Rapid training data generation from image sequences for pattern recognition

Date

2011-04-15

Author

DİLAN, Rasim Askin
Koku, Ahmet Buğra
Konukseven, Erhan İlhan

Metadata

Show full item record

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

Item Usage Stats

128
views

0
downloads

This study focuses on the development of a novel technique for the rapid generation of artificial neural network training data from video streams. Videos captured on an off-road terrain are used to train artificial neural networks that learn to differentiate road and non-road sections in the captured videos. Contrary to the times-taking frame-by-frame processing, in the proposed method, classification data of road pixels is created concurrently as the video plays. The proposed method is explained in detail and its performance is evaluated against the classical hand-classified image sequences on test videos. The proposed method can also be applied to several other applications using training for recognition.

Subject Keywords

Training Data Generation , QOSS , Artificial Neural Networks , Pattern Recognition , Dataset Down Sampling

URI

https://hdl.handle.net/11511/48768

DOI

https://doi.org/10.1109/icmech.2011.5971329

Collections

Department of Mechanical Engineering, Conference / Seminar

Suggestions

OpenMETU
Core

Deep learning approach for laboratory mice grimace scaling Eral, Mustafa; Halıcı, Uğur; Department of Electrical and Electronics Engineering (2016) Deep learning is extremely attractive research topic in pattern recognition and machine learning areas. Applications in speech recognition, natural language processing, and machine vision fields gained huge acceleration in performance by employing deep learning. In this thesis, deep learning is used for medical purposes in order to scale pain degree of drug stimulated mice by examining facial grimace. For this purpose each frame in the videos in the training set were scaled manually by experts according to ...
A deep learning methodology for the flow field prediction around airfoils Duru, Cihat; Baran, Özgür Uğraş; Alemdar, Hande; Department of Mechanical Engineering (2021-9-07) This study aims to predict flow fields around airfoils using a deep learning methodology based on an encoder-decoder convolutional neural network. Neural network training and evaluation are performed from a set of computational fluid dynamics (CFD) solutions of the 2-D flow field around a group of known airfoils at a wide range of angles of attack. Reynolds averaged Navier-Stokes (RANS)-based CFD simulations are performed at a selected Mach number on the transonic regime on high-quality structured computati...
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 digital neuron realization for the random neural network model CERKEZ, CUNEYT; AYBAY, HADİ IŞIK; Halıcı, Uğur (1997-06-12) In this study the neuron of the random neural network (RNN) model (Gelenbe 1989) is designed using digital circuitry. In the RNN model, each neuron accumulates arriving pulses and can fire if its potential at a given instant of time is strictly positive. Firing occurs at random, the intervals between successive firing instants following an exponential distribution of constant rate. When a neuron fires, it routes the generated pulses to the appropriate output lines in accordance with the connection probabili...
Robust feature space separation for deep convolutional neural network training Sekmen, Ali; Parlaktuna, Mustafa; Abdul-Malek, Ayad; Erdemir, Erdem; Koku, Ahmet Buğra (2021-11-01) This paper introduces two deep convolutional neural network training techniques that lead to more robust feature subspace separation in comparison to traditional training. Assume that dataset has M labels. The first method creates M deep convolutional neural networks called {DCNNi}i=1M" role="presentation">{DCNNi}Mi=1. Each of the networks DCNNi" role="presentation">DCNNi is composed of a convolutional neural network (CNNi" role="presentation">CNNi) and a fully connected neural network (FCNNi" role="pre...

Citation Formats

R. A. DİLAN, A. B. Koku, and E. İ. Konukseven, “Rapid training data generation from image sequences for pattern recognition,” 2011, Accessed: 00, 2020. [Online]. Available: https://hdl.handle.net/11511/48768.