Non-Causal Tracking by Deblatting
This method addresses tracking challenges in computer vision for applications like motion analysis, but it appears incremental as it builds on existing Tracking by Deblatting with non-causal improvements.
The paper tackles the problem of estimating continuous, accurate trajectories of motion-blurred objects by proposing non-causal Tracking by Deblatting, which uses energy minimization and polynomial fitting to achieve high performance in Trajectory-IoU, recall, and velocity estimation compared to high-speed camera and radar measurements.
Tracking by Deblatting stands for solving an inverse problem of deblurring and image matting for tracking motion-blurred objects. We propose non-causal Tracking by Deblatting which estimates continuous, complete and accurate object trajectories. Energy minimization by dynamic programming is used to detect abrupt changes of motion, called bounces. High-order polynomials are fitted to segments, which are parts of the trajectory separated by bounces. The output is a continuous trajectory function which assigns location for every real-valued time stamp from zero to the number of frames. Additionally, we show that from the trajectory function precise physical calculations are possible, such as radius, gravity or sub-frame object velocity. Velocity estimation is compared to the high-speed camera measurements and radars. Results show high performance of the proposed method in terms of Trajectory-IoU, recall and velocity estimation.