Miguel Angel García

3D simultaneous localization and modeling from stereo vision

This work presents a new algorithm for determining the trajectory of a mobile robot and, simultaneously, creating a detailed volumetric 3D model of its workspace. The algorithm exclusively utilizes information provided by a single stereo vision system, avoiding thus the use both of more costly laser systems and error-prone odometry. Six-degrees-of-freedom egomotion is directly estimated from images acquired at relatively close positions along the robots path. Thus, the algorithm can deal with both planar and uneven terrain in a natural way, without requiring extra processing stages or additional orientation sensors. The 3D model is based on an octree that encapsulates clouds of 3D points obtained through stereo vision, which are integrated after each egomotion stage. Every point has three spatial coordinates referred to a single frame, as well as true-color components. The spatial location of those points is continuously improved as new images are acquired and integrated into the model.

Coordinated multi-robot exploration through unsupervised clustering of unknown space

This paper proposes a new coordination algorithm for efficiently exploring an unknown environment with a team of mobile robots. The proposed technique subsequently applies a well-known unsupervised clustering algorithm (k-means) in order to fairly divide the remaining unknown space into as many disjoint regions as available robots. Each robot is primarily responsible for exploring its assigned region and can help other robots on its way through. Unknown space is dynamically repartitioned as new areas are discovered by the team, balancing thus the overall workload among team members and naturally leading to greater dispersion over the environment and thus faster broad coverage than with previous greedy-like approaches, which guide robots based on maximum profit strategies that simply trade off between distance to the closest frontiers and amount of unknown cells likely to be discovered from them.

Automatic texture feature selection for image pixel classification

Pixel-based texture classifiers and segmenters are typically based on the combination of texture feature extraction methods that belong to a single family (e.g., Gabor filters). However, combining texture methods from different families has proven to produce better classification results both quantitatively and qualitatively. Given a set of multiple texture feature extraction methods from different families, this paper presents a new texture feature selection scheme that automatically determines a reduced subset of methods whose integration produces classification results comparable to those obtained when all the available methods are integrated, but with a significantly lower computational cost. Experiments with both Brodatz and real outdoor images show that the proposed selection scheme is more advantageous than well-known general purpose feature selection algorithms applied to the same problem.

Supervised texture classification by integration of multiple texture methods and evaluation windows

Pixel-based texture classifiers and segmenters typically combine texture feature extraction methods belonging to a same family. Each method is evaluated over square windows of the same size, which is chosen experimentally. This paper proposes a pixel-based texture classifier that integrates multiple texture feature extraction methods from different families, with each method being evaluated over multiple windows of different size. Experimental results show that this integration scheme leads to significantly better results than well-known supervised and unsupervised texture classifiers based on specific families of texture methods. A practical application to fabric defect detection is also presented.

Reducing the complexity of geometric selective disassembly

This paper presents an efficient technique for determining a low-cost disassembly sequence suitable to extract a subset of s components from an assembly containing n components, e of which are exterior (e/spl Lt/n). The most efficient solution to this so-called geometric selective disassembly problem is the wave propagation algorithm, which is reported to have a computational complexity of O(sn/sup 2/). Instead, the complexity of the proposed algorithm is O(enlogn) when s/spl Lt/n, and O(sn) when s/spl sime/n. Experimental results with synthetic 3D assemblies are presented.

Efficient approximation of gray-scale images through bounded error triangular meshes

This paper presents an iterative algorithm for approximating gray-scale images with adaptive triangular meshes ensuring a given tolerance. At each iteration, the algorithm applies a non-iterative adaptive meshing technique. In this way, this technique converges faster than traditional mesh refinement algorithms. The performance of the proposed technique is studied in terms of compression ratio and speed, comparing it with an optimization-based mesh refinement algorithm.

Fast extraction of surface primitives from range images

An efficient algorithm for extracting planar and curved surface patches that express distinctive parts of the objects contained in a given range image is presented. The proposed technique does not directly segment the range image but a triangular approximation of it obtained through a fast adaptive randomized sampling algorithm. This intermediate representation allows us to avoid the processing of all the individual points of the range image in the segmentation phase.

Estimation of distance to planar surfaces and type of material with infrared sensors

This paper proposes a new technique for computing the distance to an unknown planar surface and, at the same time, estimating the material of the surface through the use of low-cost infrared sensors. Previous approaches to this problem required more costly ultrasound systems as a complement or, alternatively, an exhaustive training process that records the sensor response corresponding to known materials measured at different predefined distances. Experimental results with an off-the-shelf infrared sensor mounted on a mobile robot are presented.

Acceleration of filtering and enhancement operations through geometric processing of gray-level images

This paper describes an algorithm to implement image filtering and enhancement operations by processing adaptive triangular meshes that represent gray-level images. Experimental results show that these operations are significantly more efficient when they are performed upon triangular meshes than by sequentially processing all the pixels contained in the given images.

Efficient approximation of range images through data-dependent adaptive triangulations

The paper presents an efficient algorithm for generating adaptive triangular meshes from dense range images. The proposed technique consists of two stages. First, a quadrilateral mesh is generated from the given range image. The points of this mesh adapt to the surface shapes represented in the range image by grouping in areas of high curvature and dispersing in low-variation regions. The second stage splits each quadrilateral cell obtained before into two triangles. Between the two possible flips, it is chosen the one whose diagonals direction is closest to the orientation of the discontinuities present in that cell. Both stages avoid costly iterative optimization techniques. Results with real range images are presented. They show low CPU times and accurate triangular approximations of the given images.