Curved shape reconstruction using multiple hypothesis tracking

Abstract

Abstract| Panoramic sweeps produced by a scanning range sensor often defy interpretation using conventional line of sight models, particularly when the environment contains curved, specularly re ective surfaces. Combining multiple scans from di erent v antage points provides geometric constraints necessary to solve this problem, but not without introducing new di culties. Existing multiple scan implementations, for the most part, ignore the data correspondence issue.The multiple hypothesis tracking MHT algorithm explicitly deals with data correspondence. Given canonical observations extracted from raw scans, the MHT applies multiple behavior models to explain their evolution from one scan to the next. This technique identi es di erent topological features in the world to which it assigns the corresponding measurements.We apply the algorithm to real sonar scans generated speci cally for this investigation. The experiments consist of interrogating a variety o f t wo dimensional prismatic objects, standing on end in a 1.2 m deep fresh water tank, from multiple vantage points using a 1.25 MHz pro ling sonar system. The results re ect the validity of the algorithm under the initial assumptions and its gradual performance degradation when these assumptions fail to characterize the environment adequately. We close with recommendations that detail extending the approach to handle more natural underwater settings.

Adaptive Mobile Robot Navigation and Mapping

“…That is, isolated features and smooth surfaces appear as circular arcs, also known as regions of constant depth , in sonar scans. For the specular returns, an improved estimate of the range and bearing to the object is obtained by grouping sets of adjacent returns with nearly the same range, then taking the mode of this set of angles as the bearing measurement and the range associated with this bearing as the range measurement to the object (Moran, Leonard, and Chryssostomidis, 1997). Rough surfaces (Bozma and Kuc, 1991) yield additional returns at high angles of incidence.…”

Uncertainty Control for Reliable Video Understanding on Complex Environments

“…For controlling this combinatorial explosion of hypotheses all the unlikely hypotheses have to be eliminated at each frame (for details refer to (Pattipati et al, 2000)). MHT methods have been extensively used in radar (Rakdham et al, 2007) and sonar tracking systems (Moran et al, 1997). In (Blackman, 2004) a good summary of MHT applications is presented.…”

Real-time reliability measure-driven multi-hypothesis tracking using 2D and 3D features

“…The measures R V 3D , R V 3D , R D 2D and R V 2D are the accumulation of visibility measures in time (with decreasing factor). P w , P l and P h in Equation (20) correspond to the mean probability of the dimensional attributes according to the a priori models of objects expected in the scene, considering the cooling function as in Equation (16). Note that parameter t c has been removed for simplicity.…”