Robot and obstacles localization and tracking with an external camera ring

Abstract

Abstract-In this paper a ring of calibrated and synchronized cameras is used for achieving robot and obstacle localization inside a common observed area. To avoid complex appearance matching derived from the wide-baseline arrangement of cameras, a metric occupancy grid is obtained by intersection of silhouettes projected onto the floor. A particle filter is proposed for tracking multiple objects by using the grid as observation data. A clustering algorithm is included in the filter to increase the robustness and adaptability of the multimodal estimation task. To preserve identity of the robot from the set of tracked objects, odometry readings are used to compute a Maximum Likelihood (ML) global trajectory identification. As a proof of concept, real results are obtained in a long sequence with a mobile robot moving in a human-cluttered scene.

Tracking multiple agents in an intelligent space with probabilistic algorithms and a camera ring

“…The PF based tracking solution ensures bigger reliability and robustness, and more constant execution time that the one based on the KF (as demonstrated in [10] and [9]). …”

“…Using a single PF in the tracking task has already been successfully proposed in previous works ( [7] [8] [9] [10]). In some of them (i.e.…”

“…In some of them (i.e. [9]) a measurements' clustering process has been added to the filter in order to exploit the PF multimodality. In the work presented in this paper, a more complex solution is needed, in order to obtain a solution flexible enough to be used with non rigid 3D objects.…”

Intelligent Robot Guidance in Fixed External Camera Network for Navigation in Crowded and Narrow Passages

“…The policy must first avoid such conflicts by careful planning, and if the conflicts occur then they must be resolved intelligently by taking into account many important factors like the power availability of the robots and the priority of the task undertaken. Regarding the state of the art, using external cameras with robots has been proposed earlier but with application to localization [1], automatic calibration [2], and pose estimation [3]. In the current work, we discuss the case of using external camera sensor network for sharing narrow paths, and providing visual information to robot about blind spots for trajectory planning and path planning.…”

Visual Hull from Imprecise Polyhedral Scene

“…The visual hull concept was introduced by Laurentini [1] and is used in many image-based reconstruction methods [2], [3], [4], [5]. Since the visual hull contains the target object and it is a better approximation than the convex hull, it has great advantage in obstacle avoidance, robotic navigation [6], 3D model acquisition and human motion tracking [7]. Since it is straightforward to extract silhouettes of an object from its pictures, the visual hull reconstruction is widely used in applications.…”