Jose Luis Alarcon-Herrera's research while affiliated with University of Windsor and other places

Publications (7)

Article
Based on a convex optimization approach, we propose a new method of multi-camera deployment for visual coverage of a 3-D object surface. In particular, the optimal placement of a single camera is first formulated as translation and rotation convex optimization problems, respectively, over a set of covered triangle pieces on the target object. The c...
Conference Paper
The deployment of multi-camera networks is usually accomplished by maximizing the covered area, while the coverage strength is difficult to be optimized simultaneously. We propose a coverage enhancement approach in this paper to improve the coverage strength of three-dimensional (3D) scenes, by using convex optimization approach to refine the initi...
Article
Full-text available
A semiautomatic model-based approach to the view planning problem for high-resolution active triangulation 3-D inspection systems is presented. First, a comprehensive, general, high-fidelity model of such systems is developed for the evaluation of configurations with respect to a model of task requirements, with a bounded scalar performance metric....
Article
An automatic method for solving the problem of view planning in high-resolution industrial inspection is presented. The method's goal is to maximize the visual coverage, and to minimize the number of cameras used for inspection. Using a CAD model of the object of interest, we define the scene-points and the viewpoints, with the later being the solu...
Article
In this brief, we present a method for automatic deployment of visual sensor networks. The solution is formulated as a greedy search by taking advantage of the topological properties of the vision graph. The optimization of the optical component of the vision system is solved using a geometrical approach. We show that the information about the reso...
Conference Paper
We present a method for automatic deployment of visual sensor networks, based on a polygonal mesh model of the task. This method uses a graph-based approach to ensure an optimal level of visual overlap between the sensors. In this brief our method is further leveraged by increasing the size of the solution space, which in turn moves the solution cl...
Article
Based on convex optimization techniques, we propose a new multi-camera deployment method for optimal visual coverage of a three-dimensional (3D) object surface. Different from existing methods, the optimal placement of a single camera is formulated as two convex optimization problems, given a set of covered triangle faces. Moreover, this idea is in...

Citations

... In order to obtain a full coverage of the AvioAero gearbox, it is necessary to select the best position for the cameras inside the inspection cage. In [2], the authors propose a method to maximize the visual coverage and to minimize the number of cameras used for inspection. Starting from [2], we implement a slightly modified version of their algorithm that takes also into account the area of each surface triangle of the CAD model viewed by a camera. ...
... Several works expand the two-dimensional world view of the AGP into a more realistic three-dimensional case [7,16,20,[23][24][25][26][27][28]. However, while many of these models can be simplified when you care about a planar scene, these models require extra computation to be used for occlusion checking which is unnecessary when dealing with a planar scene. ...
... C AMERA network is widely used to fulfill various visual tasks in industry, such as surveillance [1], [2], industrial inspection [3], motion capture [4], 3-D reconstruction [5], [6] and so on. Among these implementations, visual coverage is a crucial problem, whose objective is to achieve environmental perception via deploying the visual sensors in 2-D [7]- [9] or 3-D areas [10]- [12]. The main approach for visual coverage follows three steps. ...
... When the objects' models are known before reconstruction, the NBV is calculated based on the known surface information. VP methods that deal with the above reconstruction tasks are called model-based methods [7,8]. Scott W R. [9] used the greedy method to obtain the NBV, which can be used to explore more of the unknown surface of the object. ...