A spatio-temporal probabilistic model for multi-sensor object recognition

This paper presents a general framework for multi-sensor object recognition through a discriminative probabilistic approach modelling spatial and temporal correlations. The algorithm is developed in the context of Conditional Random Fields (CRFs) trained with virtual evidence boosting. The resulting system is able to integrate arbitrary sensor information and incorporate features extracted from the data. The spatial relationships captured by are further integrated into a smoothing algorithm to improve recognition over time. We demonstrate the benefits of modelling spatial and temporal relationships for the problem of detecting cars using laser and vision data in outdoor environments.

Authors

• Bertrand Douillard
• Dieter Fox
• Fabio Ramos 0001

Keywords

• Object recognition
• Robot sensing systems
• Laser modes
• Boosting
• Object detection
• Intelligent robots
• USA Councils
• Australia
• Computer vision
• Application software
• Recognition Model
• Spatiotemporal Model
• Outdoor Environments
• Temporal Relationship
• Temporal Correlation
• Conditional Random Field
• Laser Scanning
• Classification Results
• Hidden Markov Model
• Visual Features
• Conditional Distribution
• Geometric Features
• Hidden State
• Temporal Dependencies
• Continuous Features
• Time Slice
• Hidden Variables
• Local Shape
• Discrete Features
• Conditional Random Field Model
• Iterative Closest Point Algorithm
• Iterative Closest Point
• Simultaneous Localization And Mapping
• Laser Ranging
• Arbitrary Features
• Belief Propagation
• Urban Environments
• Scale Variation
• Representation Of The Environment