A Self-Learning Mechanism-Based Approach to Helicopter Entry and Departure Recognition
In order to accurately record the entry and departure times of helicopters and reduce the incidence of general aviation accidents, this paper proposes a helicopter entry and departure recognition method based on a self-learning mechanism, which is supplemented by a lightweight object detection modul...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2022-10-01
|
Series: | Sensors |
Subjects: | |
Online Access: | https://www.mdpi.com/1424-8220/22/20/7852 |
_version_ | 1797470032600498176 |
---|---|
author | Zonglei Lyu Xuepeng Chang Wei An Tong Yu |
author_facet | Zonglei Lyu Xuepeng Chang Wei An Tong Yu |
author_sort | Zonglei Lyu |
collection | DOAJ |
description | In order to accurately record the entry and departure times of helicopters and reduce the incidence of general aviation accidents, this paper proposes a helicopter entry and departure recognition method based on a self-learning mechanism, which is supplemented by a lightweight object detection module and an image classification module. The original image data obtained from the lightweight object detection module are used to construct an Automatic Selector of Data (Auto-SD) and an Adjustment Evaluator of Data Bias (Ad-EDB), whereby Auto-SD automatically generates a pseudo-clustering of the original image data. Ad-EDB then performs the adjustment evaluation and selects the best matching module for image classification. The self-learning mechanism constructed in this paper is applied to the helicopter entry and departure recognition scenario, and the ResNet18 residual network is selected for state classification. As regards the self-built helicopter entry and departure data set, the accuracy reaches 97.83%, which is 6.51% better than the bounding box detection method. To a certain extent, the strong reliance on manual annotation for helicopter entry and departure status classification scenarios is lifted, and the data auto-selector is continuously optimized using the preorder classification results to establish a circular learning loop in the algorithm. |
first_indexed | 2024-03-09T19:31:02Z |
format | Article |
id | doaj.art-bf611f55544a4096a52fab3568d6c7fb |
institution | Directory Open Access Journal |
issn | 1424-8220 |
language | English |
last_indexed | 2024-03-09T19:31:02Z |
publishDate | 2022-10-01 |
publisher | MDPI AG |
record_format | Article |
series | Sensors |
spelling | doaj.art-bf611f55544a4096a52fab3568d6c7fb2023-11-24T02:27:16ZengMDPI AGSensors1424-82202022-10-012220785210.3390/s22207852A Self-Learning Mechanism-Based Approach to Helicopter Entry and Departure RecognitionZonglei Lyu0Xuepeng Chang1Wei An2Tong Yu3College of Computer Science and Technology, Civil Aviation University of China, Tianjin 300300, ChinaCollege of Computer Science and Technology, Civil Aviation University of China, Tianjin 300300, ChinaCollege of Computer Science and Technology, Civil Aviation University of China, Tianjin 300300, ChinaCollege of Computer Science and Technology, Civil Aviation University of China, Tianjin 300300, ChinaIn order to accurately record the entry and departure times of helicopters and reduce the incidence of general aviation accidents, this paper proposes a helicopter entry and departure recognition method based on a self-learning mechanism, which is supplemented by a lightweight object detection module and an image classification module. The original image data obtained from the lightweight object detection module are used to construct an Automatic Selector of Data (Auto-SD) and an Adjustment Evaluator of Data Bias (Ad-EDB), whereby Auto-SD automatically generates a pseudo-clustering of the original image data. Ad-EDB then performs the adjustment evaluation and selects the best matching module for image classification. The self-learning mechanism constructed in this paper is applied to the helicopter entry and departure recognition scenario, and the ResNet18 residual network is selected for state classification. As regards the self-built helicopter entry and departure data set, the accuracy reaches 97.83%, which is 6.51% better than the bounding box detection method. To a certain extent, the strong reliance on manual annotation for helicopter entry and departure status classification scenarios is lifted, and the data auto-selector is continuously optimized using the preorder classification results to establish a circular learning loop in the algorithm.https://www.mdpi.com/1424-8220/22/20/7852self-learning mechanismautomatic data selectionpseudo clusteringimage classification |
spellingShingle | Zonglei Lyu Xuepeng Chang Wei An Tong Yu A Self-Learning Mechanism-Based Approach to Helicopter Entry and Departure Recognition Sensors self-learning mechanism automatic data selection pseudo clustering image classification |
title | A Self-Learning Mechanism-Based Approach to Helicopter Entry and Departure Recognition |
title_full | A Self-Learning Mechanism-Based Approach to Helicopter Entry and Departure Recognition |
title_fullStr | A Self-Learning Mechanism-Based Approach to Helicopter Entry and Departure Recognition |
title_full_unstemmed | A Self-Learning Mechanism-Based Approach to Helicopter Entry and Departure Recognition |
title_short | A Self-Learning Mechanism-Based Approach to Helicopter Entry and Departure Recognition |
title_sort | self learning mechanism based approach to helicopter entry and departure recognition |
topic | self-learning mechanism automatic data selection pseudo clustering image classification |
url | https://www.mdpi.com/1424-8220/22/20/7852 |
work_keys_str_mv | AT zongleilyu aselflearningmechanismbasedapproachtohelicopterentryanddeparturerecognition AT xuepengchang aselflearningmechanismbasedapproachtohelicopterentryanddeparturerecognition AT weian aselflearningmechanismbasedapproachtohelicopterentryanddeparturerecognition AT tongyu aselflearningmechanismbasedapproachtohelicopterentryanddeparturerecognition AT zongleilyu selflearningmechanismbasedapproachtohelicopterentryanddeparturerecognition AT xuepengchang selflearningmechanismbasedapproachtohelicopterentryanddeparturerecognition AT weian selflearningmechanismbasedapproachtohelicopterentryanddeparturerecognition AT tongyu selflearningmechanismbasedapproachtohelicopterentryanddeparturerecognition |