A probabilistic sparse skeleton based object detection

Date

2016-11

Author

Altinoklu, Burak
Ulusoy, İlkay
Tarı, Zehra Sibel

Metadata

Show full item record

Item Usage Stats

163
views

0
downloads

We present a Markov Random Field (MRF) based skeleton model for object shape and employ it in a probabilistic chamfer-matching framework for shape based object detection. Given an object category, shape hypotheses are generated from a set of sparse (coarse) skeletons guided by suitably defined unary and binary potentials at and between shape parts. The Markov framework assures that the generated samples properly reflect the observed or desired shape variability. As the model employs a sparsely sampled skeleton, the shape hypotheses are in the form of linear boundary segments; hence, matching can be performed using Directional Chamfer Matching. As the number of states that each MRF node can take is small, the matching process is efficient. Experiments with giraffe and swan categories of the ETHZ Dataset demonstrate that the method perform well in the case of articulated objects.

Subject Keywords

Markov random field, Generative shape model, Shape skeletons, Shape-based object detection

URI

https://hdl.handle.net/11511/28314

Journal

Pattern Recognition Letters

DOI

https://doi.org/10.1016/j.patrec.2016.07.009

Collections

Department of Electrical and Electronics Engineering, Article

Suggestions

OpenMETU
Core

A logic programming framework for modeling temporal objects Çiçekli, Fehime Nihan; Sergot, M (1996-10-01) We present a general approach for modeling temporal aspects of objects in a logic programming framework. Change is formulated in the context of a database which stores explicitly a record of all changes that have occurred to objects and thus (implicitly) all states of objects in the database. A snapshot of the database at any given time is an object-oriented database, in the sense that it supports an object-based data model. An object is viewed as a collection of simple atomic formulas, with support for an ...
A High throughput FPGA implementation of markov chain monte carlo method for mixture models Bozgan, Caner; Ulusoy, İlkay; Department of Electrical and Electronics Engineering (2019) Markov Chain Monte Carlo (MCMC) is a class of algorithms which can generate samples from high dimensional and multimodal probability distributions. In many statistical and control applications, MCMC algorithms are employed widely thanks to their ability to draw sample from arbitrary distribution regardless of dimension or complexity. However, as the complexity of the Bayesian models and the computational load of the MCMC algorithm increase, performing MCMC inference becomes impractical or too time consuming...
A shape descriptor based on circular Hidden Markov Model Arica, N; Yarman Vural, Fatoş Tunay (2000-09-07) Given the shape information of an object, can we find visually meaningful "n" objects in an image database, which is ranked from the most similar to the n(th) similar one? The answer to this question depends on the complexity of the images in the database and the complexity of the objects in the query.
A Genetic Isometric Shape Correspondence Algorithm with Adaptive Sampling Sahillioğlu, Yusuf (2018-11-01) We exploit the permutation creation ability of genetic optimization to find the permutation of one point set that puts it into correspondence with another one. To this end, we provide a genetic algorithm for the 3D shape correspondence problem, which is the main contribution of this article. As another significant contribution, we present an adaptive sampling approach that relocates the matched points based on the currently available correspondence via an alternating optimization. The point sets to be match...
A Ranking-based, Balanced Loss Function Unifying Classification and Localisation in Object Detection Öksüz, Kemal; Çam, Barış Can; Akbaş, Emre; Kalkan, Sinan (2020-12-06) We propose average Localisation-Recall-Precision (aLRP), a unified, bounded, balanced and ranking-based loss function for both classification and localisation tasks in object detection. aLRP extends the Localisation-Recall-Precision (LRP) performance metric (Oksuz et al., 2018) inspired from how Average Precision (AP) Loss extends precision to a ranking-based loss function for classification (Chen et al., 2020). aLRP has the following distinct advantages: (i) aLRP is the first ranking-based loss function fo...

Citation Formats

B. Altinoklu, İ. Ulusoy, and Z. S. Tarı, “A probabilistic sparse skeleton based object detection,” Pattern Recognition Letters, pp. 243–250, 2016, Accessed: 00, 2020. [Online]. Available: https://hdl.handle.net/11511/28314.