Home
Fabio de Miranda's Library tagged → View Popular
Coevolution of Active Vision and feature Selection - Dario Floreano
We show that complex visual tasks, such as position- and size-invariant shape recognition and navigation in the environment, can be tackled with simple architectures generated by a coevolutionary process of active vision and feature selection. Behavioral machines equipped with primitive vision systems and direct pathways between visual and motor neurons are evolved while they freely interact with their environments.
RobotVision@ICPR | ImageCLEF - Image Retrieval in CLEF
The RobotVision task has been proposed to the ImageCLEF participants for the first time in 2009. The task attracted considerable attention, with 19 inscribed research groups, 7 groups eventually participating and a total of 27 submitted runs. The second edition of the RobotVision task will be part of the ImageCLEF@ICPR contest introducing new interesting challenges to the pattern recognition community.
The second edition of the RobotVision task addresses the problem of visual place classification. Specifically, participants will be asked to classify rooms and areas on the basis of image sequences, captured by a stereo camera mounted on a mobile robot within an office environment, under varying illumination conditions. The system built by the participants should be able to answer the question "where are you?" when presented with a test sequence imaging rooms seen during training (from different viewpoints and under different conditions) or additional rooms that were not imaged in the training sequence.
Artificial Intelligence and Robotics: A biologically-inspired vision system
Researchers at the Rowland Institute, Harvard, and McGovern Institute for Brain Sciences, MIT, are developing new, biologically-inspired vision systems taking advantage of faster computers. Their goal is to create vision systems for image understanding that can be as accurate as biological systems and more specifically the human visual system. The researchers have developed a new method that allows them to evaluate many different vision systems and quickly determine which are best suited for scene understanding. In a PLoS Computational Biology paper, the researchers show that their method performs better than current state-of-the-art computer vision systems when tested using standard data sets.
If you don't want to read the paper, then you should at least watch the below video in its entirety. In the video, lead researcher David Cox explains at a high level how biological vision works and how their computational system mimics it to achieve the results presented in the paper.
PLoS Computational Biology: Why is Real-World Visual Object Recognition Hard?
Progress in understanding the brain mechanisms underlying vision requires the construction of computational models that not only emulate the brain's anatomy and physiology, but ultimately match its performance on visual tasks. In recent years, “natural” images have become popular in the study of vision and have been used to show apparently impressive progress in building such models. Here, we challenge the use of uncontrolled “natural” images in guiding that progress. In particular, we show that a simple V1-like model—a neuroscientist's “null” model, which should perform poorly at real-world visual object recognition tasks—outperforms state-of-the-art object recognition systems (biologically inspired and otherwise) on a standard, ostensibly natural image recognition test. As a counterpoint, we designed a “simpler” recognition test to better span the real-world variation in object pose, position, and scale, and we show that this test correctly exposes the inadequacy of the V1-like model. Taken together, these results demonstrate that tests based on uncontrolled natural images can be seriously misleading, potentially guiding progress in the wrong direction. Instead, we reexamine what it means for images to be natural and argue for a renewed focus on the core problem of object recognition—real-world image variation.
robots.net - Robust Optical Flow Model Derived From Biology
Brinkworth and O'Carroll have come up with a new optical flow model, described in their paper, Robust Models for Optic Flow Coding in Natural Scenes Inspired by Insect Biology (PDF format). Their new system is based on the actual neural processing pathways of the fly which could prove to be a very robust velocity estimator and accurate sensor for self-motion in robots. CC-licensed image of female Tabanus Horse Fly by flickr user Thomas Shahan.
The Art of Jim Campbell: Seeing In Pixels - Boing Boing
Movement makes up for the lack of other visual information. Your brain can read and understand a video at much lower resolution than it would need to make equal sense of a still frame.
LPP - J. Kevin O'Regan
Papers about sensorimotor loop, situated perception, situated vision, enactive vision, visual contingencies
The evolution of object categorization and the challenge of image abstraction Sven Dickinson
PDF: Analyzing Vision at the Computational Level. J. K. Tsotsos
Excellent paper trying to apply computational complexity to analyze some visual tasks and a deep discussion following it.
Review of Visual Tracking
This report contains a review of visual tracking in monocular video sequences. For the purpose of this review, the majority of the visual trackers in the literature are divided into three tracking categories: discrete feature trackers, contour trackers, and region-based trackers. This categorization was performed based on the features used and the algorithms employed by the various visual trackers. The first class of trackers represents targets as discrete features (e.g. points, sets of points, lines) and performs data association using a distance metric that accommodates the particular feature.
Situated Vision in a Dynamic World: Chasing Objects
We describe a system that approaches and follows arbitrary moving objects in real time using vision as its only sense. The system uses multiple simple vision computations which, although individually unreliable, complement each other in a manner mediated by a situated control network.
Visual Attention Research: The FINST Visual Indexing Theory
Work related to Aaron Sloman ideas of registration along the optic array and also situated vision.
Indoor Scene Recognition, CVPR 09
Indoor scene recognition is a challenging open problem in high level vision. Most scene recognition models that work well for outdoor scenes perform poorly in the indoor domain. The main difficulty is that while some indoor scenes (e.g. corridors) can be well characterized by global spatial properties, others (e.g., bookstores) are better characterized by the objects they contain. More generally, to address the indoor scenes recognition problem we need a model that can exploit local and global discriminative information.
Keith Price Bibliography Integration of Vision Modules
Some papers on organisation of (artificial) visual systems
Dynamical Systems, Control, Coding, Computer Vision New Trends,Interfaces, and Interplay
This is just a mention, not the book.
Interesting bit: "As J. Malik and P. Perona point out in "Introduction to Mathematical Aspects of Computer Vision", the vision tasks may be organized in four broad categories: reconstruction of images, control (e.g. visually guided control of vehicle navigation), grouping/tracking and recognition."
Ullman's Visual Routines x CMU Tekkotsu's Sketches
Describes some of the resources available in CMU Tekkotsu robotics simulator and how they relate to Ullman's Visual Routines
To afford or not to afford: A new formalization of affordance towards affordance-based robot control
The affordances of the environment are what it offers the animal, what it provides or furnishes, either for good or ill. The verb to afford is found in the dictionary, but the noun affordance is not. I have made it up. I mean by it something that refers to both the environment and the animal in a way that no existing term does. It implies the complementarity of the animal and the environment.”“... an affordance is neither an objective property nor a subjective property; or both if you like. An affordance cuts across the dichotomy of subjective-objective and helps us to understand its inadequacy. It is equally a fact of the environment and a fact of behavior. It is both physical and psychical, yet neither. An affordance points bothways, to the environment and to the observer.”“The perceiving of an affordance is not a process of perceiving a value-free physical object to which meaning is somehow added in a way that no one has been able to agree upon; it is a process of perceiving a value-rich ecological object.”“The theory of affordances rescues us from the philosophical muddle of assumingfixed classes of objects, each defined by its common features and then given a name...You do not have to classify and label things in order to perceive what they afford.”
Tekkotsu: Cognitive Robotics
NOTE: their definition of cognitive robotics is a little off
... extending Tekkotsu to support higher level abstractions for robot programming. We call our approach "cognitive robotics" because it draws inspiration from ideas in cognitive science, such as Ullman's notion of "visual routines", Paivio's "dual coding theory", and Gibson's concept of "affordances". Cognitive robotics makes no strong theoretical claims, but instead focuses on developing technology that actually works, on real robots, with their inherent physical constraints and sensory limitations.
MeMoMan — Markerless Tracking from Videos
We are developing new computational models and a system for accurate measurement of human motion. Our primary goal is to develop markerless vision-based tracking algorithms for use with the industry-proven anthropometric human model RAMSIS (in collaboration with the TUM Ergonomics Department/Faculty of Mechanical Engineering). By providing RAMSIS with markerless tracking capabilities, we open up new fields of application in ergonomic studies and industrial design. On the other hand, we believe that a far-developed, flexible and accurate model such as RAMSIS is beneficial for human motion tracking given the ergonomic expertise that has affected its design.
Selected Tags
Related Tags
Sponsored Links
Top Contributors
Groups interested in computer...
Highlighter, Sticky notes, Tagging, Groups and Network: integrated suite dramatically boosting research productivity. Learn more »
Join Diigo