Real-time 3D Pose Estimation with a Monocular Camera Using Deep Learning and Object Priors On an Autonomous Racecar

2018/09/27 by Dhall, Ankit
#Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Robotics (cs.RO)

paper · doi:10.48550/arxiv.1809.10548

Abstract

We propose a complete pipeline that allows object detection and simultaneously estimate the pose of these multiple object instances using just a single image. A novel "keypoint regression" scheme with a cross-ratio term is introduced that exploits prior information about the object's shape and size to regress and find specific feature points. Further, a priori 3D information about the object is used to match 2D-3D correspondences and accurately estimate object positions up to a distance of 15m. A detailed discussion of the results and an in-depth analysis of the pipeline is presented. The pipeline runs efficiently on a low-powered Jetson TX2 and is deployed as part of the perception pipeline on a real-time autonomous vehicle cruising at a top speed of 54 km/hr.

Related

• Vehicle Pose and Shape Estimation through Multiple Monocular Vision
• Exploring the Capabilities and Limits of 3D Monocular Object Detection -- A Study on Simulation and Real World Data
• What My Motion tells me about Your Pose: A Self-Supervised Monocular 3D\n Vehicle Detector
• Scalable Vision-Based 3D Object Detection and Monocular Depth Estimation for Autonomous Driving
• RTM3D: Real-time Monocular 3D Detection from Object Keypoints for Autonomous Driving