Polardetr: Polar Parametrization for Vision-Based Surround-View 3d Detection

Abstract

3D detection based on surround-view camera system is a critical and promising technique in autopilot. In this work, we exploit the view symmetry of surround-view camera system as inductive bias to improve optimization and boost performance. We parameterize object’s position by polar coordinate and decompose velocity along radial and tangential direction. And the perception range, label assignment and loss function are correspondingly reformulated in polar coordinate system. This new Polar Parametrization scheme establishes explicit associations between image patterns and prediction targets. Based on it, we propose a surround-view 3D detection method, termed PolarDETR. Compared with DETR3D which is based on cartesian coordinate, PolarDETR achieves better performance on several backbone configurations, and has faster convergence speed and more accurate speed estimation. Thorough ablation studies are provided to validate the effectiveness.

Keywords: 3D object detection, Autonomous driving, Polar representation