Biologically-inspired data decorrelation for hyper-spectral imaging

Hyper-spectral data allows the construction of more robust statistical models to sample the material properties than the standard tri-chromatic color representation. However, because of the large dimensionality and complexity of the hyper-spectral data, the extraction of robust features (image descriptors) is not a trivial issue. Thus, to facilitate efficient feature extraction, decorrelation techniques are commonly applied to reduce the dimensionality of the hyper-spectral data with the aim of generating compact and highly discriminative image descriptors. Current methodologies for data decorrelation such as principal component analysis (PCA), linear discriminant analysis (LDA), wavelet decomposition (WD), or band selection methods require complex and subjective training procedures and in addition the compressed spectral information is not directly related to the physical (spectral) characteristics associated with the analyzed materials. The major objective of this article is to introduce and evaluate a new data decorrelation methodology using an approach that closely emulates the human vision. The proposed data decorrelation scheme has been employed to optimally minimize the amount of redundant information contained in the highly correlated hyper-spectral bands and has been comprehensively evaluated in the context of non-ferrous material classification

Image-based delineation and classification of built heritage masonry

[EN]Fundación Zain is developing new built heritage assessment protocols. The goal is to objectivize and standardize the analysis and decision process that leads to determining the degree of protection of built heritage in the Basque Country. The ultimate step in this objectivization and standardization effort will be the development of an information and communication technology (ICT) tool for the assessment of built heritage. This paper presents the ground work carried out to make this tool possible: the automatic, image-based delineation of stone masonry. This is a necessary first step in the development of the tool, as the built heritage that will be assessed consists of stone masonry construction, and many of the features analyzed can be characterized according to the geometry and arrangement of the stones. Much of the assessment is carried out through visual inspection. Thus, this process will be automated by applying image processing on digital images of the elements under inspection. The principal contribution of this paper is the automatic delineation the framework proposed. The other contribution is the performance evaluation of this delineation as the input to a classifier for a geometrically characterized feature of a built heritage object. The element chosen to perform this evaluation is the stone arrangement of masonry walls. The validity of the proposed framework is assessed on real images of masonry walls.

A statistical investigation of fish prices in Nigeria

The main objective of this study is to describe and characterize the behaviour of fish prices in Nigeria. Drawing upon aspects of the data from a nationwide fish survey in 1980/81 and on various secondary data, the study analyses the pattern of fish price movement and makes projections of fish prices in Nigeria till 2002 A.D. It is concluded that unless efforts are directed at stemming inflation in fish prices, prices paid by fish consumers in Nigeria will be more than doubled within the next two decades

A combined statistical model for multiple motifs search

Transcription factor binding sites (TFBS) play key roles in genebior 6.8 wavelet expression and regulation. They are short sequence segments with de¯nite structure and can be recognized by the corresponding transcription factors correctly. From the viewpoint of statistics, the candidates of TFBS should be quite di®erent from the segments that are randomly combined together by nucleotide. This paper proposes a combined statistical model for ¯nding over- represented short sequence segments in di®erent kinds of data set. While the over-represented short sequence segment is described by position weight matrix, the nucleotide distribution at most sites of the segment should be far from the background nucleotide distribution. The central idea of this approach is to search for such kind of signals. This algorithm is tested on 3 data sets, including binding sites data set of cyclic AMP receptor protein in E.coli, PlantProm DB which is a non-redundant collection of proximal promoter sequences from di®erent species, collection of the intergenic sequences of the whole genome of E.Coli. Even though the complexity of these three data sets is quite di®erent, the results show that this model is rather general and sensible.

Fisheries statistical bulletin, Kainji Lake, northern Nigeria, 1997

The bulletin presents summary tables and charts on levels of fishing activity, fishing effort, yields and economic values of yields for the fisheries of Kainji Lake, Nigeria for the year 1997. Frame survey data and fishing gear measurements are also included. (PDF contains 34 pages)

Fisheries statistical bulletin, Kainji Lake, Nigeria, 1998

A tabulated summary is presented of the main fisheries data collected to date (1998) by the Nigerian-German Kainji Lake Fisheries Promotion Project, together with a current overview of the fishery. The data are given under the following sections: 1) Fishing localities and types; 2) Frame survey data; 3) Number of licensed fishermen by state; 4) Mesh size distribution; 5) Fishing net characteristics; 6) Fish yield; 7) Total annual fishing effort by gear type; 8) Total annual value of fish landed by gear type; 9) Graphs of effort and CPUE by gear type. (PDF contains 36 pages)

Fisheries statistical bulletin, Kainji Lake, Nigeria, 1999

A tabulated summary is presented of the main Lake Kainji fisheries data collected to date (1999) by the Nigerian-German Kainji Lake Fisheries Promotion Project, together with a current overview of the fishery. The data are given under the following sections: 1) Fishing localities and types; 2) Frame survey data; 3) Number of licensed fishermen by state; 4) Mesh size distribution; 5) Fishing net characteristics; 6) Fish yield; 7) Average monthly CPUE by gear type; 8)Average monthly fishing activity by gear type; 9) Total annual fishing effort by gear type; 10) Total annual value of fish landed by gear type; 11) Trends of the total yield by gear type. (PDF contains 34 pages)

Learning and using taxonomies for visual and olfactory classification

Humans are able of distinguishing more than 5000 visual categories even in complex environments using a variety of different visual systems all working in tandem. We seem to be capable of distinguishing thousands of different odors as well. In the machine learning community, many commonly used multi-class classifiers do not scale well to such large numbers of categories. This thesis demonstrates a method of automatically creating application-specific taxonomies to aid in scaling classification algorithms to more than 100 cate- gories using both visual and olfactory data. The visual data consists of images collected online and pollen slides scanned under a microscope. The olfactory data was acquired by constructing a small portable sniffing apparatus which draws air over 10 carbon black polymer composite sensors. We investigate performance when classifying 256 visual categories, 8 or more species of pollen and 130 olfactory categories sampled from common household items and a standardized scratch-and-sniff test. Taxonomies are employed in a divide-and-conquer classification framework which improves classification time while allowing the end user to trade performance for specificity as needed. Before classification can even take place, the pollen counter and electronic nose must filter out a high volume of background “clutter” to detect the categories of interest. In the case of pollen this is done with an efficient cascade of classifiers that rule out most non-pollen before invoking slower multi-class classifiers. In the case of the electronic nose, much of the extraneous noise encountered in outdoor environments can be filtered using a sniffing strategy which preferentially samples the visensor response at frequencies that are relatively immune to background contributions from ambient water vapor. This combination of efficient background rejection with scalable classification algorithms is tested in detail for three separate projects: 1) the Caltech-256 Image Dataset, 2) the Caltech Automated Pollen Identification and Counting System (CAPICS) and 3) a portable electronic nose specially constructed for outdoor use.

Robot navigation in dense crowds : statistical models and experimental studies of human robot cooperation

This thesis explores the problem of mobile robot navigation in dense human crowds. We begin by considering a fundamental impediment to classical motion planning algorithms called the freezing robot problem: once the environment surpasses a certain level of complexity, the planner decides that all forward paths are unsafe, and the robot freezes in place (or performs unnecessary maneuvers) to avoid collisions. Since a feasible path typically exists, this behavior is suboptimal. Existing approaches have focused on reducing predictive uncertainty by employing higher fidelity individual dynamics models or heuristically limiting the individual predictive covariance to prevent overcautious navigation. We demonstrate that both the individual prediction and the individual predictive uncertainty have little to do with this undesirable navigation behavior. Additionally, we provide evidence that dynamic agents are able to navigate in dense crowds by engaging in joint collision avoidance, cooperatively making room to create feasible trajectories. We accordingly develop interacting Gaussian processes, a prediction density that captures cooperative collision avoidance, and a "multiple goal" extension that models the goal driven nature of human decision making. Navigation naturally emerges as a statistic of this distribution.

Most importantly, we empirically validate our models in the Chandler dining hall at Caltech during peak hours, and in the process, carry out the first extensive quantitative study of robot navigation in dense human crowds (collecting data on 488 runs). The multiple goal interacting Gaussian processes algorithm performs comparably with human teleoperators in crowd densities nearing 1 person/m², while a state of the art noncooperative planner exhibits unsafe behavior more than 3 times as often as the multiple goal extension, and twice as often as the basic interacting Gaussian process approach. Furthermore, a reactive planner based on the widely used dynamic window approach proves insufficient for crowd densities above 0.55 people/m². We also show that our noncooperative planner or our reactive planner capture the salient characteristics of nearly any dynamic navigation algorithm. For inclusive validation purposes, we show that either our non-interacting planner or our reactive planner captures the salient characteristics of nearly any existing dynamic navigation algorithm. Based on these experimental results and theoretical observations, we conclude that a cooperation model is critical for safe and efficient robot navigation in dense human crowds.

Finally, we produce a large database of ground truth pedestrian crowd data. We make this ground truth database publicly available for further scientific study of crowd prediction models, learning from demonstration algorithms, and human robot interaction models in general.