Long-Range Augmented Reality with Dynamic Occlusion Rendering

Proper occlusion based rendering is very important to achieve realism in all indoor and outdoor Augmented Reality (AR) applications. This paper addresses the problem of fast and accurate dynamic occlusion reasoning by real objects in the scene for large scale outdoor AR applications. Conceptually, proper occlusion reasoning requires an estimate of depth for every point in augmented scene which is technically hard to achieve for outdoor scenarios, especially in the presence of moving objects. We propose a method to detect and automatically infer the depth for real objects in the scene without explicit detailed scene modeling and depth sensing (e.g. without using sensors such as 3D-LiDAR). Specifically, we employ instance segmentation of color image data to detect real dynamic objects in the scene and use either a top-down terrain elevation model or deep learning based monocular depth estimation model to infer their metric distance from the camera for proper occlusion reasoning in real time. The realized solution is implemented in a low latency real-time framework for video-see-though AR and is directly extendable to optical-see-through AR. We minimize latency in depth reasoning and occlusion rendering by doing semantic object tracking and prediction in video frames.

1 Introduction

Augmented reality (AR) became extremely popular in recent years and continuously moving from research labs to the industrial and consumer application areas. While it is possible to purchase very compelling AR systems for indoor short-range use, outdoor geo-located AR solutions still pose a significant number of challenges. Specifically, outdoor AR systems require better quality and brighter displays, high-accuracy head tracking capable of robust operation in geo-location coordinate space and in the open area; system itself must be robust to various temperature, inclement weather, dust and mechanical impacts.