CURFIL: Random Forests for Image Labeling on GPU

Random forests are popular classifiers for computer vision tasks such as image labeling or object detection. Learning random forests on large datasets, however, is computationally demanding. Slow learning impedes model selection and scientific research on image features. We present an open-source implementation that significantly accelerates both random forest learning and prediction for image labeling of RGB-D and RGB images on GPU when compared to an optimized multi-core CPU implementation. We use the fast training to conduct hyper-parameter searches, which significantly improves on previous results on the NYU Depth v2 dataset. Our prediction runs in real time at VGA resolution on a mobile GPU and has been used as data term in multiple applications.

• Publication year

  2015

• Venue

  International Conference on Computer Vision Theory and Applications

• Publication date

  2015-05-01

• Fields of study

  Computer Science

• Identifiers
  DOI 10.5220/0005316201560164
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Dense 3D semantic mapping of indoor scenes from RGB-D images

  2014cited by this paper
• Dense real-time mapping of object-class semantics from RGB-D video

  2013cited by this paper
• Indoor Semantic Segmentation using depth information

  2013cited by this paper
• Learning Random Forests on the GPU

  2013cited by this paper
• Semantic mapping using object-class segmentation of RGB-D images

  2012cited by this paper
• Accelerating a Random Forest Classifier: Multi-Core, GP-GPU, or FPGA?

  2012cited by this paper
• 6D pose estimation of textureless shiny objects using random ferns for bin-picking

  2012cited by this paper
• Indoor Segmentation and Support Inference from RGBD Images

  2012cited by this paper
• Scikit-learn: Machine Learning in Python

  2011cited by this paper
• Real-time human pose recognition in parts from single depth images

  2011influential reference
• Algorithms for Hyper-Parameter Optimization

  2011cited by this paper
• Random Forests for CUDA GPUs

  2010cited by this paper
• Implementing Decision Trees and Forests on a GPU

  2008influential reference
• Semantic texton forests for image categorization and segmentation

  2008influential reference
• Keypoint recognition using randomized trees

  2006cited by this paper
• Randomized trees for real-time keypoint recognition

  2005cited by this paper
• Random Forests

  2001cited by this paper
• Shape Quantization and Recognition with Randomized Trees

  1997cited by this paper
• Decision trees and transient stability of electric power systems

  1991cited by this paper

• Unsupervised Learning in Space and Time: A Modern Approach for Computer Vision using Graph-based Techniques and Deep Neural Networks

  2020cites this paper
• Semantic RGB-D Perception for Cognitive Service Robots

  2019cites this paper
• Semantic Segmentation and Completion of 2D and 3D Scenes

  2019influential citation
• Raster Time Series: Learning and Processing (Raster Zeitreihen: Lernen und Verarbeiten)

  2019cites this paper
• RFAcc: a 3D ReRAM associative array based random forest accelerator

  2019cites this paper
• Improving random forests by neighborhood projection for effective text classification

  2018cites this paper
• Fast Cloud Segmentation Using Convolutional Neural Networks

  2018cites this paper
• Semantic segmentation for robotic using neuro-fuzzy network technique

  2017cites this paper
• Object class segmentation of RGB-D video using recurrent convolutional neural networks

  2017cites this paper
• Neuro-Fuzzy Network Technique for Semantic Segmentation Robotics

  2017cites this paper
• Combining Semantic and Geometric Features for Object Class Segmentation of Indoor Scenes

  2017cites this paper
• A new tool for supervised classification of satellite images available on web servers: Google Maps as a case study

  2016cites this paper
• A novel approach to train random forests on GPU for computer vision applications using local features

  2016cites this paper
• Real-Time Semantic Segmentation with Label Propagation

  2016influential citation
• Genetic Randomized Trees for Object Classification

  2015cites this paper
• Real-time 3D Reconstruction and Semantic Segmentation using Multi-layer Heightmaps

  2015influential citation
• Data Stream Classification Using Random Feature Functions and Novel Method Combinations

  2015cites this paper