Novel Perception Algorithmic Framework For Object Identification and Tracking In Autonomous Navigation
This addresses the problem of real-time object tracking for autonomous vehicles, but it appears incremental as it builds on existing techniques like KD-Tree segmentation and VFH.
The paper tackles object identification and tracking in autonomous navigation by introducing a novel perception framework that achieves a median tracking accuracy of 91% with an end-to-end computational time of 153 milliseconds on the KITTI dataset.
This paper introduces a novel perception framework that has the ability to identify and track objects in autonomous vehicle's field of view. The proposed algorithms don't require any training for achieving this goal. The framework makes use of ego-vehicle's pose estimation and a KD-Tree-based segmentation algorithm to generate object clusters. In turn, using a VFH technique, the geometry of each identified object cluster is translated into a multi-modal PDF and a motion model is initiated with every new object cluster for the purpose of robust spatio-temporal tracking. The methodology further uses statistical properties of high-dimensional probability density functions and Bayesian motion model estimates to identify and track objects from frame to frame. The effectiveness of the methodology is tested on a KITTI dataset. The results show that the median tracking accuracy is around 91% with an end-to-end computational time of 153 milliseconds