skip to main content
10.1145/1646396.1646405acmconferencesArticle/Chapter ViewAbstractPublication PagescivrConference Proceedingsconference-collections
research-article

Real-time bag of words, approximately

Published: 08 July 2009 Publication History

Abstract

We start from the state-of-the-art Bag of Words pipeline that in the 2008 benchmarks of TRECvid and PASCAL yielded the best performance scores. We have contributed to that pipeline, which now forms the basis to compare various fast alternatives for all of its components: (i) For descriptor extraction we propose a fast algorithm to densely sample SIFT and SURF, and we compare several variants of these descriptors. (ii) For descriptor projection we compare a k-means visual vocabulary with a Random Forest. As a preprojection step we experiment with PCA on the descriptors to decrease projection time. (iii) For classification we use Support Vector Machines and compare the x2 kernel with the RBF kernel. Our results lead to a 10-fold speed increase without any loss of accuracy and to a 30-fold speed increase with 17% loss of accuracy, where the latter system does real-time classification at 26 images per second.

References

[1]
H. Bay, A. Ess, T. Tuytelaars, and L. Van Gool. Speeded-up robust features (SURF). Computer Vision and Image Understanding, 110: 346--359, 2008.
[2]
M. Everingham and J. Winn. The Pascal VOC challenge 2007 development kit. Technical report, University of Leeds, 2007.
[3]
P. Geurts, D. Ernst, and L. Wehenkel. Extremely randomized trees. Machine Learning, 63(1): 3--42, 2006.
[4]
J. M. Geusebroek, A. W. M. Smeulders, and J. van de Weijer. Fast anisotropic gauss filtering. IEEE Transactions on Image Processing, 12: 938--943, 2003.
[5]
M. Grabner, H. Grabner, and H. Bischof. Fast approximated SIFT. In ACCV, 2006.
[6]
Y. G. Jiang, C. W. Ngo, and J. Yang. Towards optimal bag-of-features for object categorization and semantic video retrieval. In CIVR, 2007.
[7]
F. Jurie and B. Triggs. Creating efficient codebooks for visual recognition. In ICCV, 2005.
[8]
S. Lazebnik, C. Schmid, and J. Ponce. Beyond bags of features: Spatial pyramid matching for recognizing natural scene categories. In CVPR, 2006.
[9]
D. G. Lowe. Distinctive image features from scale-invariant keypoints. IJCV, 60: 91--110, 2004.
[10]
M. Marszałek, C. Schmid, H. Harzallah, and J. van de Weijer. Learning representations for visual object class recognition. Pascal VOC 2007 challenge workshop. ICCV, 2007.
[11]
K. Mikolajczyk, B. Leibe, and B. Schiele. Local features for object class recognition. In ICCV, 2005.
[12]
K. Mikolajczyk and J. Matas. Improving descriptors for fast tree matching by optimal linear projection. In ICCV, 2007.
[13]
K. Mikolajczyk and C. Schmid. A performance evaluation of local descriptors. PAMI, 27: 1615--1630, 2005.
[14]
F. Moosmann, E. Nowak, and F. Jurie. Randomized clustering forests for image classification. PAMI, 9: 1632--1646, 2008.
[15]
F. Moosmann, B. Triggs, and F. Jurie. Fast discriminative visual codebooks using randomized clustering forests. In NIPS, pages 985--992, 2006.
[16]
D. Nistér and H. Stewénius. Scalable recognition with a vocabulary tree. In CVPR, 2006.
[17]
J. Shotton, M. Johnson, and R. Cipolla. Semantic texton forests for image categorization and segmentation. In CVPR, 2008.
[18]
A. F. Smeaton, P. Over, and W. Kraaij. Evaluation campaigns and TRECVID. In MIR, 2006.
[19]
M. A. Tahir, K. van de Sande, J. Uijlings, F. Yan, X. Li, K. Mikolajczyk, J. Kittler, T. Gevers, and A. Smeulders. Uva and surrey @ pascal voc 2008. Pascal VOC 2008 challenge workshop. ECCV, 2008.
[20]
K. E. A. van de Sande, T. Gevers, and C. G. M. Snoek. A comparison of color features for visual concept classification. In CIVR, 2008.
[21]
J. Zhang, M. Marszałek, S. Lazebnik, and C. Schmid. Local Features and Kernels for Classification of Texture and Object Categories: A Comprehensive Study. IJCV, 73(2): 213--238, 2007.

Cited By

View all
  • (2023)An Overview of Key SLAM Technologies for Underwater ScenesRemote Sensing10.3390/rs1510249615:10(2496)Online publication date: 9-May-2023
  • (2021)Exploitation whale optimization based optimal offloading approach and topology optimization in a mobile ad hoc cloud environmentJournal of Ambient Intelligence and Humanized Computing10.1007/s12652-021-02945-zOnline publication date: 1-Mar-2021
  • (2019)Abnormal crowd density estimation in aerial imagesJournal of Electronic Imaging10.1117/1.JEI.28.1.01304728:01(1)Online publication date: 26-Feb-2019
  • Show More Cited By

Recommendations

Comments

Information & Contributors

Information

Published In

cover image ACM Conferences
CIVR '09: Proceedings of the ACM International Conference on Image and Video Retrieval
July 2009
383 pages
ISBN:9781605584805
DOI:10.1145/1646396
Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]

Sponsors

In-Cooperation

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 08 July 2009

Permissions

Request permissions for this article.

Check for updates

Author Tags

  1. bag of words
  2. computational efficiency
  3. feature extraction
  4. image retrieval
  5. random forest

Qualifiers

  • Research-article

Conference

CIVR '09
Sponsor:

Contributors

Other Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

  • Downloads (Last 12 months)32
  • Downloads (Last 6 weeks)5
Reflects downloads up to 16 Feb 2025

Other Metrics

Citations

Cited By

View all
  • (2023)An Overview of Key SLAM Technologies for Underwater ScenesRemote Sensing10.3390/rs1510249615:10(2496)Online publication date: 9-May-2023
  • (2021)Exploitation whale optimization based optimal offloading approach and topology optimization in a mobile ad hoc cloud environmentJournal of Ambient Intelligence and Humanized Computing10.1007/s12652-021-02945-zOnline publication date: 1-Mar-2021
  • (2019)Abnormal crowd density estimation in aerial imagesJournal of Electronic Imaging10.1117/1.JEI.28.1.01304728:01(1)Online publication date: 26-Feb-2019
  • (2018)Dynamic Reconstruction of Deformable Soft-Tissue With Stereo Scope in Minimal Invasive SurgeryIEEE Robotics and Automation Letters10.1109/LRA.2017.27354873:1(155-162)Online publication date: Jan-2018
  • (2018)An improved deep learning approach for detection of thyroid papillary cancer in ultrasound imagesScientific Reports10.1038/s41598-018-25005-78:1Online publication date: 26-Apr-2018
  • (2017)Real-time graph-based SLAM in unknown environments using a small UAV2017 International Conference on Unmanned Aircraft Systems (ICUAS)10.1109/ICUAS.2017.7991524(1118-1123)Online publication date: Jun-2017
  • (2017)Image processing based proposed drone for detecting and controlling street crimes2017 IEEE 17th International Conference on Communication Technology (ICCT)10.1109/ICCT.2017.8359925(1725-1730)Online publication date: Oct-2017
  • (2017)A multi-language approach towards the identification of suspicious users on social networks2017 International Carnahan Conference on Security Technology (ICCST)10.1109/CCST.2017.8167794(1-6)Online publication date: Oct-2017
  • (2017)Extensive exploration of comprehensive vehicle attributes using D‐CNN with weighted multi‐attribute strategyIET Intelligent Transport Systems10.1049/iet-its.2017.006612:3(186-193)Online publication date: 19-Dec-2017
  • (2016)[Invited Paper] Semantic Indexing for Large-Scale Video RetrievalITE Transactions on Media Technology and Applications10.3169/mta.4.2094:3(209-217)Online publication date: 2016
  • Show More Cited By

View Options

Login options

View options

PDF

View or Download as a PDF file.

PDF

eReader

View online with eReader.

eReader

Figures

Tables

Media

Share

Share

Share this Publication link

Share on social media