Multimodal deep learning for robust RGB-D object recognition

Robust object recognition is a crucial ingredient of many, if not all, real-world robotics applications. This paper leverages recent progress on Convolutional Neural Networks (CNNs) and proposes a novel RGB-D architecture for object recognition. Our architecture is composed of two separate CNN processing streams - one for each modality - which are consecutively combined with a late fusion network. We focus on learning with imperfect sensor data, a typical problem in real-world robotics tasks. For accurate learning, we introduce a multi-stage training methodology and two crucial ingredients for handling depth data with CNNs. The first, an effective encoding of depth information for CNNs that enables learning without the need for large depth datasets. The second, a data augmentation scheme for robust learning with depth images by corrupting them with realistic noise patterns. We present state-of-the-art results on the RGB-D object dataset [15] and show recognition in challenging RGB-D real-world noisy settings.

Authors

• Andreas Eitel
• Jost Tobias Springenberg
• Luciano Spinello
• Martin A. Riedmiller
• Wolfram Burgard

Keywords

• Object recognition
• Training
• Image coding
• Robot sensing systems
• Streaming media
• Feature extraction
• Robustness
• Multimodal Learning
• Robust Recognition
• Robust Object Recognition
• Neural Network
• Convolutional Neural Network
• Data Augmentation
• Depth Images
• Depth Information
• Depth Data
• Fusion Network
• Noise Patterns
• Late Fusion
• Additional Experiments
• Object Detection
• Recognition Accuracy
• RGB Images
• Recognition Performance
• Depth Camera
• Domain Adaptation
• RGB Data
• Real-world Environments
• Pre-trained Convolutional Neural Network
• Surface Normals
• Pre-trained Network
• Stream Network
• Early Fusion
• ImageNet Dataset
• Object Surface
• Real-world Scenes