Mr. Caglar Kavak Profile

Caglar Kavak

at ASELSAN A.S.

SPIE Involvement:

Author

Publications (2)

This will count as one of your downloads.

You will have access to both the presentation and article (if available).

DOWNLOAD NOW

This content is available for download via your institution's subscription. To access this item, please sign in to your personal account.

Email or Username Forgot your username?

Password Forgot your password?

Show

Keep me signed in

No SPIE account? Create an account

Proceedings Article | 28 October 2022 Presentation + Paper

Automated example selection for iterative training of annotation networks

Ugur Berk Sahin, Caglar Kavak, Yoldas Ataseven, Anıl Turker

Proceedings Volume 12276, 1227605 (2022) https://doi.org/10.1117/12.2636013

KEYWORDS: Video, Sensors, Video processing, Data modeling, Cameras, Detection and tracking algorithms, Visualization, Machine learning, Image processing, Evolutionary algorithms

Read Abstract +

Data annotation is a time-consuming, labor-intensive step in supervised learning, mainly for detection and classification. Most of the time, human effort for annotation is required to obtain an accurately labeled dataset, which is time-consuming and sometimes impossible, especially for large datasets. Most of the novel methods use various networks to annotate the data. However, numerous hand-labeled data are still required for those methods. In order to solve this problem, we propose a method to make the process as human-independent as possible while preserving the annotation performance. The proposed method is applicable to datasets, for which the majority of the frames/images contain a single object (or a known number, ”n”, of objects). The method starts with an initial annotation network that is trained with a small amount of labeled data, %10 of the total training set, and then it continues iteratively. We use the annotation network to select the subset of the training set that is to be hand-labeled for the next iteration. This way, examples that are more likely to improve the annotation network can be selected. The total number of necessary hand-labeled images is dependent on the specific problem. We observed that when the proposed approach was used rather than annotating all the images, manually annotating approximately %25 of the dataset was sufficient. This percentage can vary according to the complexity and the type of the annotation network, as well as the dataset content. Our method can be used with existing (semi) automatic annotation tools.

Proceedings Article | 12 May 2015 Paper

Memory efficient atmospheric effects modeling for infrared scene generators

Çağlar Kavak, Seçkin Özsaraç

Proceedings Volume 9452, 945212 (2015) https://doi.org/10.1117/12.2176852

KEYWORDS: Atmospheric modeling, Transmittance, Atmospheric physics, Sensors, Mid-IR, Long wavelength infrared, Infrared radiation, Data modeling, OpenGL, Electro optical modeling

Read Abstract +

The infrared (IR) energy radiated from any source passes through the atmosphere before reaching the sensor. As a result, the total signature captured by the IR sensor is significantly modified by the atmospheric effects. The dominant physical quantities that constitute the mentioned atmospheric effects are the atmospheric transmittance and the atmospheric path radiance. The incoming IR radiation is attenuated by the transmittance and path radiance is added on top of the attenuated radiation. In IR scene simulations OpenGL is widely used for rendering purposes. In the literature there are studies, which model the atmospheric effects in an IR band using OpenGLs exponential fog model as suggested by Beers law. In the standard pipeline of OpenGL, the related fog model needs single equivalent OpenGL variables for the transmittance and path radiance, which actually depend on both the distance between the source and the sensor and also on the wavelength of interest. However, in the conditions where the range dependency cannot be modeled as an exponential function, it is not accurate to replace the atmospheric quantities with a single parameter. The introduction of OpenGL Shading Language (GLSL) has enabled the developers to use the GPU more flexible. In this paper, a novel method is proposed for the atmospheric effects modeling using the least squares estimation with polynomial fitting by programmable OpenGL shader programs built with GLSL. In this context, a radiative transfer model code is used to obtain the transmittance and path radiance data. Then, polynomial fits are computed for the range dependency of these variables. Hence, the atmospheric effects model data that will be uploaded in the GPU memory is significantly reduced. Moreover, the error because of fitting is negligible as long as narrow IR bands are used.

My Library

You currently do not have any folders to save your paper to! Create a new folder below.

Folder Name

Folder Description

View contact details

UPDATE YOUR PROFILE

Is this your profile? Update it now.

Sign into your SPIE.org account

Don’t have a profile and want one?

Create an account on SPIE.org

Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks. You are receiving this notice because your organization may not have SPIE eBooks access.*

*Shibboleth/Open Athens users─please sign in to access your institution's subscriptions.

To obtain this item, you may purchase the complete book in print or electronic format on SPIE.org.

ORGANIZATIONAL
Sign in with credentials provided by your organization.

Organizational Username

Organizational Password

Show/Hide Password

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available

Members:

Non-members: ADD TO CART

Keywords/Phrases

Search In:

Publication Years