Active search for real-time vision
The DOI matches its Crossref record; 2 of the 2 references it cites were found in a registry or an index.
Abstract
In most cases when information is to be extracted from an image, there are priors available on the state of the world and therefore on the detailed measurements which are obtained. While such priors are commonly combined with the actual measurements via Bayes' rule to calculate posterior probability distributions on model parameters, their additional value in guiding efficient image processing has almost always been overlooked. Priors tell us where to look for information in an image, how much computational effort we can expect to expend to extract it, and of how much utility to the task in hand it is likely to be. Such considerations are of importance in all practical real time vision systems, where the processing resources available at each frame in a sequence are strictly limited - and it is exactly in high frame rate real time systems such as trackers where strong priors are most likely to be available. In this paper, we use Shannon information theory to analyse the fundamental value of measurements using mutual information scores in absolute units of bits, specifically looking at the overwhelming case where uncertainty can be characterised by Gaussian probability distributions. We then compare these measurement values with the computational cost of the image processing required to obtain them. This theory puts on a firm footing for the first time principles of 'active search' for efficient guided image processing, in which candidate features of possibly different types can be compared and selected automatically for measurement.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Object recognition from local scale-invariant features
Lowe, D. G. (1999) · Proceedings of the Seventh IEEE International Conference on Computer Vision · doi:10.1109/iccv.1999.790410 · Cited by 16,472
Probability Theory: The Logic of Science
Jaynes, E. T. (2003) · doi:10.1017/cbo9780511790423 · Cited by 4,045
Cited by
MonoSLAM: Real-time single camera SLAM
Davison, A. J., Reid, I. D., Molton, N. D., & Stasse, O. (2007) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2007.1049 · Cited by 3,959
“An interesting aspect of our active search image processing is that a doubling in frame-rate would not imply a doubling of image processing effort as in bottom-up feature detection schemes (see [45]) because search regions would become correspondingly smaller due to reduced motion uncertainty.”
BackgroundMethodInfluentialSelf-citationStrasdat, H., Montiel, J. M. M., & Davison, A. J. (2012) · Image and Vision Computing · doi:10.1016/j.imavis.2012.02.009 · Cited by 439
Self-citationA Survey on Active Simultaneous Localization and Mapping: State of the Art and New Frontiers
Placed, J. A., Strader, J., Carrillo, H., Atanasov, N., Indelman, V., Carlone, L., & Castellanos, J. A. (2023) · IEEE Transactions on Robotics · doi:10.1109/tro.2023.3248510 · Cited by 332
Skeletal graphs for efficient structure from motion
Snavely, N., Seitz, S. M., & Szeliski, R. (2008) · 2008 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2008.4587678 · Cited by 271
Active Visual Object Reconstruction using D-, E-, and T-Optimal Next Best Views
Wenhardt, S., Deutsch, B., Angelopoulou, E., & Niemann, H. (2007) · 2007 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2007.383363 · Cited by 60
“A similar method is used in [3], in which the next 2-D feature for object tracking is selected via mutual information between the state and the features, and between two features.”
MethodGeneric factor-based node marginalization and edge sparsification for pose-graph SLAM
Carlevaris-Bianco, N., & Eustice, R. M. (2013) · 2013 IEEE International Conference on Robotics and Automation · doi:10.1109/icra.2013.6631403 · Cited by 52
Efficient information-theoretic graph pruning for graph-based SLAM with laser range finders
Kretzschmar, H., Stachniss, C., & Grisetti, G. (2011) · 2011 IEEE/RSJ International Conference on Intelligent Robots and Systems · doi:10.1109/iros.2011.6094414 · Cited by 48
“Davison [3] shows that in the Gaussian case the mutual information of two variables x i and x j can be efficiently 0k 1k 2k 3k 0 1000 2000 number of nodes time step no pruning our approach 0k 5k 10k 15k 0 1000 2000 number of edges time step no pruning our approach Fig.”
Background
Metadata
- Authors
- Davison, A. J.
- Venue
- Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1
- Publisher
- IEEE
- Published
- 2005
- Pages
- 66-73 Vol. 1
- OpenAlex
- W2117298007
- Cited by
- 111
- References
- 2
- FWCI
- 7.55
- Type
- conference paper
- Language
- en
- Open access
- closed
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.