Discriminative feature learning for efficient RGB-D object recognition

This paper presents an efficient approach to recognize objects captured with an RGB-D sensor. The proposed approach uses a Bag-of-Words (BOW) model to learn feature representations from raw RGB-D point clouds in a weakly supervised manner. To this end, we introduce a novel method based on randomized clustering trees to learn visual vocabularies which are fast to compute and more discriminative compared to the vocabularies generated by classical methods such as k-means. We show that, when combined with standard spatial pooling strategies, our proposed approach yields a powerful feature representation for RGB-D object recognition. Our extensive experimental evaluation on two challenging RGB-D object datasets and live video streams from Kinect shows that our learned features result in superior object recognition accuracies compared with the state-of-the-art methods.

Authors

• Umar Asif
• Mohammed Bennamoun
• Ferdous Ahmed Sohel

Keywords

• Feature extraction
• Three-dimensional displays
• Object recognition
• Vocabulary
• Vegetation
• Computational modeling
• Training
• Feature Learning
• Discriminative Features
• Discriminative Feature Learning
• Feature Representation
• Point Cloud
• Recognition Accuracy
• Extensive Evaluation
• Live Streaming
• Spatial Pooling
• Raw Point
• Feature Representation Learning
• Raw Point Cloud
• Extensive Experimental Evaluation
• Convolutional Neural Network
• Random Forest
• Deep Neural Network
• Local Features
• Average Accuracy
• Class Labels
• Code Vector
• Vocabulary Learning
• Fixed-length Vector
• Dimensional Feature Space
• Feature Mining
• Feature Channels
• Color Values
• Spatial Pyramid Pooling
• Spatial Pyramid
• Dimensional Vector