Robust 3D Bounding Box Detection and State Estimation of Dynamic Objects for Autonomous Navigation

Carita M.; Contreras M.; Hashemi E. · IEEE Conference on Intelligent Transportation Systems, Proceedings, ITSC (2025) · DOI: 10.1109/itsc60802.2025.11423093

Resumen

Accurate state estimation of dynamic objects is critical for safe and reliable autonomous navigation in dynamic urban settings. Real-world scenarios may include occlusions, drifting in pose estimation, data sparsity, or abrupt appearances, representing complexity in multi-object tracking. This paper addresses the challenges of estimating the states of non-ego vehicles during autonomous navigation using multimodal visual-LiDAR perception, without any need to global navigation systems. The proposed estimation framework integrates detection and tracking through an optimal variance filter. The first stage incorporates instance segmentation and point cloud association, followed by an L-shape fitting method to estimate 3D Bounding Boxes. Object tracking is then performed using a modified multiobject tracking algorithm augmented by the initialization of motion models. This enables estimation of consistent surrounding vehicle velocities and positions while keeping track of them in the 3D space, enhancing situational awareness for motion planning, and supporting collision avoidance using predictive models. Comprehensive experiments on the KITTI dataset demonstrate the effectiveness and accuracy of the proposed framework compared to current benchmarks and state-of-the-art methods.

Instituciones: Universidad de Ingeniería y Tecnología