How to track your dragon: A Multi-Attentional Framework for real-time RGB-D 6-DOF Object Pose Tracking
This addresses the problem of robust object tracking in cluttered environments for robotics and AR/VR applications, representing a strong specific gain rather than a broad paradigm shift.
The paper tackles real-time RGB-D 6-DOF object pose tracking by proposing a multi-attentional convolutional framework that handles background clutter and occlusion, improving state-of-the-art performance by 34.03% for translation and 40.01% for rotation on a benchmark dataset.
We present a novel multi-attentional convolutional architecture to tackle the problem of real-time RGB-D 6D object pose tracking of single, known objects. Such a problem poses multiple challenges originating both from the objects' nature and their interaction with their environment, which previous approaches have failed to fully address. The proposed framework encapsulates methods for background clutter and occlusion handling by integrating multiple parallel soft spatial attention modules into a multitask Convolutional Neural Network (CNN) architecture. Moreover, we consider the special geometrical properties of both the object's 3D model and the pose space, and we use a more sophisticated approach for data augmentation during training. The provided experimental results confirm the effectiveness of the proposed multi-attentional architecture, as it improves the State-of-the-Art (SoA) tracking performance by an average score of 34.03% for translation and 40.01% for rotation, when tested on the most complete dataset designed, up to date,for the problem of RGB-D object tracking.