Efficient Marker Matching Using Pair-Wise Constraints in Physical Therapy

Abstract

Abstract. In this paper, we report a robust, efficient, and automatic method for matching infrared tracked markers for human motion analysis in computer-aided physical therapy applications. The challenges of this task stem from non-rigid marker motion, occlusion, and timing requirements. To overcome these difficulties, we use pair-wise distance constraints for marker identification. To meet the timing requirements, we first reduce the candidate marker labels by proximity constraints before enforcing the pair-wise constraints. Experiments with 38 real motion sequences, our method has shown superior accuracy and significant speedup over a semi-automatic proprietary method and the Iterative Closest Point (ICP) approach.

Ghost marker detection and elimination in marker‐based optical tracking systems for real‐time tracking in stereotactic body radiotherapy

“…[27][28][29][30][31][32] The motion estimation problem recovers the 3D motion parameters (rotation and translation) of a moving object from images taken at two time instances. Since finding exact point correspondence (typically using local structural comparison) is considerably time-consuming due to the large number of points involved 27,29 and challenging due to the presence of missing points, 30,33 motion parameters are usually estimated without knowing correspondences. 25,28,32 Fortunately, the number of markers used in our problem is usually rather small (<10).…”

“…The constraints are based on PWDs, the invariance of which is assumed under rigid motion. 33 The backtracking approach is the standard way to solve a CSP. 23 It traverses the space of partial solutions in a depth first manner.…”