A Bayesian approach to object detection using probabilistic appearance-based models

In this paper, we introduce a Bayesian approach, inspired by probabilistic principal component analysis (PPCA) (Tipping and Bishop in J Royal Stat Soc Ser B 61(3):611–622, 1999), to detect objects in complex scenes using appearance-based models. The originality of the proposed framework is to explicitly take into account general forms of the underlying distributions, both for the in-eigenspace distribution and for the observation model. The approach combines linear data reduction techniques (to preserve computational efficiency), non-linear constraints on the in-eigenspace distribution (to model complex variabilities) and non-linear (robust) observation models (to cope with clutter, outliers and occlusions). The resulting statistical representation generalises most existing PCA-based models (Tipping and Bishop in J Royal Stat Soc Ser B 61(3):611–622, 1999; Black and Jepson in Int J Comput Vis 26(1):63–84, 1998; Moghaddam and Pentland in IEEE Trans Pattern Anal Machine Intell 19(7):696–710, 1997) and leads to the definition of a new family of non-linear probabilistic detectors. The performance of the approach is assessed using receiver operating characteristic (ROC) analysis on several representative databases, showing a major improvement in detection performances with respect to the standard methods that have been the references up to now.This revised version was published online in November 2004 with corrections to the section numbers.     

Parallel Ant Colony Optimization on Graphics Processing Units

The purpose of this paper is to propose effective parallelization strategies for the Ant Colony Optimization (ACO) metaheuristic on Graphics Processing Units (GPUs). The Max–Min Ant System (MMAS) algorithm augmented with 3-opt local search is used as a framework for the implementation of the parallel ants and multiple ant colonies general parallelization approaches. The four resulting GPU algorithms are extensively evaluated and compared on both speedup and solution quality on a state-of-the-art Fermi GPU architecture. A rigorous effort is made to keep parallel algorithms true to the original MMAS applied to the Traveling Salesman Problem. We report speedups of up to 23.60 with solution quality similar to the original sequential implementation. With the intent of providing a parallelization framework for ACO on GPUs, a comparative experimental study highlights the performance impact of ACO parameters, GPU technical configuration, memory structures and parallelization granularity.     

A conceptual framework to define the spatial resolution requirements for agricultural monitoring using remote sensing

Satellite remote sensing is an invaluable tool to monitor agricultural resources. However, spatial patterns in agricultural landscapes vary significantly across the Earth resulting in different imagery requirements depending on what part of the globe is observed. Furthermore, there is an increasing diversity of Earth observation instruments providing imagery with various configurations of spatial, temporal, spectral and angular resolutions. In terms of spatial resolution, the choice of imagery should be conditioned by knowing the appropriate spatial frequency at which the landscape must be sampled with the imaging instrument in order to provide the required information from the targeted fields. This paper presents a conceptual framework to define quantitatively such requirements for both crop area estimation and crop growth monitoring based on user-defined constraints. The methodological development is based on simulating how agricultural landscapes, and more specifically the fields covered by a crop of interest, are seen by instruments with increasingly coarser resolving power. The results are provided not only in terms of acceptable pixel size but also of pixel purity which is the degree of homogeneity with respect to the target crop. This trade-off between size and purity can be adjusted according to the end-user's requirements. The method is implemented over various agricultural landscapes with contrasting spatial patterns, demonstrating its operational applicability. This diagnostic approach can be used: (i) to guide users in choosing the most appropriate imagery for their application, (ii) to evaluate the adequacy of existing remote sensing systems for monitoring agriculture in different regions of the world and (iii) to provide guidelines for space agencies to design future instruments dedicated to agriculture monitoring.     

On testing for serial correlation of unknown form using wavelet thresholding

Omnibus procedures for testing serial correlation are developed, using spectral density estimation and wavelet shrinkage. The asymptotic distributions of the wavelet coefficients under the null hypothesis of no serial correlation are derived. Under some general conditions on the wavelet basis, the wavelet coefficients asymptotically follow a normal distribution. Furthermore, they are asymptotically uncorrelated. Adopting a spectral approach and using results on wavelet shrinkage, new one-sided test statistics are proposed. As a spatially adaptive estimation method, wavelets can effectively detect fine features in the spectral density, such as sharp peaks and high frequency alternations. Using an appropriate thresholding parameter, shrinkage rules are applied to the empirical wavelet coefficients, resulting in a non-linear wavelet-based spectral density estimator. Consequently, the advocated approach avoids the need to select the finest scale J, since the noise in the wavelet coefficients is naturally suppressed. Simple data-dependent threshold parameters are also considered. In general, the convergence of the spectral test statistics toward their respective asymptotic distributions appears to be relatively slow. In view of that, Monte Carlo methods are investigated. In a small simulation study, several spectral test statistics are compared, with respect to level and power, including versions of these test statistics using Monte Carlo simulations.     

Interactive tabletops in education

Interactive tabletops are gaining increased attention from CSCL researchers. This paper analyses the relation between this technology and teaching and learning processes. At a global level, one could argue that tabletops convey a socio-constructivist flavor: they support small teams that solve problems by exploring multiple solutions. The development of tabletop applications also witnesses the growing importance of face-to-face collaboration in CSCL and acknowledges the physicality of learning. However, this global analysis is insufficient. To analyze the educational potential of tabletops in education, we present 33 points that should be taken into consideration. These points are structured on four levels: individual user-system interaction, teamwork, classroom orchestration, and socio-cultural contexts. God lies in the details.     

A survey of models and algorithms for emergency response logistics in electric distribution systems. Part I: Reliability planning with fault considerations

Emergency response operations in electric distribution systems involve a host of decision-making problems at the reliability and contingency planning levels. Those operations include fault diagnosis, fault location, fault isolation, restoration, and repair. As the first of a two-part survey, this paper reviews optimization models and solution methodologies for reliability planning problems with fault considerations related to electric distribution operations. Contingency planning problems of emergency distribution response are discussed in the second part. The present paper surveys research on determining a distribution substation single-fault capacity, reallocating excess load, configuring distribution systems, partitioning a geographical area into service territories, and locating material stores and depots.     

Autonomous car decision making and trajectory tracking based on genetic algorithms and fractional potential fields

Intelligent Service Robotics - This article deals with the issue of trajectory optimization of autonomous terrestrial vehicles on a specific range handled by the human driver. The main...     

Simpler PAC-Bayesian bounds for hostile data

PAC-Bayesian learning bounds are of the utmost interest to the learning community. Their role is to connect the generalization ability of an aggregation distribution \(\rho \) to its empirical risk and to its Kullback-Leibler divergence with respect to some prior distribution \(\pi \). Unfortunately, most of the available bounds typically rely on heavy assumptions such as boundedness and independence of the observations. This paper aims at relaxing these constraints and provides PAC-Bayesian learning bounds that hold for dependent, heavy-tailed observations (hereafter referred to as hostile data). In these bounds the Kullack-Leibler divergence is replaced with a general version of Csiszár’s f-divergence. We prove a general PAC-Bayesian bound, and show how to use it in various hostile settings.