Occlusion-Aware Region-Based 3D Pose Tracking of Objects With Temporally Consistent Polar-Based Local Partitioning

Region-based methods have become the state-of-art solution for monocular 6-DOF object pose tracking in recent years. However, two main challenges still remain: the robustness to heterogeneous configurations (both foreground and background), and the robustness to partial occlusions. In this paper, we propose a novel region-based monocular 3D object pose tracking method to tackle these problems. Firstly, we design a new strategy to define local regions, which is simple yet efficient in constructing discriminative local color histograms. Contrary to previous methods which define multiple circular regions around the object contour, we propose to define multiple overlapped, fan-shaped regions according to polar coordinates. This local region partitioning strategy produces much less number of local regions that need to be maintained and updated, while still being temporally consistent. Secondly, we propose to detect occluded pixels using edge distance and color cues. The proposed occlusion detection strategy is seamlessly integrated into the region-based pose optimization pipeline via a pixel-wise weight function, which significantly alleviates the interferences caused by partial occlusions. We demonstrate the effectiveness of the proposed two new strategies with a careful ablation study. Furthermore, we compare the performance of our method with the most recent state-of-art region-based methods in a recently released large dataset, in which the proposed method achieves competitive results with a higher average tracking success rate. Evaluations on two real-world datasets also show that our method is capable of handling realistic tracking scenarios.

I. Introduction

Tracking the 6-DOF pose of a rigid object in monocular videos is an essential problem in computer vision [1]. It is the basic technology in various applications such augmented reality (AR), robotic perception and human-computer interaction [2]–[4]. Recent researches have demonstrated the advantages of region-based methods in real-time 3D object pose tracking among other traditional approaches [5]–[7], especially in some difficult situations. The underlying statistical formulation of region-based method makes it robust to certain kinds of pixel-level outliers, such as a moderate degree of lighting variation, background cluttering, and minor occlusions. However, two main challenges still remain for region-based methods and have limited the application in more complex configurations: (1) Dealing with heterogeneous object and background; (2) Dealing with partial occlusions. We discuss the two challenges in detail as follows.