Implementation of Target Tracking Methods on Images Taken from Unmanned Aerial Vehicles
17th IEEE World Symposium on Applied Machine Intelligence and Informatics, SAMI 2019 --24 January 2019 through 26 January 2019 -- -- Traditional object detection algorithms generate proposals and implement feature extraction. Then, a classification algorithm is implemented to label object classes. T...
Published in: | 2019 IEEE 17th World Symposium on Applied Machine Intelligence and Informatics (SAMI) |
---|---|
Main Authors: | , |
Other Authors: | |
Format: | Conference Object |
Language: | English |
Published: |
Institute of Electrical and Electronics Engineers Inc.
2019
|
Subjects: | |
Online Access: | https://hdl.handle.net/20.500.12605/16164 https://doi.org/10.1109/SAMI.2019.8782768 |
id |
ftcukurovauniv:oai:openaccess.cu.edu.tr:20.500.12605/16164 |
---|---|
record_format |
openpolar |
spelling |
ftcukurovauniv:oai:openaccess.cu.edu.tr:20.500.12605/16164 2023-08-27T04:11:47+02:00 Implementation of Target Tracking Methods on Images Taken from Unmanned Aerial Vehicles Eriş H. Çevik U. Çukurova Üniversitesi 2019 https://hdl.handle.net/20.500.12605/16164 https://doi.org/10.1109/SAMI.2019.8782768 English eng Institute of Electrical and Electronics Engineers Inc. 10.1109/SAMI.2019.8782768 SAMI 2019 - IEEE 17th World Symposium on Applied Machine Intelligence and Informatics, Proceedings Konferans Öğesi - Uluslararası - Kurum Öğretim Elemanı 9781728102504 https://dx.doi.org/10.1109/SAMI.2019.8782768 https://hdl.handle.net/20.500.12605/16164 311 316 info:eu-repo/semantics/closedAccess convolutional neural network deep learning image analysis neural network object classification target tracking conferenceObject 2019 ftcukurovauniv https://doi.org/20.500.12605/1616410.1109/SAMI.2019.8782768 2023-08-05T18:08:41Z 17th IEEE World Symposium on Applied Machine Intelligence and Informatics, SAMI 2019 --24 January 2019 through 26 January 2019 -- -- Traditional object detection algorithms generate proposals and implement feature extraction. Then, a classification algorithm is implemented to label object classes. This process is slow, and the accuracy may not be adequate for UAV's real-time application tasks due to their movement in the air. We specified and practically implemented an object detection and localization scheme on images taken from a UAV, and provided the UAV with an advanced vision. We used YOLOv2 model. The YOLOv2 is a suitable object detection approach based on deep learning, and it presents a network architecture with accurate results in high speed. The object detection and localization were successfully implemented for people, car, and motorcycle classes within the threshold confidence scores. We pre-trained the model on COCO dataset and tested the model with our test images. The confidence scores were higher in altitudes from 5 to 15 meters and the confidence scores varied between - mAP. © 2019 IEEE. Conference Object sami Çukurova University Institutional Repository 2019 IEEE 17th World Symposium on Applied Machine Intelligence and Informatics (SAMI) 311 316 |
institution |
Open Polar |
collection |
Çukurova University Institutional Repository |
op_collection_id |
ftcukurovauniv |
language |
English |
topic |
convolutional neural network deep learning image analysis neural network object classification target tracking |
spellingShingle |
convolutional neural network deep learning image analysis neural network object classification target tracking Eriş H. Çevik U. Implementation of Target Tracking Methods on Images Taken from Unmanned Aerial Vehicles |
topic_facet |
convolutional neural network deep learning image analysis neural network object classification target tracking |
description |
17th IEEE World Symposium on Applied Machine Intelligence and Informatics, SAMI 2019 --24 January 2019 through 26 January 2019 -- -- Traditional object detection algorithms generate proposals and implement feature extraction. Then, a classification algorithm is implemented to label object classes. This process is slow, and the accuracy may not be adequate for UAV's real-time application tasks due to their movement in the air. We specified and practically implemented an object detection and localization scheme on images taken from a UAV, and provided the UAV with an advanced vision. We used YOLOv2 model. The YOLOv2 is a suitable object detection approach based on deep learning, and it presents a network architecture with accurate results in high speed. The object detection and localization were successfully implemented for people, car, and motorcycle classes within the threshold confidence scores. We pre-trained the model on COCO dataset and tested the model with our test images. The confidence scores were higher in altitudes from 5 to 15 meters and the confidence scores varied between - mAP. © 2019 IEEE. |
author2 |
Çukurova Üniversitesi |
format |
Conference Object |
author |
Eriş H. Çevik U. |
author_facet |
Eriş H. Çevik U. |
author_sort |
Eriş H. |
title |
Implementation of Target Tracking Methods on Images Taken from Unmanned Aerial Vehicles |
title_short |
Implementation of Target Tracking Methods on Images Taken from Unmanned Aerial Vehicles |
title_full |
Implementation of Target Tracking Methods on Images Taken from Unmanned Aerial Vehicles |
title_fullStr |
Implementation of Target Tracking Methods on Images Taken from Unmanned Aerial Vehicles |
title_full_unstemmed |
Implementation of Target Tracking Methods on Images Taken from Unmanned Aerial Vehicles |
title_sort |
implementation of target tracking methods on images taken from unmanned aerial vehicles |
publisher |
Institute of Electrical and Electronics Engineers Inc. |
publishDate |
2019 |
url |
https://hdl.handle.net/20.500.12605/16164 https://doi.org/10.1109/SAMI.2019.8782768 |
genre |
sami |
genre_facet |
sami |
op_relation |
10.1109/SAMI.2019.8782768 SAMI 2019 - IEEE 17th World Symposium on Applied Machine Intelligence and Informatics, Proceedings Konferans Öğesi - Uluslararası - Kurum Öğretim Elemanı 9781728102504 https://dx.doi.org/10.1109/SAMI.2019.8782768 https://hdl.handle.net/20.500.12605/16164 311 316 |
op_rights |
info:eu-repo/semantics/closedAccess |
op_doi |
https://doi.org/20.500.12605/1616410.1109/SAMI.2019.8782768 |
container_title |
2019 IEEE 17th World Symposium on Applied Machine Intelligence and Informatics (SAMI) |
container_start_page |
311 |
op_container_end_page |
316 |
_version_ |
1775354964516798464 |