Multi-feature Fusion Strategy Research Articles

Scene classification of high-resolution remote sensing images based on IMFNet

Currently, due to the limited amount of data and the difficulty of designing a network, there are few papers on constructing a new convolutional neural network for scene classification using the publicly available datasets of high-resolution remote sensing images. Considering the existing problems, the current scene classification methods of high-resolution remote sensing images are summarized, and the IMFNet model is constructed to classify scenes of high-resolution remote sensing images in this paper. The IMFNet is an end-to-end network, which can learn features from data automatically. The main characteristic of the IMFNet network structure is that the Inception module is used to extract the details of remote sensing images and the multifeature fusion strategy is proposed to ensure the integrity of information. In addition, optimization methods are adopted to improve the classification accuracy. In order to verify the effectiveness of the method proposed in this paper, the two benchmark datasets—the UC Merced dataset and the SIRI-WHU dataset were adopted for experiments. The classification accuracy of the two datasets reaches 92.14% and 90.43%, respectively. Experimental results show that the method proposed has certain advantages over the classification methods based on low-level and middle-level visual features and even some classification methods based on high-level visual features.

Hyperspectral image classification using multi-feature fusion

Traditional hyperspectral image (HSI) classification methods typically use the spectral features and do not make full use of the spatial or other features of the HSI. To address this problem, this paper proposes a novel HSI classification method based on a multi-feature fusion strategy. The spectral-spatial features are first extracted by spectral-spatial feature learning (SSFL), which is a deep hierarchical architecture. Additionally, the texture features of the local binary pattern (LBP) image are applied and fused with the spectral-spatial features. Then, the kernel extreme learning machine (KELM) is used to classify the hyperspectral images. The results of a number of experiments show that the proposed method effectively improves the classification accuracy of hyperspectral images.

Target Tracking Algorithm Based on an Adaptive Feature and Particle Filter

To boost the robustness of the traditional particle-filter-based tracking algorithm under complex scenes and to tackle the drift problem that is caused by the fast moving target, an improved particle-filter-based tracking algorithm is proposed. Firstly, all of the particles are divided into two parts and put separately. The number of particles that are put for the first time is large enough to ensure that the number of the particles that can cover the target is as many as possible, and then the second part of the particles are put at the location of the particle with the highest similarity to the template in the particles that are first put, to improve the tracking accuracy. Secondly, in order to obtain a sparser solution, a novel minimization model for an Lp tracker is proposed. Finally, an adaptive multi-feature fusion strategy is proposed, to deal with more complex scenes. The experimental results demonstrate that the proposed algorithm can not only improve the tracking robustness, but can also enhance the tracking accuracy in the case of complex scenes. In addition, our tracker can get better accuracy and robustness than several state-of-the-art trackers.

Weighted score-level feature fusion based on Dempster–Shafer evidence theory for action recognition

The majority of human action recognition methods use multifeature fusion strategy to improve the classification performance, where the contribution of different features for specific action has not been paid enough attention. We present an extendible and universal weighted score-level feature fusion method using the Dempster–Shafer (DS) evidence theory based on the pipeline of bag-of-visual-words. First, the partially distinctive samples in the training set are selected to construct the validation set. Then, local spatiotemporal features and pose features are extracted from these samples to obtain evidence information. The DS evidence theory and the proposed rule of survival of the fittest are employed to achieve evidence combination and calculate optimal weight vectors of every feature type belonging to each action class. Finally, the recognition results are deduced via the weighted summation strategy. The performance of the established recognition framework is evaluated on Penn Action dataset and a subset of the joint-annotated human metabolome database (sub-JHMDB). The experiment results demonstrate that the proposed feature fusion method can adequately exploit the complementarity among multiple features and improve upon most of the state-of-the-art algorithms on Penn Action and sub-JHMDB datasets.

Robust object tracking based on adaptive templates matching via the fusion of multiple features

Moving object tracking under complex scenes remains to be a challenging problem because the appearance of a target object can be drastically changed due to several factors, such as occlusions, illumination, pose, scale change and deformation. This study proposes an adaptive multi–feature fusion strategy, in which the target appearance is modeled based on timed motion history image with HSV color histogram features and edge orientation histogram features. The variances based on the similarities between the candidate patches and the target templates are used for adaptively adjusting the weight of each feature. Double templates matching, including online and offline template matching, is adopted to locate the target object in the next frame. Experimental evaluations on challenging sequences demonstrate the accuracy and robustness of the proposed algorithm in comparison with several state-of-the-art algorithms.

Scene Classification Based on the Multifeature Fusion Probabilistic Topic Model for High Spatial Resolution Remote Sensing Imagery

Scene classification has been proved to be an effective method for high spatial resolution (HSR) remote sensing image semantic interpretation. The probabilistic topic model (PTM) has been successfully applied to natural scenes by utilizing a single feature (e.g., the spectral feature); however, it is inadequate for HSR images due to the complex structure of the land-cover classes. Although several studies have investigated techniques that combine multiple features, the different features are usually quantized after simple concatenation (CAT-PTM). Unfortunately, due to the inadequate fusion capacity of $\boldsymbol{k}$ -means clustering, the words of the visual dictionary obtained by CAT-PTM are highly correlated. In this paper, a semantic allocation level (SAL) multifeature fusion strategy based on PTM, namely, SAL-PTM (SAL-pLSA and SAL-LDA) for HSR imagery is proposed. In SAL-PTM: 1) the complementary spectral, texture, and scale-invariant-feature-transform features are effectively combined; 2) the three features are extracted and quantized separately by $\boldsymbol{k}$ -means clustering, which can provide appropriate low-level feature descriptions for the semantic representations; and 3)the latent semantic allocations of the three features are captured separately by PTM, which follows the core idea of PTM-based scene classification. The probabilistic latent semantic analysis (pLSA) and latent Dirichlet allocation (LDA) models were compared to test the effect of different PTMs for HSR imagery. A U.S. Geological Survey data set and the UC Merced data set were utilized to evaluate SAL-PTM in comparison with the conventional methods. The experimental results confirmed that SAL-PTM is superior to the single-feature methods and CAT-PTM in the scene classification of HSR imagery.

Object Tracking Method Based on a New Multi-Feature Fusion Strategy

In order to solve the poor robustness problem due to partial occlusionof target, we propose an adaptive particle filter tracking method based on thefusion of the multiple features. First, we regard information fusion as aprocess of information loss, loss coefficient is defined based on this idea.Then the credibility of feature can be obtained by weighted distance and themean of particle filter, and we use the features’ credibility to reallocate theloss coefficient. An extensive number of comparative experiments show theproposed algorithm is more stable and robust than multiplicative fusion andadditive fusion tracking algorithms.

Object Tracking Method Based on a New Multi-Feature Fusion Strategy

Object Tracking Method Based on a New Multi-Feature Fusion Strategy

Robust object tracking via multi-feature adaptive fusion based on stability: contrast analysis

Object tracking under complex circumstances is a challenging task because of background interference, obstacle occlusion, object deformation, etc. Given such conditions, robustly detecting, locating, and analyzing a target through single-feature representation are difficult tasks. Global features, such as color, are widely used in tracking, but may cause the object to drift under complex circumstances. Local features, such as HOG and SIFT, can precisely represent rigid targets, but these features lack the robustness of an object in motion. An effective method is adaptive fusion of multiple features in representing targets. The process of adaptively fusing different features is the key to robust object tracking. This study uses a multi-feature joint descriptor (MFJD) and the distance between joint histograms to measure the similarity between a target and its candidate patches. Color and HOG features are fused as the tracked object of the joint representation. This study also proposes a self-adaptive multi-feature fusion strategy that can adaptively adjust the joint weight of the fused features based on their stability and contrast measure scores. The mean shift process is adopted as the object tracking framework with multi-feature representation. The experimental results demonstrate that the proposed MFJD tracking method effectively handles background clutter, partial occlusion by obstacles, scale changes, and deformations. The novel method performs better than several state-of-the-art methods in real surveillance scenarios.