Multi-modal Tracking for Object based SLAM
This work improves object-based tracking for semantic mapping in robotics or autonomous systems, though it appears incremental as it builds on existing frameworks like OmniMapper.
The paper tackles the problem of 3D visual object tracking for monocular cameras by integrating spatial knowledge from semantic mapping with visual odometry measurements, achieving a mean error of 0.23m per frame and a 9% relative error improvement over state-of-the-art trackers.
We present an on-line 3D visual object tracking framework for monocular cameras by incorporating spatial knowledge and uncertainty from semantic mapping along with high frequency measurements from visual odometry. Using a combination of vision and odometry that are tightly integrated we can increase the overall performance of object based tracking for semantic mapping. We present a framework for integration of the two data-sources into a coherent framework through information based fusion/arbitration. We demonstrate the framework in the context of OmniMapper[1] and present results on 6 challenging sequences over multiple objects compared to data obtained from a motion capture systems. We are able to achieve a mean error of 0.23m for per frame tracking showing 9% relative error less than state of the art tracker.