Abstract
In this paper, we present a novel 2D–3D pedestrian tracker designed for applications in autonomous vehicles. The system operates on a tracking by detection principle and can track multiple pedestrians in complex urban traffic situations. By using a behavioral motion model and a non-parametric distribution as state model, we are able to accurately track unpredictable pedestrian motion in the presence of heavy occlusion. Tracking is performed independently, on the image and ground plane, in global, motion compensated coordinates. We employ Camera and LiDAR data fusion to solve the association problem where the optimal solution is found by matching 2D and 3D detections to tracks using a joint log-likelihood observation model. Each 2D–3D particle filter then updates their state from associated observations and a behavioral motion model. Each particle moves independently following the pedestrian motion parameters which we learned offline from an annotated training dataset. Temporal stability of the state variables is achieved by modeling each track as a Markov Decision Process with probabilistic state transition properties. A novel track management system then handles high level actions such as track creation, deletion and interaction. Using a probabilistic track score the track manager can cull false and ambiguous detections while updating tracks with detections from actual pedestrians. Our system is implemented on a GPU and exploits the massively parallelizable nature of particle filters. Due to the Markovian nature of our track representation, the system achieves real-time performance operating with a minimal memory footprint. Exhaustive and independent evaluation of our tracker was performed by the KITTI benchmark server, where it was tested against a wide variety of unknown pedestrian tracking situations. On this realistic benchmark, we outperform all published pedestrian trackers in a multitude of tracking metrics.
Highlights
As our society steadily embraces automation in our transportation systems, the demands from computer vision systems are increasing with an accelerated pace
This is performed at the positions in the image that correspond to the previous observation of the person after correction for camera motion estimated by visual odometry
Tracker-to-target assignment: This metric describes the reliability of the Multi-Object Tracker by measuring the number of False Positive (FP) and False Negative (FN) per and across all frames given by the F1 score
Summary
As our society steadily embraces automation in our transportation systems, the demands from computer vision systems are increasing with an accelerated pace. Level 4 and 5 autonomy on public roads requires safety levels that are beyond the capability of any available system on the market Transitioning to these levels of autonomy requires overlapping and redundant systems where the driving without human intervention must continue even in the event of a sensor failure. The motion of tracked pedestrians is modeled by behavioral motion models that closely match short-term human behavior in general traffic situations. These behavioral models drive the initialization and update steps in the Monte Carlo simulations using statistics from offline training data. We conclude the paper with closing remarks on some of the fail cases and directions for future improvement
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.