Saliency-based object recognition in 3D data

This paper presents a robust and real-time capable recognition system for the fast detection and classification of objects in spatial 3D data. Depth and reflection data from a 3D laser scanner are rendered into images and fed into a saliency-based visual attention system that detects regions of potential interest. Only these regions are examined by a fast classifier. The time saving of classifying objects in salient regions rather than in complete images is linear with the number of trained object classes. Robustness is achieved by the fusion of the bi-modal scanner data; in contrast to camera images, this data is completely illumination independent. The recognition system is trained for two different object classes and evaluated on real indoor data.

Authors

• Simone Frintrop
• Andreas Nüchter
• Hartmut Surmann
• Joachim Hertzberg

Keywords

• Object detection
• Reflectivity
• Robustness
• Lighting
• Fuses
• Laser modes
• Optical reflection
• Computer vision
• Focusing
• Object recognition
• 3D Data
• Objective Data
• Visual Attention
• Object Classification
• 3D Scanning
• Reflectance Data
• Complete Image
• Attentional System
• Salient Regions
• 3D Laser Scanning
• System Performance
• Autonomic System
• Feature Maps
• Attention Mechanism
• Focus Of Attention
• Grayscale Images
• Exhaustive Search
• Depth Images
• Saliency Map
• Integral Image
• Detection Of Regions
• Simple Classification
• Reflectance Images
• Laser Mode
• Automated Guided Vehicles
• Mobile Robot
• Search Window
• Simple Features