Research descriptionRange Synthesis for 3D Environment ModelingI am involved in the problem of Mobile Robot Environment Modeling. We have developed a new statistical learning method to infer the geometric structures from images. Specifically, our method computes dense range maps of locations of the environment using only intensity images and very limited amount of range data as an input. Our goal is to facilitate the building of 3D environment models by exploiting the fact that both video imaging and limited range sensing are ubiquitous readily-available technologies while complete volume scanning is prohibitive on most mobile platforms. The main idea is to exploit the assumption that intensity and range data are correlated, albeit in potentially complicated ways, but exhibiting useful structure. The scientific issue is to represent this correlation such that it can be used to recover range data where missing. Markov Random Fields are used as a model to capture the local statistics of the intensity and range. A 2002 technical report explaining more about our method can be found here. Preliminary results using MRF with Belief Propagation Image Enhancement for Underwater ImagesFor many inspection and observation tasks, high quality image data is desirable. We have sucessfully applied our learning based Markov random field model to image enhancement based on training from examples. Particularly, in vision systems for aquatic robots, this training from examples allows the system to adapt the image restoration algorithm to the current environmental conditions and also to the task requirements. Image restoration involves the removal of some known degradation in an image. Traditionally, the most common sources of degradation are due to imperfections of the sensors, or in transmission. For the case of underwater images, additional factors are poor visibility (even in the cleanest water), ambient light, and frequency-dependent scattering and absorption, both between the camera and the environment, and also between the light source (the sun) and the local environment (i.e. this varies with both depth and local water conditions). The light undergoes scattering into the line of sight. the result is an image that appears bluish, blurry and out of focus. Our approach is based on learning the statistical relationships between image pairs. In our case, these pairs are the image we actually observe and a corresponding color-corrected and deblurred images. This model uses multi-scale representations of the corrected (enhanced) and original images to construct a probabilistic enhancement algorithm that improves the observed video. This improvement is based on a combination of color matching correspondence with training data, and local context via belief propagation, all embodies in the Markov random field model. Training images are small patches of regions of interest that capture the maximum of the intensity variations from the image to be restored. Examples of color restoration of underwater imagesExperiment: Using different tones of poor colored images on the same training pair example. It shows that the algorithm is robust even with almost no color on the input image. I am working under the supervision of Prof. Greg Dudek at the Centre for Intelligent Machines, McGill University. Check out the mobile robotics lab for more info. PublicationsMy complete BibTeX file is here. Refereed journal publicationsTranslation, Rotation, and Scale-Invariant Object Recognition, L.A. Torres-Mendez, J.C Ruiz-Suarez, L.E. Sucar, and G. Gomez. IEEE Transactions on Systems, Man and Cybernetics. Part C: Applications and Reviews, February 2000, vol. 30(1), pp 125-130. [Reprints available on request] [postscript gzipped ] Simulation of a solar-hydrogen-fuel cell system: results for different locations in Mexico, L.A. Torres, F.J. Rodriguez and P.J. Sebastian. International Journal of Hydrogen Energy, vol. 23(11), November 1998, pp 1005-1009. Refereed conference publicationsAll papers included a conference presentation, unless otherwise indicated.
AQUA: An aquatic walking robot, Georgidas, G., German, A., Hogue, A., Liu, H., Prahacs, C., Ripsman, A., Sim, R., Torres, L.A., Zhang, P., Buehler, M., Dudek, G., Jenkin, M. and Milios, E.
Statistical Inference and Synthesis in the Image Domain for Mobile Robot
Environment Modeling, Luz Abril Torres-Méndez and Gregory Dudek
Statistics in the Image Domain for Mobile Robot Environment Modeling, Luz Abril Torres-Méndez and Gregory Dudek
Inter-Image Statistics for Scene Reconstruction, Luz A. Torres-Ménez, Gregory Dudek and Paul Di Marco Proc. American Association for Artificial Intelligence (AAAI), 2004, pp. 476-481. [ pdf ]
Range Synthesis for 3D Environment Modeling, Luz A. Torres-Méndez and Gregory Dudek
A Statistical Learning Method for Mobile Robot Environment Modeling, Luz A. Torres-Méndez and Gregory Dudek
Range Synthesis for 3D Environment Modeling, Luz A. Torres-Méndez and Gregory Dudek
Automated Enhancement of 3D Models, Luz A. Torres-Méndez and Gregory Dudek
Upper bound conditioning as a performance index for manipulator motion planning, Rene V. Mayorga and Luz Abril Torres Simulation of a PV-hydrogen-fuel cell system: results for different cities of Mexico, Luz Abril Torres, Javier Rodriguez and P. Joseph Sebastian. Poster presentation in the International Symposium on New Materials for Hydrogen-Fuel Cell-Photovoltaic Systems I, Cancun, Mexico, September 1997.
Translation, Rotation and Scale Invariant Object Recognition, L.A. Torres-Mendez, J.C. Ruiz-Suarez and L.E. Sucar-Succar. PhD proposal
Sensor Fusion for 3-D Indoor Environment Modeling, Luz Abril Torres-Méndez
Master's Thesis
Translation, Rotation and Scale Invariant Object Recognition Abstracts
Range Synthesis for 3D Environment Modeling, Luz Abril Torres-Mendez and Gregory Dudek
Sensor fusion for 3-D Modeling of Indoor Environments, Luz Abril Torres-Mendez and Gregory Dudek
|