Hsiuhan Lexie Yang

Active Learning: Any Value for Classification of Remotely Sensed Data?

Active learning, which has a strong impact on processing data prior to the classification phase, is an active research area within the machine learning community, and is now being extended for remote sensing applications. To be effective, classification must rely on the most informative pixels, while the training set should be as compact as possible. Active learning heuristics provide capability to select unlabeled data that are the “most informative” and to obtain the respective labels, contributing to both goals. Characteristics of remotely sensed image data provide both challenges and opportunities to exploit the potential advantages of active learning. We present an overview of active learning methods, then review the latest techniques proposed to cope with the problem of interactive sampling of training pixels for classification of remotely sensed data with support vector machines (SVMs). We discuss remote sensing specific approaches dealing with multisource and spatially and time-varying data, and provide examples for high-dimensional hyperspectral imagery.

Ensemble Multiple Kernel Active Learning For Classification of Multisource Remote Sensing Data

Incorporating disparate features from multiple sources can provide valuable diverse information for remote sensing data analysis. However, multisource remote sensing data require large quantities of labeled data to train robust supervised classifiers, which are often difficult and expensive to acquire. A mixture-of-kernel approach can facilitate the construction of an effective formulation for acquiring useful samples via active learning (AL). In this paper, we propose an ensemble multiple kernel active learning (EnsembleMKL-AL) framework that incorporates different types of features extracted from multisensor remote sensing data (hyperspectral imagery and LiDAR data) for robust classification. An ensemble of probabilistic multiple kernel classifiers is embedded into a maximum disagreement-based AL system, which adaptively optimizes the kernel for each source during the AL process. At the end of each learning step, a decision fusion strategy is implemented to make a final decision based on the probabilistic outputs. The proposed framework is tested in a multisource environment, including different types of features extracted from hyperspectral and LiDAR data. The experimental results validate the efficacy of the proposed approach. In addition, we demonstrate that using ensemble classifiers and a large number of disparate but relevant features can further improve the performance of an AL-based classification approach.

Spectral and Spatial Proximity-Based Manifold Alignment for Multitemporal Hyperspectral Image Classification

Multitemporal hyperspectral images provide valuable information for a wide range of applications related to supervised classification, including long-term environmental monitoring and land cover change detection. However, the required ground reference data are time-consuming and expensive to acquire, motivating researchers to investigate options for reusing limited training data for classification of other temporal images. Current studies that address high dimensionality and nonstationarity inherent in temporal hyperspectral data for classification are limited for the case where significant spectral drift exists between images. In this paper, we adapt and extend two manifold alignment (MA) methods for classification of multitemporal hyperspectral images in a common manifold space, assuming that the local geometries of two temporal spectral images are similar. The first method exploits a locally based manifold configuration of a source image (considered to be the “prior” manifold), and the second approach links local manifolds of two images using bridging pairs. In addition to exploiting manifolds estimated with spectral information for MA, we also demonstrate how spatial information can be incorporated into the MA methods. When evaluated using three Hyperion data sets, the proposed methods outperform four baseline approaches and two state-of-the-art domain adaptation methods. The advantages of the proposed MA methods are more evident when significant spectral drift exists between two temporal images. In addition to the promising classification results, the proposed methods establish a domain adaptation framework for analysis of temporal hyperspectral data based on data geometry.

Manifold alignment for multitemporal hyperspectral image classification

While spectral and temporal advantages of multitemporal hyperspectral images provide opportunities for advancing classification of time varying phenomena, significant challenges are associated with high dimensionality and nonstationary signatures. While manifold learning retains critical geometry and develops a low dimension space where class clusters are recovered, spectral changes in temporal imagery impact the fidelity of the geometric representation of class dependent data. In this paper, we investigate a manifold alignment framework that exploits prior information while exploring similar local structures. The aim is to make use of common underlying geometries of two multitemporal images and embed the resemblances in a joint data manifold for classification tasks. Promising results support the advantages of the proposed manifold alignment approach.

Domain Adaptation With Preservation of Manifold Geometry for Hyperspectral Image Classification

Adapting a pretrained classifier with unlabeled samples from an image for classification of another related image is a common domain adaptation strategy. However, traditional adaptation methods are not effective when the drift of spectral signatures is significant. Instead of iteratively redefining classifier parameters or decision boundaries, we exploit similar data geometries of images and preserve essential common data characteristics in a joint manifold space where similar samples are clustered. The proposed classification framework is based on aligning two global data manifolds with bridging pairs. In addition to global structures, we also consider the local scale by incorporating similar local clusters into the alignment process. In experiments with challenging temporal and spatially disjoint hyperspectral data sets, the proposed framework provides favorable classification results compared to two baseline methods, naive k-NN in both the original space and the manifold derived from pooled data. In comparisons with four state-of-the-art domain adaptation benchmark methods, the proposed method is demonstrated to be a competitive domain adaptation method, especially for the case when spectral changes between two data domains are significant. Results also provide insights related to the usefulness of incorporating global and local geometric characteristics of remote sensing data for domain adaptation studies.

Improving Orthorectification of UAV-Based Push-Broom Scanner Imagery Using Derived Orthophotos From Frame Cameras

Low-cost unmanned airborne vehicles (UAVs) are emerging as a promising platform for remote-sensing data acquisition to satisfy the needs of wide range of applications. Utilizing UAVs, which are equipped with directly georeferenced RGB-frame cameras and hyperspectral push-broom scanners, for precision agriculture and high-throughput phenotyping is an important application that is gaining significant attention from researchers in the mapping and plant science fields. The advantages of UAVs as mobile-mapping platforms include low cost, ease of storage and deployment, ability to fly lower and collect high-resolution data, and filling an important gap between wheel-based and manned-airborne platforms. However, limited endurance and payload are the main disadvantages of consumer-grade UAVs. These limitations lead to the adoption of low-quality direct georeferencing and imaging systems, which in turn will impact the quality of the delivered products. Thanks to recent advances in sensor calibration and automated triangulation, accurate mapping using low-cost frame imaging systems equipped with consumer-grade georeferencing units is feasible. Unfortunately, the quality of derived geospatial information from push-broom scanners is quite sensitive to the performance of the implemented direct georeferencing unit. This paper presents an approach for improving the orthorectification of hyperspectral push-broom scanner imagery with the help of generated orthophotos from frame cameras using tie point and linear features, while modeling the impact of residual artifacts in the direct georeferencing information. The performance of the proposed approach has been verified through real datasets that have been collected by quadcopter and fixed-wing UAVs over an agricultural field.

Active-Metric Learning for Classification of Remotely Sensed Hyperspectral Images

Classification of remotely sensed hyperspectral images via supervised approaches is typically affected by high dimensionality of the spectral data and a limited number of labeled samples. Dimensionality reduction via feature extraction and active learning (AL) are two approaches that researchers have investigated independently to deal with these two problems. In this paper, we propose a new method in which the feature extraction and AL steps are combined into a unique framework. The idea is to learn and update a reduced feature space in a supervised way at each iteration of the AL process, thus taking advantage of the increasing labeled information provided by the user. In particular, the computation of the reduced feature space is based on the large-margin nearest neighbor (LMNN) metric learning principle. This strategy is applied in conjunction with k-nearest neighbor ( k-NN) classification, for which a new sample selection strategy is proposed. The methodology is validated experimentally on four benchmark hyperspectral data sets. Good improvements in terms of classification accuracy and computational time are achieved with respect to the state-of-the-art strategies that do not combine feature extraction and AL.

Exploiting spectral-spatial proximity for classification of hyperspectral data on manifolds

Similarity measures for classification of hyperspectral data in the manifold space are typically based on spectral characteristics. However, samples that are not spectrally separable may cause incorrectly connected graphs and result in noninformative data manifolds. Spatial relationships inherent in remote sensing images can be beneficial for constructing connectivity graphs. A spectral-spatial proximity graph utilizing both spectral characteristics and spatial homogeneity is proposed for robust manifold learning. With the proposed spectral-spatial graph, we are able to extract essential features and preserve important knowledge in a lower dimensional manifold space, where classification tasks can be performed effectively. Two hyperspectral data sets were used to validate the proposed approach. Classification results obtained by the nearest neighbor classifier demonstrate the usefulness of exploiting spectral similarity and spatial proximity for the manifold-based classification.

Learning a joint manifold with global-local preservation for multitemporal hyperspectral image classification

Adapting a pre-trained classifier with labeled samples from an image for classification of another temporally related image is a common multitemporal image classification strategy. However, the adaptation is not effective when the spectral drift exhibited in temporal data is significant. Instead of iteratively redefining classifier parameters, we exploit similar data geometries of temporal data and project temporal data into a joint manifold space where similar samples are clustered. The proposed classification framework is based on aligning global temporal data manifolds. In addition to global structures, we also consider the local scale by incorporating local point relations into the alignment process. In experiments with challenging temporal hyperspectral data, the proposed framework provides favorable classification results, compared to the baseline.

Multimetric Active Learning for Classification of Remote Sensing Data

The classification of hyperspectral and multimodal remote sensing data is affected by two key problems: the high dimensionality of the input data and the limited number of the labeled samples. In this letter, a multimetric learning approach that combines feature extraction and active learning (AL) is introduced to deal with these two issues simultaneously. In particular, distinct metrics are assigned to different types of features and then learned jointly. In this way, multiple features are projected into a common feature space, in which AL is then performed in conjunction with k- nearest neighbor classification to enrich the set of labeled samples. Experiments on two sets of remote sensing data illustrate the effectiveness of the proposed framework in terms of both classification accuracy and computational requirements.