Results 1 -
6 of
6
Learning to Track Colored Objects with Log-Polar Vision
, 2004
"... An approach bringing together space-variant vision through a simple color segmentation technique and learning is presented. The proposed approach is employed to control the movement of a 5 degree of freedom (d.o.f.) robotic head. Color information is used to determine the position of the object of i ..."
Abstract
-
Cited by 9 (2 self)
- Add to MetaCart
An approach bringing together space-variant vision through a simple color segmentation technique and learning is presented. The proposed approach is employed to control the movement of a 5 degree of freedom (d.o.f.) robotic head. Color information is used to determine the position of the object of interest in the image plane and, consequently, to track it during its motion. The distance of the target from the center of the image is used to feed both a closed-loop and an open-loop controller. Most important, the parameters of the controllers are learnt on-line in a self-supervised fashion. Experiments are presented to demonstrate empirically the feasibility of the approach and its application to a real world control problem.
A Review of Biologically-Motivated Space-Variant Data Reduction Models for Robotic Vision
, 1996
"... The primate retina performs nonlinear "image" data reduction while providing a compromise between high resolution where needed, a wide field-of-view, and small output image size. For autonomous robotics, this compromise is useful for developing vision systems with adequate response times. ..."
Abstract
-
Cited by 6 (0 self)
- Add to MetaCart
The primate retina performs nonlinear "image" data reduction while providing a compromise between high resolution where needed, a wide field-of-view, and small output image size. For autonomous robotics, this compromise is useful for developing vision systems with adequate response times. This paper reviews the two classes of models of retino-cortical data reduction used in hardware implementations. The first class reproduces the retina to cortex mapping based on conformal mapping functions. The pixel intensities are averaged in groups called receptive fields (RF's) which are non-overlapping, and the averaging performed is uniform. As is the case in the retina, the size of the RF's increases with distance from the centre of the sensor. Implementations using this class of models are reported to run at video rates (30 frames per second). The second class of models reproduce, in addition to the variable-resolution retino-cortical mapping, the overlap feature of receptive fields of retinal...
Dealing with 2D translation estimation in log polar imagery
- Image Visual Computation
, 2003
"... Abstract Log-polar mapping has been proposed as a very appropriate space-variant imaging model in active vision applications. This biologically inspired model has several advantages, and facilitates some visual tasks. For example, it provides an efficient data reduction, and simplifies rotational a ..."
Abstract
-
Cited by 6 (2 self)
- Add to MetaCart
(Show Context)
Abstract Log-polar mapping has been proposed as a very appropriate space-variant imaging model in active vision applications. This biologically inspired model has several advantages, and facilitates some visual tasks. For example, it provides an efficient data reduction, and simplifies rotational and scaling image transformations. However, simple translations become a difficult transform due to the log-polar geometry. There is no doubt about the importance of translation estimation in active visual tracking. Therefore, in this work, the problem of translation estimation in log-polar images is tackled. Two different approaches are presented, and their performances are evaluated and compared. One approach uses a gradient descent for minimizing a dissimilarity measure, while the other converts the 2D problem into two simpler 1D problems, by using projections. As the experimental results reveal, this second approach, besides being more efficient, can deal with larger translations than the gradient-based search can. q
High-Speed Log-Polar Time to Crash Calculation of Mobile Vehicles
"... Time to impact computation is one of the applications of the image optical flow. It is useful in vehicle crash detection or robotic navigation. A high-speed image acquisition and computation rate is necessary in most of these applications. The main problem of time to impact computation from optical ..."
Abstract
- Add to MetaCart
(Show Context)
Time to impact computation is one of the applications of the image optical flow. It is useful in vehicle crash detection or robotic navigation. A high-speed image acquisition and computation rate is necessary in most of these applications. The main problem of time to impact computation from optical flow is the accuracy; accurate results usually need complex and slow computations not affordable for the fast time reaction of a vehicle or robot. Using log-polar images reduces the amount of data to be processed thus increasing speed and accuracy of results. Most optical flow techniques are inadequate to obtain high rate time to impact measurements, since they rely on complex static calculations on few images of the sequence. In our approach the time to impact is calculated using simple but fast algorithms over a high amount of images to have accurate results. 1
unknown title
, 2003
"... Similarity motion estimation and active elegant biological solution, but also an appropriatemechanism in computer-based vision of arti- ..."
Abstract
- Add to MetaCart
(Show Context)
Similarity motion estimation and active elegant biological solution, but also an appropriatemechanism in computer-based vision of arti-
Space variant vision and pipelined architecture for time to impact computation
"... Image analysis is one of the most interesting ways for a mobile vehicle to understand its environment [1]. One of the tasks of an autonomous vehicle is to get accurate informa-tion of what it has in front, to avoid collision or find a way to a target. This task requires real-time restrictions depend ..."
Abstract
- Add to MetaCart
(Show Context)
Image analysis is one of the most interesting ways for a mobile vehicle to understand its environment [1]. One of the tasks of an autonomous vehicle is to get accurate informa-tion of what it has in front, to avoid collision or find a way to a target. This task requires real-time restrictions depending on the vehicle speed and external object movement. The use of normal cameras, with homogeneous (squared) pixel dis-tribution, for real-time image processing, usually requires high performance computing and high image rates. A different approach makes use of a CMOS space-variant camera that yields a high frame rate with low data bandwidth. The camera also performs the log-polar trans-form, simplifying some image processing algorithms. One of this simplified algorithms is the time to impact compu-tation. The calculation of the time to impact uses a differ-ential algorithm. A pipelined architecture specially suited for differential image processing algorithms has been also developed using programmable FPGAs. 1
