PWP3D: Real-time Segmentation and Tracking of 3D Objects
We formulate a probabilistic framework for simultaneous region-based 2D segmentation and 2D to 3D pose tracking, using a known 3D model. Given such a model, we aim to maximize the discrimination between statistical foreground and background appearance models, via direct optimization of the 3D pose parameters. The foreground region is delineated by the zero-level-set of a signed distance embedding function, and we define an energy over this region and its immediate background surroundings based on pixel-wise posterior membership probabilities (as opposed to likelihoods). We derive the differentials of this energy with respect to the pose parameters of the 3D object, meaning we can conduct a search for the correct pose using standard gradient-based non-linear minimisation techniques. We propose novel enhancements at the pixel level based on temporal consistency and improved online appearance model adaptation. Furthermore, straightforward extensions of our method lead to multi-camera and multi-object tracking as part of the same framework. The parallel nature of much of the processing in our algorithm means it is amenable to GPU acceleration, and we give details of our real-time implementation, which we use to generate experimental results on both real and artificial video sequences, with a number of 3D models. These experiments demonstrate the benefit of using pixel-wise posteriors rather than likelihoods, and showcase the qualities, such as robustness to occlusions and motion blur (and also some failure modes), of our tracker.
- Prisacariu, Victor A., and Ian D. Reid. "Pwp3d: Real-time segmentation and tracking of 3d objects." International journal of computer vision 98.3 (2012): 335-354.
- Active Vision Laboratory, Department of Engineering Science, University of Oxford
- Tjaden, Henning, Ulrich Schwanecke, and Elmar Schömer. "Real-Time Monocular Segmentation and Pose Tracking of Multiple Objects." European Conference on Computer Vision. Springer International Publishing, 2016.
- Computer Science Department, RheinMain University of Applied Sciences
- Institute of Computer Science, Johannes Gutenberg University Mainz