Using a 3d Time-of-Flight Range Camera for Visual Tracking

ToF cameras for active vision in robotics

“…As it is widely known, this second approach requires textured objects while their first approach does not. In the same project, Reiser and Kubacki [42] have proposed a method to actively orientate the camera using a visual servoing approach to control a panand-tilt unit. They proved that position-based visual servoing is straightforward by using a ToF camera, because of its ability to deliver 3D images at high rate.…”

“…A classical solution in the area of object modeling is the use of calibrated stereo rigs. Therefore, initial works were devoted to their comparison with [37] Dynamic object detection and classification Color and light independence PMD Hussmann and Liepert [38] Object pose Easy object/background segmentation PMD Guomundsson et al [39] Known object pose estimation Light independent / Absolute scale SR3 Beder et al [40] Surface reconstruction using patchlets ToF easily combines with stereo PMD Fuchs and May [7] Precise surface reconstruction 3D at high rate SR3/O3D100 (Depth) Dellen et al [5] 3D object reconstruction 3D at high rate SR3 (Depth) Foix et al [6] Kuehnle et al [8] Object recognition for grasping 3D allow geometric primitives search SR3 Grundmann et al [41] Collision free object manipulation 3D at high rate SR3 + stereo Reiser and Kubacki [42] Position based visual servoing 3D is simply obtained / No model needed SR3 (Depth) Gachter et al [43] Object part detection for classification 3D at high rate SR3 Shin et al [44] SR2 Klank et al [45] Mobile manipulation Easy table/object segmentation SR4 Marton et al [46] Object categorization ToF easily combines with stereo SR4 + color Nakamura et al [47] Mobile manipulation Easy table segmentation SR4 + color Saxena et al [9] Grasping unknown objects 3D at high rate SR3 + stereo Zhu et al [48] Short range depth maps ToF easily combines with stereo SR3 + stereo Lindner et al [49] Object segmentation for recognition Easy color registration PMD + color camera Fischer et al [50] Occlusion handling in virtual objects 3D at high rate PMD + color camera…”

ToF Cameras for Eye-in-Hand Robotics *

“…Swadzba et al [32] propose a new algorithm to cluster redundant points using a virtual plane, which apparently performs better in planar regions and reduces noise, improving registration results. Furthermore, a group at [39] Dynamic object detection and classification Color and light independence PMD Hussmann and Liepert [40] Object pose Easy object/background segmentation PMD Guomundsson et al [41] Known object pose estimation Light independent / Absolute scale SR3 Beder et al [42] Surface reconstruction using patchlets ToF easily combines with stereo PMD Fuchs and May [9] Precise surface reconstruction 3D at high rate SR3/O3D100 (Depth) Dellen et al [7] 3D object reconstruction 3D at high rate SR3 (Depth) Foix et al [8] Kuehnle et al [10] Object recognition for grasping 3D allow geometric primitives search SR3 Grundmann et al [43] Collision free object manipulation 3D at high rate SR3 + stereo Reiser and Kubacki [44] Position based visual servoing 3D is simply obtained / No model needed SR3 (Depth) Gachter et al [45] Object part detection for classification 3D at high rate SR3 Shin et al [46] SR2 Marton et al [47] Object categorisation ToF easily combines with stereo SR4 + color Saxena et al [11] Grasping unknown objects 3D at high rate SR3 + stereo Zhu et al [48] Short range depth maps ToF easily combines with stereo SR3 + stereo Lindner et al [49] Object segmentation for recognition Easy color registration PMD + color camera Fischer et al [50] Occlusion handling in virtual objects 3D at high rate PMD + color camera Jacobs University [33], [34] has proposed to identify surfaces using a region growing approach that allows the poligonization of the resulting regions in an incremental manner. The nature of the information delivered by ToF cameras, specially the neighbourhood relation of the different points, is explicitly exploited and also their noisy nature is taken into account.…”

“…As it is widely known, this second approach requires textured objects while their first approach does not. In the same project, Reiser and Kubacki [44] have proposed a method to actively orientate the camera using a visual servoing approach to control a pan-and-tilt unit. They proved that position-based visual servoing is straightforward by using a ToF camera, because of its ability to deliver 3D images at high rate.…”

Visual Control of Robots Using Range Images

“…Within these works, a visual servoing system using PSD (Position Sensitive Device) triangulation for PCB manufacturing is presented in [ 2 ]. In [ 3 ] a position-based visual servoing is described to perform the tracking of a moving sphere using a pan-tilt unit. In this last paper a ToF Camera manufactured by CSEM is used.…”