Object Recognition and Positioning with Neural Networks: Single Ultrasonic Sensor Scanning Approach

Ultrasonic sensing may become a useful technique for distance measurement and object detection when optical visibility is not available. However, the research on detecting multiple target objects and locating their coordinates is limited. This makes it a valuable topic. Reflection signal data obtain...

Full description

Saved in:
Bibliographic Details
Main Authors: Ahmet Karagoz, Gokhan Dindis
Format: Article
Language:English
Published: MDPI AG 2025-02-01
Series:Sensors
Subjects:
Online Access:https://www.mdpi.com/1424-8220/25/4/1086
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849719154180882432
author Ahmet Karagoz
Gokhan Dindis
author_facet Ahmet Karagoz
Gokhan Dindis
author_sort Ahmet Karagoz
collection DOAJ
description Ultrasonic sensing may become a useful technique for distance measurement and object detection when optical visibility is not available. However, the research on detecting multiple target objects and locating their coordinates is limited. This makes it a valuable topic. Reflection signal data obtained from a single ultrasonic sensor may be just enough for the measurements of distance and reflection strength. On the other hand, if extracted properly, a scanned set of signal data by the same sensor holds a significant amount of information about the surrounding geometries. Evaluating this dataset from a single sensor scanning can be a perfect application for convolutional neural networks (CNNs). This study proposes an imaging technique based on a scanned dataset obtained by a single low-cost ultrasonic sensor. So that images are suitable for desired outputs in a CNN, a 3D printer is converted to an ultrasonic image scanner and automated to perform as a data acquisition system for the desired datasets. A deep learning model demonstrated by this work extracts object features using convolutional neural networks (CNNs) and performs coordinate estimation using regression layers. With the proposed solution, by training a reasonable amount of obtained data, 90% accuracy was achieved in the classification and position estimation of multiple objects with the CNN algorithm as a result of converting the signals obtained from ultrasonic sensors into images.
format Article
id doaj-art-78cedb7e9d90449fafd67719aaf276ea
institution DOAJ
issn 1424-8220
language English
publishDate 2025-02-01
publisher MDPI AG
record_format Article
series Sensors
spelling doaj-art-78cedb7e9d90449fafd67719aaf276ea2025-08-20T03:12:12ZengMDPI AGSensors1424-82202025-02-01254108610.3390/s25041086Object Recognition and Positioning with Neural Networks: Single Ultrasonic Sensor Scanning ApproachAhmet Karagoz0Gokhan Dindis1Department of Electrical and Electronics Engineering, Faculty of Engineering and Architecture, Eskisehir Osmangazi University, Eskisehir 26040, TürkiyeDepartment of Electrical and Electronics Engineering, Faculty of Engineering and Architecture, Eskisehir Osmangazi University, Eskisehir 26040, TürkiyeUltrasonic sensing may become a useful technique for distance measurement and object detection when optical visibility is not available. However, the research on detecting multiple target objects and locating their coordinates is limited. This makes it a valuable topic. Reflection signal data obtained from a single ultrasonic sensor may be just enough for the measurements of distance and reflection strength. On the other hand, if extracted properly, a scanned set of signal data by the same sensor holds a significant amount of information about the surrounding geometries. Evaluating this dataset from a single sensor scanning can be a perfect application for convolutional neural networks (CNNs). This study proposes an imaging technique based on a scanned dataset obtained by a single low-cost ultrasonic sensor. So that images are suitable for desired outputs in a CNN, a 3D printer is converted to an ultrasonic image scanner and automated to perform as a data acquisition system for the desired datasets. A deep learning model demonstrated by this work extracts object features using convolutional neural networks (CNNs) and performs coordinate estimation using regression layers. With the proposed solution, by training a reasonable amount of obtained data, 90% accuracy was achieved in the classification and position estimation of multiple objects with the CNN algorithm as a result of converting the signals obtained from ultrasonic sensors into images.https://www.mdpi.com/1424-8220/25/4/1086ultrasonic sensorssignal classificationconvolutional neural networkssignal processingobject recognitionmachine learning
spellingShingle Ahmet Karagoz
Gokhan Dindis
Object Recognition and Positioning with Neural Networks: Single Ultrasonic Sensor Scanning Approach
Sensors
ultrasonic sensors
signal classification
convolutional neural networks
signal processing
object recognition
machine learning
title Object Recognition and Positioning with Neural Networks: Single Ultrasonic Sensor Scanning Approach
title_full Object Recognition and Positioning with Neural Networks: Single Ultrasonic Sensor Scanning Approach
title_fullStr Object Recognition and Positioning with Neural Networks: Single Ultrasonic Sensor Scanning Approach
title_full_unstemmed Object Recognition and Positioning with Neural Networks: Single Ultrasonic Sensor Scanning Approach
title_short Object Recognition and Positioning with Neural Networks: Single Ultrasonic Sensor Scanning Approach
title_sort object recognition and positioning with neural networks single ultrasonic sensor scanning approach
topic ultrasonic sensors
signal classification
convolutional neural networks
signal processing
object recognition
machine learning
url https://www.mdpi.com/1424-8220/25/4/1086
work_keys_str_mv AT ahmetkaragoz objectrecognitionandpositioningwithneuralnetworkssingleultrasonicsensorscanningapproach
AT gokhandindis objectrecognitionandpositioningwithneuralnetworkssingleultrasonicsensorscanningapproach