a feature vector for classification. Texture retrieval performance of the proposed representation is compared to those of the conventional transforms including the Gabor wavelet, the contourlet and the steerable pyramid. The overcomplete ratio of the proposed complex directional pyramid is about twice that of the contourlet, and is much lower than those of the other two transforms. An experiment shows that the new transform outperforms the steerable pyramid and the contourlet, and is comparable to the Gabor wavelet in texture image retrieval
Contourlet
Filter bank
Pyramid (geometry)
Texture (cosmology)
Feature (linguistics)
Cite
Citations (22)