PURSUIT (Projection Understanding and recognition from a SUite of intelligent Tools) has been under development at the Naval Research Laboratory for a number of years. It is a versatile software tool designed to addre...
详细信息
PURSUIT (Projection Understanding and recognition from a SUite of intelligent Tools) has been under development at the Naval Research Laboratory for a number of years. It is a versatile software tool designed to address the problem of automatic feature extraction and classification from remotesensing data. Although the tool can be applied to a variety of applications outside of the field of remotesensing, it is particularly useful for automated remotesensingimagery analysis. To date, the package has been applied to imagery from a variety of different sensor types including: multispectral, hyperspectral, synthetic aperture radar (SAR), and multi-sensor data. Because of its modular design, PURSUIT is re-configurable and the suite of algorithms that comprise it can be flexibly combined to address new applications as they arise. As such, new algorithms can be easily added. Algorithms included in the present corpus consist of a variety of in-house algorithms, as well as standard algorithms derived from many areas of the statistical patternrecognition literature, including adaptive vector quantization, unsupervised and supervised feature extraction and classification, and neural networks. Each module contains a number of different preprocessing and post-processing options, and the input data may be spectral, spatial, or spatial-spectral. The modular design of the package allows data from multiple sources to be combined in the same overall automatic classification model.
Range images (depth maps) are seeing increased usage in a variety of application areas including entertainment, industrial automation, inspection, remotesensing, and military tactical planning. As the corpus of range...
详细信息
Range images (depth maps) are seeing increased usage in a variety of application areas including entertainment, industrial automation, inspection, remotesensing, and military tactical planning. As the corpus of range imagery increases in size and the need to communicate such images over fixed-bandwidth channels increases, the compression of range data deserves investigation. Since the geometry encoded by range sensors is inherently "low-bandwidth", transform-based techniques seem appropriate for investigation in this context. This paper reports on experiments with a popular zerotree-based image codec (the SPIHT algorithm developed by Said and Pearlman) and its application to the compression of range imagery. Experiments suggest that compression rates of 1 bit/pixel and below are achievable with minimal impact on fidelity.
remotesensing produces large amounts of digital data that is collected into databases. Since a variety of applications utilize multispectral data, the data cannot be compressed with lossy methods for some user commun...
详细信息
remotesensing produces large amounts of digital data that is collected into databases. Since a variety of applications utilize multispectral data, the data cannot be compressed with lossy methods for some user communities. In this paper, we propose improvements for the combination of two reversible methods for the lossless compression of multispectral images. Our improvements are three-fold: number of bits allocated to the coefficients from PCA is not constant but it is based on heuristics, difference between consecutive coefficients are entropy-coded, also the back-end is modified so that all bands are separately entropy coded, i.e. instead of one entropy coder we used several. Depending on the AVIRIS image, the actual compression ratios, calculated from the files sizes, were in the range from 3.05 to 3.21.
We investigate the behavior knowledge space method (see Xu, L. et al., IEEE Transactions SMC, vol.22, no.3, p.418-35, 1992) and decision templates method (see Kuncheva, L. et al., patternrecognition, vol.34, p.299-31...
详细信息
We investigate the behavior knowledge space method (see Xu, L. et al., IEEE Transactions SMC, vol.22, no.3, p.418-35, 1992) and decision templates method (see Kuncheva, L. et al., patternrecognition, vol.34, p.299-314, 2001) of classifier fusion in the context of face verification. The study involves six experts which are not only correlated, but also their performance levels differ by as much as a factor of three. Through extensive experiments on the XM2VTS database using the Lausanne protocol, we found that the behavior knowledge space fusion strategy achieved consistently better results than the decision templates method. Most importantly, it exhibited quasi monotonic behavior as the number of experts combined increased. This is a very important conclusion, as it means that the performance of the multimodal system is not degraded by adding experts.
In the past decade, several rules for fusion of pattern classifiers' outputs have been proposed. Although imbalanced classifiers, that is, classifiers exhibiting very different accuracy, are used in many practical...
详细信息
In the past decade, several rules for fusion of pattern classifiers' outputs have been proposed. Although imbalanced classifiers, that is, classifiers exhibiting very different accuracy, are used in many practical applications (e.g., multimodal biometrics for personal identity verification), the conditions of classifiers' imbalance under which a given rule can significantly outperform another one are not completely clear. In this paper, we experimentally compare various fixed and trained rules for fusion of imbalanced classifiers. The experiments are guided by the results of a previous theoretical analysis of the authors. Linear, order statistics-based, and trained combiners are compared by experiments on remote-sensingimage data and on the X2M2VTS multimodal biometrics data base.
A relative entropic thresholding approach was recently developed by Chang et al. (see patternrecognition, vol. 27, no. 9, p. 1275-1289, 1994). This paper extends Chang et al.'s approach to two more relative entro...
详细信息
A relative entropic thresholding approach was recently developed by Chang et al. (see patternrecognition, vol. 27, no. 9, p. 1275-1289, 1994). This paper extends Chang et al.'s approach to two more relative entropy-based thresholding methods, called local relative entropy thresholding (LRE) and joint relative entropy thresholding (JRE). Since relative entropy based methods are sensitive to sparse image histograms, a histogram compression and translation is suggested to compact the histogram. In order to achieve an objective assessment, uniformity and shape measures are introduced for performance evaluation. Experimental results show that when image histograms are sparse, with the proposed histogram compression and translation, JRE and LRE generally perform better than Chang et al.'s approach.
Spatial relationships among image objects play a vital role in countless domains of computer vision (e.g., patternrecognition, image understanding, scene description). Some have received considerable attention the la...
详细信息
Spatial relationships among image objects play a vital role in countless domains of computer vision (e.g., patternrecognition, image understanding, scene description). Some have received considerable attention the last few years (e.g., "to the right of," "above," "to the left of" and "below"), but others have not been the subject of as much investigation. In this paper, we design consistent fuzzy models of three important spatial relationships: "surrounded by," "between" and "among." These models are based on the histogram of forces, which represents the relative position between two objects. Here, force histograms are assimilated to fuzzy sets and processed through their /spl alpha/-cuts. Our goal is to extend the capabilities of a fuzzy system for linguistic scene description introduced in an earlier paper.
In this paper we deal with the problem of texture segmentation using a joint spectral and spatial analysis of pixel distribution. Hyperspectral images are considered and, using a Markovian model, we develop a vectoria...
详细信息
In this paper we deal with the problem of texture segmentation using a joint spectral and spatial analysis of pixel distribution. Hyperspectral images are considered and, using a Markovian model, we develop a vectorial approach for this image type. A classification algorithm using this model was implemented for extracting and classifying urban areas. Results obtained from AVIRIS images are shown.
A scheme for detecting edges and lines in multichannel SAR images is proposed. The line detector is constructed from the edge detector. The latter is based on multivariate statistical hypothesis tests applied to log-i...
详细信息
ISBN:
(纸本)076951695X
A scheme for detecting edges and lines in multichannel SAR images is proposed. The line detector is constructed from the edge detector. The latter is based on multivariate statistical hypothesis tests applied to log-intensity SAR images. The raw results are vectorized by a traditional bright line extraction process. The scheme is illustrated by extracting dark linear structures on various full-polarimetric SAR images.
With its combination of good spatial and spectral resolution, visible to near infrared spectral imaging from aircraft or spacecraft is a highly valuable technology for remotesensing of the Earth's surface. Typica...
详细信息
With its combination of good spatial and spectral resolution, visible to near infrared spectral imaging from aircraft or spacecraft is a highly valuable technology for remotesensing of the Earth's surface. Typically it is desirable to eliminate atmospheric effects on the imagery, a process known as atmospheric correction. We review the basic methodology of first-principles atmospheric correction and present results from the latest version of the FLAASH (fast line-of-sight atmospheric analysis of spectral hypercubes) algorithm. We show some comparisons of ground truth spectra with FLAASH-processed AVIRIS (airborne visible/infrared imaging spectrometer) data, including results obtained using different processing options, and with results from the ACORN (atmospheric correction now) algorithm that derive from an older MODTRAN4 spectral database.
暂无评论