Stefan Uhlmann

Integrating Color Features in Polarimetric SAR Image Classification

Polarimetric synthetic aperture radar (PolSAR) data are used extensively for terrain classification applying SAR features from various target decompositions and certain textural features. However, one source of information has so far been neglected from PolSAR classification: Color. It is a common practice to visualize PolSAR data by color coding methods and thus, it is possible to extract powerful color features from such pseudocolor images so as to provide additional data for a superior terrain classification. In this paper, we first review previous attempts for PolSAR classifications using various feature combinations and then we introduce and perform in-depth investigation of the application of color features over the Pauli color-coded images besides SAR and texture features. We run an extensive set of comparative evaluations using 24 different feature set combinations over three images of the Flevoland- and the San Francisco Bay region from the RADARSAT-2 and the AIRSAR systems operating in C- and L-bands, respectively. We then consider support vector machines and random forests classifier topologies to test and evaluate the role of color features over the classification performance. The classification results show that the additional color features introduce a new level of discrimination and provide noteworthy improvement in classification performance (compared with the traditionally employed PolSAR and texture features) within the application of land use and land cover classification.

Personalization algorithms for portable personality

With the advances in ubiquitous computing, there is an increasing focus on personalization of user information especially in web applications. Currently those personalized user profiles are scattered around the Internet, mostly stored for each individual website. Therefore, this prohibits the usage of those profiles in other environments such as shopping in local stores or sharing interests among people. The so-called Portable Personality focuses on the management and distribution of personalized profiles via mobile devices. This paper provides an overview of related factors, which are to be considered in a portable personality environment. We discuss common user profile categorization approaches and their possible representation. Moreover, we mention the current state-of-the-art of profile acquisition and management algorithms to obtain and handle personalized information. This also includes approaches towards portable profiles. At the end, profile merging and personalization algorithms are covered to handle the challenges of aggregate multiple profiles and personalized recommendations based on distributed (portable) profiles.

Collective Network of Binary Classifier Framework for Polarimetric SAR Image Classification: An Evolutionary Approach

Terrain classification over polarimetric synthetic aperture radar (SAR) images has been an active research field where several features and classifiers have been proposed up to date. However, some key questions, e.g., 1) how to select certain features so as to achieve highest discrimination over certain classes?, 2) how to combine them in the most effective way?, 3) which distance metric to apply?, 4) how to find the optimal classifier configuration for the classification problem in hand?, 5) how to scale/adapt the classifier if large number of classes/features are present?, and finally, 6) how to train the classifier efficiently to maximize the classification accuracy?, still remain unanswered. In this paper, we propose a collective network of (evolutionary) binary classifier (CNBC) framework to address all these problems and to achieve high classification performance. The CNBC framework adapts a “Divide and Conquer” type approach by allocating several NBCs to discriminate each class and performs evolutionary search to find the optimal BC in each NBC. In such an (incremental) evolution session, the CNBC body can further dynamically adapt itself with each new incoming class/feature set without a full-scale retraining or reconfiguration. Both visual and numerical performance evaluations of the proposed framework over two benchmark SAR images demonstrate its superiority and a significant performance gap against several major classifiers in this field.

Dominant Color Extraction Based on Dynamic Clustering by Multi-dimensional Particle Swarm Optimization

Color is the major source of information widely used in image analysis and content-based retrieval. Extracting dominant colors that are prominent in a visual scenery is of utter importance since human visual system primarily uses them for perception. In this paper we address dominant color extraction as a dynamic clustering problem and use techniques based on Particle Swarm Optimization (PSO) for finding optimal (number of) dominant colors in a given color space, distance metric and a proper validity index function. The first technique, so-called Multi-Dimensional (MD) PSO, re-forms the native structure of swarm particles in such a way that they can make inter-dimensional passes with a dedicated dimensional PSO process. Therefore, in a multidimensional search space where the optimum dimension is unknown, swarm particles can seek both positional and dimensional optima. Nevertheless, MD PSO is still susceptible to premature convergences due to lack of divergence. To address this problem we then present Fractional Global Best Formation (FGBF) technique, which basically collects all promising dimensional components and fractionally creates an artificial global-best particle (aGB) that has the potential to be a better “guide” than the PSO’s native gbest particle. We finally propose an efficient color distance metric, which uses a fuzzy model for computing color (dis-) similarities over HSV (or HSL) color space. The comparative evaluations against MPEG-7 dominant color descriptor show the superiority of the proposed technique.

Sport Type Classification of Mobile Videos

The recent proliferation of mobile video content has emphasized the need for applications such as automatic organization and automatic editing of videos. These applications could greatly benefit from domain knowledge about the content. However, extracting semantic information from mobile videos is a challenging task, due to their unconstrained nature. We extract domain knowledge about sport events recorded by multiple users, by classifying the sport type into soccer, American football, basketball, tennis, ice-hockey, or volleyball. We adopt a multi-user and multimodal approach, where each user simultaneously captures audio-visual content and auxiliary sensor data (from magnetometers and accelerometers). Firstly, each modality is separately analyzed; then, analysis results are fused for obtaining the sport type. The auxiliary sensor data is used for extracting more discriminative spatio-temporal visual features and efficient camera motion features. The contribution of each modality to the fusion process is adapted according to the quality of the input data. We performed extensive experiments on data collected at public sport events, showing the merits of using different combinations of modalities and fusion methods. The results indicate that analyzing multimodal and multi-user data, coupled with adaptive fusion, improves classification accuracies in most tested cases, up to 95.45%.

Evaluation of classifiers for polarimetric SAR classification

Polarimetric SAR data is been extensively used for the application of land use and land cover classification. Various classifier approaches have been applied to many different polarimetric images employing numerous features. In this paper, we want to provide an evaluation of commonly used supervised classifiers within the field of polarimetric SAR classification considering the effects of different number of training samples. Two polarimetric SAR images are considered representing an easier 4 class and more complex 15 class problem using a small set of eigen-decomposition features and tested with Neural Network, SVM, and Decision Tree classifiers. Results show that already rather small training sets can provide comparable results reducing the need for large labeled training data especially considering more challenging classification tasks. This can be further investigated in the area of semi-supervised learning.

Semi-Supervised Learning for Ill-Posed Polarimetric SAR Classification

In recent years, the interest in semi-supervised learning has increased, combining supervised and unsupervised learning approaches. This is especially valid for classification applications in remote sensing, while the data acquisition rate in current systems has become fairly large considering high- and very-high resolution data; yet on the other hand, the process of obtaining the ground truth data may be cumbersome for such large repositories. In this paper, we investigate the application of semi-supervised learning approaches and particularly focus on the small sample size problem. To that extend, we consider two basic unsupervised approaches by enlarging the initial labeled training set as well as an ensemble-based self-training method. We propose different strategies within self-training on how to select more reliable candidates from the pool of unlabeled samples to speed-up the learning process and to improve the classification performance of the underlying classifier ensemble. We evaluate the effectiveness of the proposed semi-supervised learning approach over polarimetric SAR data. Results show that the proposed self-training approach using an ensemble-based classifier that is initially trained over a small training set can achieve a similar performance level of a fully supervised learning approach where the training is performed over significantly larger labeled data. Considering the difficulties of the manual data labeling in such massive volumes of SAR repositories, this is indeed a promising accomplishment for semi-supervised SAR classification.

Incremental Learning with Support Vector Data Description

Due to the simplicity and firm mathematical foundation, Support Vector Machines (SVMs) have been intensively used to solve classification problems. However, training SVMs on real world large-scale databases is computationally costly and sometimes infeasible when the dataset size is massive and non-stationary. In this paper, we propose an incremental learning approach that greatly reduces the time consumption and memory usage for training SVMs. The proposed method is fully dynamic, which stores only a small fraction of previous training examples whereas the rest can be discarded. It can further handle unseen labels in new training batches. The classification experiments show that the proposed method achieves the same level of classification accuracy as batch learning while the computational cost is significantly reduced, and it can outperform other incremental SVM approaches for the new class problem.

Collective network of evolutionary binary classifiers for content-based image retrieval

The content-based image retrieval (CBIR) has been an active research field for which several feature extraction, classification and retrieval techniques have been proposed up to date. However, when the database size grows larger, it is a common fact that the overall retrieval performance significantly deteriorates. In this paper, we propose collective network of (evolutionary) binary classifiers (CNBC) framework to achieve a high retrieval performance even though the training (ground truth) data may not be entirely present from the beginning and thus the system can only be trained incrementally. The CNBC framework basically adopts a “Divide and Conquer” type approach by allocating several networks of binary classifiers (NBCs) to discriminate each class and performs evolutionary search to find the optimal binary classifier (BC) in each NBC. In such an evolution session, the CNBC body can further dynamically adapt itself with each new incoming class/feature set without a full-scale re-training or re-configuration. Both visual and numerical performance evaluations of the proposed framework over benchmark image databases demonstrate its scalability; and a significant performance improvement is achieved over traditional retrieval techniques.

Polarimetric SAR classification using visual color features extracted over pseudo color images

Polarimetric SAR data have been used extensively for terrain classification applying primitives from various target decompositions as well as texture features. However, there is a source of information that has been neglected so far from polarimetric SAR classification: Color. It is a common practice to visualize polarimetric SAR data by color coding methods and thus it is possible to extract powerful color features from such pseudocolor images. In this paper, we investigate and evaluate discrimination power of color features extracted over various pseudocolor images. Experiments are conducted over the San Francisco Bay region on RADARSAT-2 data by using Support Vector Machines. The classification results show that the additional color features introduce a new level of discrimination and provide noteworthy improvement in classification performance (compared to the traditionally employed polarimetric SAR and texture features) within the application of land use and land cover classification.