Visual Loop Closure Detection with Thorough Temporal and Spatial Context Exploitation

Despite advancements in visual Simultaneous Localization and Mapping (SLAM), prevailing visual Loop Closure Detection (LCD) methods primarily rely on computationally intensive image similarity comparisons, neglecting temporal-spatial context during long-term exploration. To address this issue, we propose TOSA, a novel visual LCD algorithm harnessing TempOral and SpAtial context for efficient LCD. Specifically, as the agent explores through time, our approach recurrently updates a latent feature incorporating historical information via a Long Short-Term Memory (LSTM) module. Upon receiving a query frame, TOSA seamlessly fuses the latent feature with the query feature to predict the candidates’ distribution, thus averting intensive similarity computation. Additionally, TOSA integrates a temporal-spatial convolution for candidate refinement by thoroughly exploiting the temporal consistency and spatial correlation to enhance selected candidates, further boosting the performance. Extensive experiments across four standard datasets showcase the superiority of our method over existing state-of-the-art techniques, demonstrating the effectiveness of utilizing rich temporal-spatial contexts.

Authors

• Jiaxin Li
• Zan Wang
• Huijun Di
• Jian Li
• Wei Liang 0008

Keywords

• Visualization
• Simultaneous localization and mapping
• Correlation
• Convolution
• Multi label classification
• Prediction algorithms
• Liquid crystal displays
• Proposals
• Long short term memory
• Standards
• Spatial Context
• Temporal Context
• Loop Closure
• Loop Closure Detection
• Extensive Experiments
• Long Short-term Memory
• Consistent Correlation
• Latent Features
• Temporal Consistency
• Query Features
• Image Features
• Spatial Information
• Temporal Dimension
• Spatial Dimensions
• City Centre
• Global Features
• Precision And Recall
• Multilayer Perceptron
• Convolution Operation
• Temporal Information
• Self-supervised Learning
• Historical Framing
• Multi-label Classification Task
• Latent State
• Memory Usage
• Position Weight Matrices
• Feature Extraction Network
• Image Descriptors
• Intrinsic Information