Large scale SLAM with visual features

Comunicación presentada en el X Workshop of Physical Agents, Cáceres, 10-11 septiembre 2009.

Using GNG to improve 3D feature extraction—Application to 6DoF egomotion

Several recent works deal with 3D data in mobile robotic problems, e.g. mapping or egomotion. Data comes from any kind of sensor such as stereo vision systems, time of flight cameras or 3D lasers, providing a huge amount of unorganized 3D data. In this paper, we describe an efficient method to build complete 3D models from a Growing Neural Gas (GNG). The GNG is applied to the 3D raw data and it reduces both the subjacent error and the number of points, keeping the topology of the 3D data. The GNG output is then used in a 3D feature extraction method. We have performed a deep study in which we quantitatively show that the use of GNG improves the 3D feature extraction method. We also show that our method can be applied to any kind of 3D data. The 3D features obtained are used as input in an Iterative Closest Point (ICP)-like method to compute the 6DoF movement performed by a mobile robot. A comparison with standard ICP is performed, showing that the use of GNG improves the results. Final results of 3D mapping from the egomotion calculated are also shown.

Experiences Using an Open Source Sofware Library to Teach Computer Vision Subjects

Machine vision is an important subject in computer science and engineering degrees. For laboratory experimentation, it is desirable to have a complete and easy-to-use tool. In this work we present a Java library, oriented to teaching computer vision. We have designed and built the library from the scratch with enfasis on readability and understanding rather than on efficiency. However, the library can also be used for research purposes. JavaVis is an open source Java library, oriented to the teaching of Computer Vision. It consists of a framework with several features that meet its demands. It has been designed to be easy to use: the user does not have to deal with internal structures or graphical interface, and should the student need to add a new algorithm it can be done simply enough. Once we sketch the library, we focus on the experience the student gets using this library in several computer vision courses. Our main goal is to find out whether the students understand what they are doing, that is, find out how much the library helps the student in grasping the basic concepts of computer vision. In the last four years we have conducted surveys to assess how much the students have improved their skills by using this library.

Driver's enhanced vision systems (DEVS). Final report.

Federal Aviation Administration, Atlantic City International Airport, N.J.

Vision and visibility in highway driving; a bibliography.

Mode of access: Internet.

The Coordinated City’s Mutation Machine: Capitalism, Sympathy, and Urbanization in Seattle’s South Lake Union Neighborhood

Thesis (Ph.D.)--University of Washington, 2016-06

The correspondence framework for 3D surface matching algorithms

Beyond the inherent technical challenges, current research into the three dimensional surface correspondence problem is hampered by a lack of uniform terminology, an abundance of application specific algorithms, and the absence of a consistent model for comparing existing approaches and developing new ones. This paper addresses these challenges by presenting a framework for analysing, comparing, developing, and implementing surface correspondence algorithms. The framework uses five distinct stages to establish correspondence between surfaces. It is general, encompassing a wide variety of existing techniques, and flexible, facilitating the synthesis of new correspondence algorithms. This paper presents a review of existing surface correspondence algorithms, and shows how they fit into the correspondence framework. It also shows how the framework can be used to analyse and compare existing algorithms and develop new algorithms using the framework's modular structure. Six algorithms, four existing and two new, are implemented using the framework. Each implemented algorithm is used to match a number of surface pairs. Results demonstrate that the correspondence framework implementations are faithful implementations of existing algorithms, and that powerful new surface correspondence algorithms can be created. (C) 2004 Elsevier Inc. All rights reserved.

Automatic building detection using the Dempster-Shafer algorithm

An approach and strategy for automatic detection of buildings from aerial images using combined image analysis and interpretation techniques is described in this paper. It is undertaken in several steps. A dense DSM is obtained by stereo image matching and then the results of multi-band classification, the DSM, and Normalized Difference Vegetation Index (NDVI) are used to reveal preliminary building interest areas. From these areas, a shape modeling algorithm has been used to precisely delineate their boundaries. The Dempster-Shafer data fusion technique is then applied to detect buildings from the combination of three data sources by a statistically-based classification. A number of test areas, which include buildings of different sizes, shape, and roof color have been investigated. The tests are encouraging and demonstrate that all processes in this system are important for effective building detection.

Matching of catalogues by probabilistic pattern classification

We consider the statistical problem of catalogue matching from a machine learning perspective with the goal of producing probabilistic outputs, and using all available information. A framework is provided that unifies two existing approaches to producing probabilistic outputs in the literature, one based on combining distribution estimates and the other based on combining probabilistic classifiers. We apply both of these to the problem of matching the HI Parkes All Sky Survey radio catalogue with large positional uncertainties to the much denser SuperCOSMOS catalogue with much smaller positional uncertainties. We demonstrate the utility of probabilistic outputs by a controllable completeness and efficiency trade-off and by identifying objects that have high probability of being rare. Finally, possible biasing effects in the output of these classifiers are also highlighted and discussed.

Multisensorial obstacles detection and classification for ADAS and autonomous driving

A reliable perception of the real world is a key-feature for an autonomous vehicle and the Advanced Driver Assistance Systems (ADAS). Obstacles detection (OD) is one of the main components for the correct reconstruction of the dynamic world. Historical approaches based on stereo vision and other 3D perception technologies (e.g. LIDAR) have been adapted to the ADAS first and autonomous ground vehicles, after, providing excellent results. The obstacles detection is a very broad field and this domain counts a lot of works in the last years. In academic research, it has been clearly established the essential role of these systems to realize active safety systems for accident prevention, reflecting also the innovative systems introduced by industry. These systems need to accurately assess situational criticalities and simultaneously assess awareness of these criticalities by the driver; it requires that the obstacles detection algorithms must be reliable and accurate, providing: a real-time output, a stable and robust representation of the environment and an estimation independent from lighting and weather conditions. Initial systems relied on only one exteroceptive sensor (e.g. radar or laser for ACC and camera for LDW) in addition to proprioceptive sensors such as wheel speed and yaw rate sensors. But, current systems, such as ACC operating at the entire speed range or autonomous braking for collision avoidance, require the use of multiple sensors since individually they can not meet these requirements. It has led the community to move towards the use of a combination of them in order to exploit the benefits of each one. Pedestrians and vehicles detection are ones of the major thrusts in situational criticalities assessment, still remaining an active area of research. ADASs are the most prominent use case of pedestrians and vehicles detection. Vehicles should be equipped with sensing capabilities able to detect and act on objects in dangerous situations, where the driver would not be able to avoid a collision. A full ADAS or autonomous vehicle, with regard to pedestrians and vehicles, would not only include detection but also tracking, orientation, intent analysis, and collision prediction. The system detects obstacles using a probabilistic occupancy grid built from a multi-resolution disparity map. Obstacles classification is based on an AdaBoost SoftCascade trained on Aggregate Channel Features. A final stage of tracking and fusion guarantees stability and robustness to the result.

Binocular contrast vision at and above threshold

A fundamental problem for any visual system with binocular overlap is the combination of information from the two eyes. Electrophysiology shows that binocular integration of luminance contrast occurs early in visual cortex, but a specific systems architecture has not been established for human vision. Here, we address this by performing binocular summation and monocular, binocular, and dichoptic masking experiments for horizontal 1 cycle per degree test and masking gratings. These data reject three previously published proposals, each of which predict too little binocular summation and insufficient dichoptic facilitation. However, a simple development of one of the rejected models (the twin summation model) and a completely new model (the two-stage model) provide very good fits to the data. Two features common to both models are gently accelerating (almost linear) contrast transduction prior to binocular summation and suppressive ocular interactions that contribute to contrast gain control. With all model parameters fixed, both models correctly predict (1) systematic variation in psychometric slopes, (2) dichoptic contrast matching, and (3) high levels of binocular summation for various levels of binocular pedestal contrast. A review of evidence from elsewhere leads us to favor the two-stage model. © 2006 ARVO.

Binocular interaction:Contrast matching and contrast discrimination are predicted by the same model

How do signals from the 2 eyes combine and interact? Our recent work has challenged earlier schemes in which monocular contrast signals are subject to square-law transduction followed by summation across eyes and binocular gain control. Much more successful was a new 'two-stage' model in which the initial transducer was almost linear and contrast gain control occurred both pre- and post-binocular summation. Here we extend that work by: (i) exploring the two-dimensional stimulus space (defined by left- and right-eye contrasts) more thoroughly, and (ii) performing contrast discrimination and contrast matching tasks for the same stimuli. Twenty-five base-stimuli made from 1 c/deg patches of horizontal grating, were defined by the factorial combination of 5 contrasts for the left eye (0.3-32%) with five contrasts for the right eye (0.3-32%). Other than in contrast, the gratings in the two eyes were identical. In a 2IFC discrimination task, the base-stimuli were masks (pedestals), where the contrast increment was presented to one eye only. In a matching task, the base-stimuli were standards to which observers matched the contrast of either a monocular or binocular test grating. In the model, discrimination depends on the local gradient of the observer's internal contrast-response function, while matching equates the magnitude (rather than gradient) of response to the test and standard. With all model parameters fixed by previous work, the two-stage model successfully predicted both the discrimination and the matching data and was much more successful than linear or quadratic binocular summation models. These results show that performance measures and perception (contrast discrimination and contrast matching) can be understood in the same theoretical framework for binocular contrast vision. © 2007 VSP.

Interocular suppression and contrast gain control in human vision

The human visual system combines contrast information from the two eyes to produce a single cyclopean representation of the external world. This task requires both summation of congruent images and inhibition of incongruent images across the eyes. These processes were explored psychophysically using narrowband sinusoidal grating stimuli. Initial experiments focussed on binocular interactions within a single detecting mechanism, using contrast discrimination and contrast matching tasks. Consistent with previous findings, dichoptic presentation produced greater masking than monocular or binocular presentation. Four computational models were compared, two of which performed well on all data sets. Suppression between mechanisms was then investigated, using orthogonal and oblique stimuli. Two distinct suppressive pathways were identified, corresponding to monocular and dichoptic presentation. Both pathways impact prior to binocular summation of signals, and differ in their strengths, tuning, and response to adaptation, consistent with recent single-cell findings in cat. Strikingly, the magnitude of dichoptic masking was found to be spatiotemporally scale invariant, whereas monocular masking was dependent on stimulus speed. Interocular suppression was further explored using a novel manipulation, whereby stimuli were presented in dichoptic antiphase. Consistent with the predictions of a computational model, this produced weaker masking than in-phase presentation. This allowed the bandwidths of suppression to be measured without the complicating factor of additive combination of mask and test. Finally, contrast vision in strabismic amblyopia was investigated. Although amblyopes are generally believed to have impaired binocular vision, binocular summation was shown to be intact when stimuli were normalized for interocular sensitivity differences. An alternative account of amblyopia was developed, in which signals in the affected eye are subject to attenuation and additive noise prior to binocular combination.

The role of texture amplitude in shape from shading: evidence from a haptic matching task

The pattern of illumination on an undulating surface can be used to infer its 3-D form (shape from shading). But the recovery of shape would be invalid if the shading actually arose from reflectance variation. When a corrugated surface is painted with an albedo texture, the variation in local mean luminance (LM) due to shading is accompanied by a similar modulation in texture amplitude (AM). This is not so for reflectance variation, nor for roughly textured surfaces. We used a haptic matching technique to show that modulations of texture amplitude play a role in the interpretation of shape from shading. Observers were shown plaid stimuli comprising LM and AM combined in-phase (LM+AM) on one oblique and in anti-phase (LM-AM) on the other. Stimuli were presented via a modified ReachIN workstation allowing the co-registration of visual and haptic stimuli. In the first experiment, observers were asked to adjust the phase of a haptic surface, which had the same orientation as the LM+AM combination, until its peak in depth aligned with the visually perceived peak. The resulting alignments were consistent with the use of a lighting-from-above prior. In the second experiment, observers were asked to adjust the amplitude of the haptic surface to match that of the visually perceived surface. Observers chose relatively large amplitude settings when the haptic surface was oriented and phase-aligned with the LM+AM cue. When the haptic surface was aligned with the LM-AM cue, amplitude settings were close to zero. Thus the LM/AM phase relation is a significant visual depth cue, and is used to discriminate between shading and reflectance variations. [Supported by the Engineering and Physical Sciences Research Council, EPSRC].

The primal sketch revisited: locating and representing edges in human vision via Gaussian-derivative filtering

Marr's work offered guidelines on how to investigate vision (the theory - algorithm - implementation distinction), as well as specific proposals on how vision is done. Many of the latter have inevitably been superseded, but the approach was inspirational and remains so. Marr saw the computational study of vision as tightly linked to psychophysics and neurophysiology, but the last twenty years have seen some weakening of that integration. Because feature detection is a key stage in early human vision, we have returned to basic questions about representation of edges at coarse and fine scales. We describe an explicit model in the spirit of the primal sketch, but tightly constrained by psychophysical data. Results from two tasks (location-marking and blur-matching) point strongly to the central role played by second-derivative operators, as proposed by Marr and Hildreth. Edge location and blur are evaluated by finding the location and scale of the Gaussian-derivative `template' that best matches the second-derivative profile (`signature') of the edge. The system is scale-invariant, and accurately predicts blur-matching data for a wide variety of 1-D and 2-D images. By finding the best-fitting scale, it implements a form of local scale selection and circumvents the knotty problem of integrating filter outputs across scales. [Supported by BBSRC and the Wellcome Trust]