Car Pose in Context: Accurate Pose Estimation with Ground Plane Constraints

TL;DR

This paper presents a joint optimization method for estimating car poses and ground plane geometry in scenes with unknown camera parameters, improving accuracy and enabling better behavior classification from video sequences.

Contribution

It introduces a novel joint optimization approach that incorporates ground plane constraints and statistical car shape models for improved pose estimation.

Findings

Significant improvement in car pose accuracy.

Enhanced behavior classification from 3D geometry.

Reliable camera focal length estimation.

Abstract

Scene context is a powerful constraint on the geometry of objects within the scene in cases, such as surveillance, where the camera geometry is unknown and image quality may be poor. In this paper, we describe a method for estimating the pose of cars in a scene jointly with the ground plane that supports them. We formulate this as a joint optimization that accounts for varying car shape using a statistical atlas, and which simultaneously computes geometry and internal camera parameters. We demonstrate that this method produces significant improvements for car pose estimation, and we show that the resulting 3D geometry, when computed over a video sequence, makes it possible to improve on state of the art classification of car behavior. We also show that introducing the planar constraint allows us to estimate camera focal length in a reliable manner.