A Novel Bag-of-Visual-Words Approach for Geospatial Object Detection

Date

2011-04-29

Author

Aytekin, Caglar
Alatan, Abdullah Aydın

Metadata

Show full item record

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Item Usage Stats

143
views

0
downloads

A novel bag-of-visual-words algorithm is presented with two extensions compared to its classical version: exploiting scale information and weighting visual words. The scale information that is already extracted with SIFT detector is included as an additional element to the SIFT key-point descriptor, while the visual words are weighted during histogram assignment proportional to their importance which is measured by the ratio of their occurrences in the object to the occurrences in the background. The algorithm is tested for different geo-spatial object classes and the performance of the classical bag-of-visual-words algorithm is compared against the classical approach. Based on these results, a significant improvement is observed in terms of detection performance.

Subject Keywords

Bag-of-visual-words, Geospatial object recognition, SIFT, Scale information, Weighting visual words

URI

https://hdl.handle.net/11511/48102

DOI

https://doi.org/10.1117/12.883801

Collections

Department of Electrical and Electronics Engineering, Conference / Seminar

Suggestions

OpenMETU
Core

A NOVEL BOVW MIMICKING END-TO-END TRAINABLE CNN CLASSIFICATION FRAMEWORK USING OPTIMAL TRANSPORT THEORY Gürbüz, Yeti Ziya (2019-01-01) An end-to-end trainable convolutional neural network (CNN) framework which mimics bag of visual words (BoVW) is proposed for image classification. To this end, a new paradigm for histogram-like image representation is introduced and optimal transport (OT) distance is utilized for the similarity assessment. Any patch of an image is considered as a unique visual word and the image is represented as the uniform histogram of the visual words with the histogram bins associated to embedding vectors according to t...
A novel neural network based approach for direction of arrival estimation Çaylar, Selçuk; Dural Ünver, Mevlüde Gülbin; Department of Electrical and Electronics Engineering (2007) In this study, a neural network(NN) based algorithm is proposed for real time multiple source tracking problem based on a previously reported work. The proposed algorithm namely modified neural network based multiple source tracking algorithm (MN-MUST) performs direction of arrival(DoA) estimation in three stages which are the detection, filtering and DoA estimation stages. The main contributions of this proposed system are: reducing the input size for the uncorrelated source case (reducing the training tim...
A Customized force-directed layout algorithm for biological graphs whose vertices have enzyme commission attributes Danacı, Hasan Fehmi; Atalay, Mehmet Volkan; Department of Computer Engineering (2015) Force directed layout algorithm is popularly used to draw biological graphs. However, it employs only graph structure. When we would like to embed domain-specific knowledge, such as biological or chemical attributes related to the vertices, force directed layout algorithm should be modified. It is then important to draw more readable layouts for biologists without the dispose of aesthetically pleasing way that comes from force-directed algorithm’s nature. This thesis aims to describe a modified and improved...
A matching algorithm based on Godel coding scheme Dicle, N; Atalay, Mehmet Volkan (2000-01-28) We describe an algorithm for the correspondence of line features between two consecutive images. The algorithm is based on Godel coding of the features and singular value decomposition. First, line segments are extracted by Canny operator followed by the end-point-fit method. Line segments are represented by coordinates of midpoints and the angle of a perpendicular line from a reference point. Then, a proximity matrix is constructed following the minimal mapping theory of Ullman. Thus if two line segments a...
A Layout algorithm for visualization of graph alignments Akarsu, Andaç; Can, Tolga; Department of Computer Engineering (2017) Graph layout algorithms are commonly used when visualizing. Usually these algorithms focus on a single graph. To be able to visualize multiple graphs at once, such as the results of graph alignment algorithms on biological networks, new layout algorithms need to be developed. A layout algorithm for visualizing graph alignments should display the aligned graphs separately, so that both the graphs and their alignment can be viewed individually. In addition, for better interpretation of the alignment results, ...

Citation Formats

C. Aytekin and A. A. Alatan, “A Novel Bag-of-Visual-Words Approach for Geospatial Object Detection,” 2011, vol. 8055, Accessed: 00, 2020. [Online]. Available: https://hdl.handle.net/11511/48102.