Maxim Bazik, Vision Systems Inc.; Brien Flewelling, ExoAnalytic Solutions; Manoranjan Majji, Texas A&M University; Joseph Mundy, Vision Systems Inc.
Keywords: Satellite, pose estimation, particle filter, bayesian probability, space situation awareness
Abstract:
Automated 3D pose estimation of satellites and other known space objects is a critical component of space situational awareness. Ground-based imagery offers a convenient data source for satellite characterization; however, analysis algorithms must contend with atmospheric distortion, variable lighting, and unknown reflectance properties. Traditional feature-based pose estimation approaches are unable to discover an accurate correlation between a known 3D model and imagery given this challenging image environment.
This paper presents an innovative pose estimation method able which does not rely on feature points. The proposed approach fits the silhouette of a known satellite model to ground-based imagery via particle filtering. Each particle contains sufficient information (orientation, position, scale, model articulation) to generate an accurate object silhouette. The silhouette of individual particles is compared to an observed image. Comparison is done probabilistically by calculating the joint probability that pixels inside the silhouette belong to the foreground distribution and that pixels outside the silhouette belong to the background distribution. Both foreground and background distributions are computed by observing empty space. The population of particles are resampled at each new image observation, with the probability of a particle being resampled proportional to the similarity of a particle silhouette and the observation image. The resampling process maintains multiple pose estimates which is beneficial in escaping local error minimums.
The proposed pose estimation method is tested on both consumer grade RGB imagery of a NASA shuttle and ground-based imagery of a LEO satellite.
Date of Conference: September 11-14, 2018
Track: Poster