Action Recognition Using a Bio-Inspired Feedforward Spiking Network

We propose a bio-inspired feedforward spiking network modeling two brain areas dedicated to motion (V1 and MT), and we show how the spiking output can be exploited in a computer vision application: action recognition. In order to analyze spike trains, we consider two characteristics of the neural code: mean firing rate of each neuron and synchrony between neurons. Interestingly, we show that they carry some relevant information for the action recognition application. We compare our results to Jhuang et al. (Proceedings of the 11th international conference on computer vision, pp. 1–8, 2007) on the Weizmann database. As a conclusion, we are convinced that spiking networks represent a powerful alternative framework for real vision applications that will benefit from recent advances in computational neuroscience.     

Regularized estimation of bathymetry and water quality using hyperspectral remote sensing

Coastal water mapping from remote-sensing hyperspectral data suffers from poor retrieval performance when the targeted parameters have little effect on subsurface reflectance, especially due to the ill-posed nature of the inversion problem. For example, depth cannot accurately be retrieved for deep water, where the bottom influence is negligible. Similarly, for very shallow water it is difficult to estimate the water quality because the subsurface reflectance is affected more by the bottom than by optically active water components.

Most methods based on radiative transfer model inversion do not consider the distribution of targeted parameters within the inversion process, thereby implicitly assuming that any parameter value in the estimation range has the same probability. In order to improve the estimation accuracy for the above limiting cases, we propose to regularize the objective functions of two estimation methods (maximum likelihood or ML, and hyperspectral optimization process exemplar, or HOPE) by introducing local prior knowledge on the parameters of interest. To do so, loss functions are introduced into ML and HOPE objective functions in order to reduce the range of parameter estimation. These loss functions can be characterized either by using prior or expert knowledge, or by inferring this knowledge from the data (thus avoiding the use of additional information).

This approach was tested both on simulated and real hyperspectral remote-sensing data. We show that the regularized objective functions are more peaked than their non-regularized counterparts when the parameter of interest has little effect on subsurface reflectance. As a result, the estimation accuracy of regularized methods is higher for these depth ranges. In particular, when evaluated on real data, these methods were able to estimate depths up to 20 m, while corresponding non-regularized methods were accurate only up to 13 m on average for the same data.

This approach thus provides a solution to deal with such difficult estimation conditions. Furthermore, because no specific framework is needed, it can be extended to any estimation method that is based on iterative optimization.     

Adjacent versus coincident representations of geospatial uncertainty: Which promote better decisions?

3D geological models commonly built to manage natural resources are much affected by uncertainty because most of the subsurface is inaccessible to direct observation. Appropriate ways to intuitively visualize uncertainties are therefore critical to draw appropriate decisions. However, empirical assessments of uncertainty visualization for decision making are currently limited to 2D map data, while most geological entities are either surfaces embedded in a 3D space or volumes.This paper first reviews a typical example of decision making under uncertainty, where uncertainty visualization methods can actually make a difference. This issue is illustrated on a real Middle East oil and gas reservoir, looking for the optimal location of a new appraisal well. In a second step, we propose a user study that goes beyond traditional 2D map data, using 2.5D pressure data for the purposes of well design. Our experiments study the quality of adjacent versus coincident representations of spatial uncertainty as compared to the presentation of data without uncertainty; the representations' quality is assessed in terms of decision accuracy. Our study was conducted within a group of 123 graduate students specialized in geology.     

Efficient search of combinatorial maps using signatures

In this paper, we address the problem of computing canonical representations of n-dimensional combinatorial maps and of using them for efficiently searching for a map in a database. We define two combinatorial map signatures: the first one has a quadratic space complexity and may be used to decide an isomorphism with a new map in linear time whereas the second one has a linear space complexity and may be used to decide an isomorphism in quadratic time. We show that these signatures can be used to efficiently search for a map in a database.     

Loop Shifting for Loop Compaction

The idea of decomposed software pipelining is to decouple the software pipelining problem into a cyclic scheduling problem without resource constraints and an acyclic scheduling problem with resource constraints. In terms of loop transformation and code motion, the technique can be formulated as a combination of loop shifting and loop compaction. Loop shifting amounts to moving statements between iterations thereby changing some loop independent dependences into loop carried dependences and vice versa. Then, loop compaction schedules the body of the loop considering only loop independent dependences, but taking into account the details of the target architecture. In this paper, we show how loop shifting can be optimized so as to minimize both the length of the critical path and the number of dependences for loop compaction. The first problem is well-known and can be solved by an algorithm due to Leiserson and Saxe. We show that the second optimization (and the combination with the first one) is also polynomially solvable with a fast graph algorithm, variant of minimum-cost flow algorithms. Finally, we analyze the improvements obtained on loop compaction by experiments on random graphs.     

Improving virus protection with an efficient secure architecture with memory encryption, integrity and information leakage protection

Malicious software and other attacks are a major concern in the computing ecosystem and there is a need to go beyond the answers based on untrusted software. Trusted and secure computing can add a new hardware dimension to software protection. Several secure computing hardware architectures using memory encryption and memory integrity checkers have been proposed during the past few years to provide applications with a tamper resistant environment. Some solutions, such as HIDE, have also been proposed to solve the problem of information leakage on the address bus. We propose the CRYPTOPAGE architecture which implements memory encryption, memory integrity protection checking and information leakage protection together with a low performance penalty (3% slowdown on average) by combining the Counter Mode of operation, local authentication values and MERKLE trees. It has also several other security features such as attestation, secure storage for applications and program identification. We present some applications of the CRYPTOPAGE architecture in the computer virology field as a proof of concept of improving security in presence of viruses compared to software only solutions.     

Testing Planning Domains (without Model Checkers)

We address the problem of verifying planning domains as used in model-based planning, for example in space missions. We propose a methodology for testing flight rules of planning domains which is self-contained, in the sense that flight rules are verified using a planner and no external tools are required. We review and analyse coverage conditions for requirements-based testing, and we reason in detail on "Unique First Cause" (UFC) coverage for test suites. We characterise flight rules using patterns, encoded using LTL, and we provide UFC coverage for them. We then present a translation of LTL formulae into planning goals, and illustrate our approach on a case study.     

How do interactive tabletop systems influence collaboration?

This paper examines some aspects of the usefulness of interactive tabletop systems, if and how these impact collaboration. We chose creative problem solving such as brainstorming as an application framework to test several collaborative media: the use of pen-and-paper tools, the “around-the-table” form factor, the digital tabletop interface, the attractiveness of interaction styles. Eighty subjects in total (20 groups of four members) participated in the experiments. The evaluation criteria were task performance, collaboration patterns (especially equity of contributions), and users’ subjective experience. The “around-the-table” form factor, which is hypothesized to promote social comparison, increased performance and improved collaboration through an increase of equity. Moreover, the attractiveness of the tabletop device improved subjective experience and increased motivation to engage in the task. However, designing attractiveness seems a highly challenging issue, since overly attractive interfaces may distract users from the task.     

3D model based tracking for omnidirectional vision: A new spherical approach

The current work addresses the problem of 3D model tracking in the context of monocular and stereo omnidirectional vision in order to estimate the camera pose. To this end, we track 3D objects modeled by line segments because the straight line feature is often used to model the environment. Indeed, we are interested in mobile robot navigation using omnidirectional vision in structured environments. In the case of omnidirectional vision, 3D straight lines are projected as conics in omnidirectional images. Under certain conditions, these conics may have singularities.In this paper, we present two contributions. We, first, propose a new spherical formulation of the pose estimation withdrawing singularities, using an object model composed of lines. The theoretical formulation and the validation on synthetic images thus show that the new formulation clearly outperforms the former image plane one. The second contribution is the extension of the spherical representation to the stereovision case. We consider in the paper a sensor which combines a camera and four mirrors. Results in various situations show the robustness to illumination changes and local mistracking. As a final result, the proposed new stereo spherical formulation allows us to localize online a robot indoor and outdoor whereas the classical formulation fails.