A Learning-based method for person re-identification

Download

index.pdf

Date

2013

Author

Oğul, Burçin Buket

Metadata

Show full item record

Item Usage Stats

154
views

64
downloads

Matching pedestrian images captured from different cameras is called person re-identification problem. The problem is challenging due to the low resolution of images, differences in illumination, the positional variance and possible appearance of carried objects, such as a bag, at different viewpoints. In this thesis, we investigate the discriminative ability of different features extracted from image in a binary classification framework. We finally propose a learning based method to combine different feature sets, Hue, Saturation, Value (HSV) histogram, Maximally Stable Color Regions (MSCR) and Speeded up Robust Features (SURF) matches, in a single framework. The experiments on widely used benchmark sets have shown that the best accuracy is obtained with weighted and localized histogram features. We also argue that further division of pedestrian body along the horizontal axis has the potential to increase the reidentification performance. Final integrative framework that we built outperforms the existing state-of-the-art models in terms of prediction accuracy.

Subject Keywords

Image processing., Image analysis., Image processing, Imaging systems

URI

http://etd.lib.metu.edu.tr/upload/12615933/index.pdf
https://hdl.handle.net/11511/22627

Collections

Graduate School of Informatics, Thesis

Suggestions

OpenMETU
Core

A Fast shape detection approach by directional integrations Okman, Osman Erman; Akar, Gözde; Department of Electrical and Electronics Engineering (2013) Detection and identification of objects from aerial images are important problems for various types of application areas. For many of the man-made structures shape is a fundamental feature by which these objects are separated from the background and other structures. In this thesis, a novel geometric shape detection algorithm based on the spatial properties of structures is proposed. Since the objects are transformed into 1-D vectors by evaluating directional integrals and detections occur by the analysis o...
An Evaluation of ghost removal algorithms for exposure fusion Kutlu, Tuğser; Akar, Gözde; Department of Electrical and Electronics Engineering (2015) In high dynamic range imaging (HDR), the goal is to capture a scene with a higher dynamic range than the camera capable of capturing with a single exposure. Similar to HDR, exposure fusion is a process that takes multiple images and combines them to create a single dynamically enhanced image by only keeping the properly exposed elements. When using multiple images, local motion of objects can influence the quality of the final image in such a way that local motion of objects causes a ghost artifact. In this...
Alignment of uncalibrated images for multi-view classification Arık, Sercan Ömer; Vural, Elif; Frossard, Pascal (2011-12-29) Efficient solutions for the classification of multi-view images can be built on graph-based algorithms when little information is known about the scene or cameras. Such methods typically require a pairwise similarity measure between images, where a common choice is the Euclidean distance. However, the accuracy of the Euclidean distance as a similarity measure is restricted to cases where images are captured from nearby viewpoints. In settings with large transformations and viewpoint changes, alignment of im...
The State of the art in HDR deghosting and an objective HDR image deghosting quality metric Tursun, Okan Tarhan; Akyüz, Ahmet Oğuz; Department of Computer Engineering (2016) Despite the emergence of new HDR acquisition methods, the multiple exposure technique (MET) is still the most popular one. The application of MET on dynamic scenes is a challenging task due to the diversity of motion patterns and uncontrollable factors such as sensor noise, scene occlusion and performance concerns on some platforms with limited computational capability. Currently, there are already more than 50 deghosting algorithms proposed for artifact-free HDR imaging of dynamic scenes and it is expected...
Deep joint deinterlacing and denoising for single shot dual-ISO HDR reconstruction Çoğalan, Uğur; Akyüz, Ahmet Oğuz; Department of Computer Engineering (2019) HDR (High Dynamic Range) images have traditionally been obtained by merging multiple exposures each captured with a different exposure time. However, this approach entails longer capture times and necessitates deghosting if the captured scene contains moving objects. With the advent of modern camera sensors that can perform per-pixel exposure modulation, it is now possible to capture all of the required exposures within a single shot. The new challenge then becomes how to best combine different pixels with ...

Citation Formats

B. B. Oğul, “A Learning-based method for person re-identification,” M.S. - Master of Science, Middle East Technical University, 2013.