The more you learn, the less you store: Memory-controlled incremental SVM for visual place recognition

Authors:
Andrzej Pronobis;Luo Jie;Barbara Caputo
Affiliations:
CAS/CVAP, The Royal Institute of Technology (KTH), SE-100 44 Stockholm, Sweden;Idiap Research Institute, Rue Marconi 19, CH-1920 Martigny, Switzerland and Swiss Federal Institute of Technology in Lausanne (EPFL), CH-1015 Lausanne, Switzerland;Idiap Research Institute, Rue Marconi 19, CH-1920 Martigny, Switzerland
Venue:
Image and Vision Computing
Year:
2010

Citing 23
Cited 4

Topological mapping for mobile robots using a combination of sonar and vision sensing

AAAI'94 Proceedings of the twelfth national conference on Artificial intelligence (vol. 2)
Learning metric-topological maps for indoor mobile robot navigation

Artificial Intelligence
Handling concept drifts in incremental learning with support vector machines

KDD '99 Proceedings of the fifth ACM SIGKDD international conference on Knowledge discovery and data mining
An introduction to support Vector Machines: and other kernel-based learning methods

An introduction to support Vector Machines: and other kernel-based learning methods
Spectral Partitioning with Indefinite Kernels Using the Nyström Extension

ECCV '02 Proceedings of the 7th European Conference on Computer Vision-Part III
Incremental Support Vector Machine Construction

ICDM '01 Proceedings of the 2001 IEEE International Conference on Data Mining
Bootstrap learning for place recognition

Eighteenth national conference on Artificial intelligence
Exact simplification of support vector solutions

The Journal of Machine Learning Research
Recognition with Local Features: the Kernel Recipe

ICCV '03 Proceedings of the Ninth IEEE International Conference on Computer Vision - Volume 2
Context-based vision system for place and object recognition

ICCV '03 Proceedings of the Ninth IEEE International Conference on Computer Vision - Volume 2
Weighted and Robust Incremental Method for Subspace Learning

ICCV '03 Proceedings of the Ninth IEEE International Conference on Computer Vision - Volume 2
Distinctive Image Features from Scale-Invariant Keypoints

International Journal of Computer Vision
Object Recognition Using Composed Receptive Field Histograms of Higher Dimensionality

ICPR '04 Proceedings of the Pattern Recognition, 17th International Conference on (ICPR'04) Volume 2 - Volume 02
Integrating Representative and Discriminative Models for Object Category Detection

ICCV '05 Proceedings of the Tenth IEEE International Conference on Computer Vision - Volume 2
The Pyramid Match Kernel: Discriminative Classification with Sets of Image Features

ICCV '05 Proceedings of the Tenth IEEE International Conference on Computer Vision - Volume 2
Class-Specific Material Categorisation

ICCV '05 Proceedings of the Tenth IEEE International Conference on Computer Vision - Volume 2
Autonomous shaping: knowledge transfer in reinforcement learning

ICML '06 Proceedings of the 23rd international conference on Machine learning
Supervised semantic labeling of places using information extracted from sensor data

Robotics and Autonomous Systems
Visual door detection integrating appearance and shape cues

Robotics and Autonomous Systems
Transfer of samples in batch reinforcement learning

Proceedings of the 25th international conference on Machine learning
COLD: The CoSy Localization Database

International Journal of Robotics Research
Biologically-inspired robotics

IROS'09 Proceedings of the 2009 IEEE/RSJ international conference on Intelligent robots and systems
Robust vision-based localization by combining an image-retrieval system with Monte Carlo localization

IEEE Transactions on Robotics

Supervised and semi-supervised online boosting tree for industrial machine vision application

Proceedings of the Fifth International Workshop on Knowledge Discovery from Sensor Data
Multi kernel learning with online-batch optimization

The Journal of Machine Learning Research
Predicting what lies ahead in the topology of indoor environments

SC'12 Proceedings of the 2012 international conference on Spatial Cognition VIII
A spatio-temporal Long-term Memory approach for visual place recognition in mobile robotic navigation

Robotics and Autonomous Systems

Quantified Score

Hi-index	0.00

Visualization

Abstract

The capability to learn from experience is a key property for autonomous cognitive systems working in realistic settings. To this end, this paper presents an SVM-based algorithm, capable of learning model representations incrementally while keeping under control memory requirements. We combine an incremental extension of SVMs [43] with a method reducing the number of support vectors needed to build the decision function without any loss in performance [15] introducing a parameter which permits a user-set trade-off between performance and memory. The resulting algorithm is able to achieve the same recognition results as the original incremental method while reducing the memory growth. Our method is especially suited to work for autonomous systems in realistic settings. We present experiments on two common scenarios in this domain: adaptation in presence of dynamic changes and transfer of knowledge between two different autonomous agents, focusing in both cases on the problem of visual place recognition applied to mobile robot topological localization. Experiments in both scenarios clearly show the power of our approach.