Machine vision-based testing action recognition method for robotic testing of mobile application

The explosive growth and rapid version iteration of various mobile applications have brought enormous workloads to mobile application testing. Robotic testing methods can efficiently handle repetitive testing tasks, which can compensate for the accuracy of manual testing and improve the efficiency o...

Full description

Saved in:
Bibliographic Details
Main Authors: Tao Zhang, Zhengqi Su, Jing Cheng, Feng Xue, Shengyu Liu
Format: Article
Language:English
Published: Wiley 2022-08-01
Series:International Journal of Distributed Sensor Networks
Online Access:https://doi.org/10.1177/15501329221115375
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849435249025482752
author Tao Zhang
Zhengqi Su
Jing Cheng
Feng Xue
Shengyu Liu
author_facet Tao Zhang
Zhengqi Su
Jing Cheng
Feng Xue
Shengyu Liu
author_sort Tao Zhang
collection DOAJ
description The explosive growth and rapid version iteration of various mobile applications have brought enormous workloads to mobile application testing. Robotic testing methods can efficiently handle repetitive testing tasks, which can compensate for the accuracy of manual testing and improve the efficiency of testing work. Vision-based robotic testing identifies the types of test actions by analyzing expert test videos and generates expert imitation test cases. The mobile application expert imitation testing method uses machine learning algorithms to analyze the behavior of experts imitating test videos, generates test cases with high reliability and reusability, and drives robots to execute test cases. However, the difficulty of estimating multi-dimensional gestures in 2D images leads to complex algorithm steps, including tracking, detection, and recognition of dynamic gestures. Hence, this article focuses on the analysis and recognition of test actions in mobile application robot testing. Combined with the improved YOLOv5 algorithm and the ResNet-152 algorithm, a visual modeling method of mobile application test action based on machine vision is proposed. The precise localization of the hand is accomplished by injecting dynamic anchors, attention mechanism, and the weighted boxes fusion in the YOLOv5 algorithm. The improved algorithm recognition accuracy increased from 82.6% to 94.8%. By introducing the pyramid context awareness mechanism into the ResNet-152 algorithm, the accuracy of test action classification is improved. The accuracy of the test action classification was improved from 72.57% to 76.84%. Experiments show that this method can reduce the probability of multiple detections and missed detection of test actions, and improve the accuracy of test action recognition.
format Article
id doaj-art-4f121aeb71f042adbdc07c806978670b
institution Kabale University
issn 1550-1477
language English
publishDate 2022-08-01
publisher Wiley
record_format Article
series International Journal of Distributed Sensor Networks
spelling doaj-art-4f121aeb71f042adbdc07c806978670b2025-08-20T03:26:21ZengWileyInternational Journal of Distributed Sensor Networks1550-14772022-08-011810.1177/15501329221115375Machine vision-based testing action recognition method for robotic testing of mobile applicationTao Zhang0Zhengqi Su1Jing Cheng2Feng Xue3Shengyu Liu4School of Software, Northwestern Polytechnical University, Xi’an, ChinaSchool of Software, Northwestern Polytechnical University, Xi’an, ChinaSchool of Computer Science and Engineering, Xi’an Technological University, Xi’an, ChinaSchool of Software, Northwestern Polytechnical University, Xi’an, ChinaSchool of Software, Northwestern Polytechnical University, Xi’an, ChinaThe explosive growth and rapid version iteration of various mobile applications have brought enormous workloads to mobile application testing. Robotic testing methods can efficiently handle repetitive testing tasks, which can compensate for the accuracy of manual testing and improve the efficiency of testing work. Vision-based robotic testing identifies the types of test actions by analyzing expert test videos and generates expert imitation test cases. The mobile application expert imitation testing method uses machine learning algorithms to analyze the behavior of experts imitating test videos, generates test cases with high reliability and reusability, and drives robots to execute test cases. However, the difficulty of estimating multi-dimensional gestures in 2D images leads to complex algorithm steps, including tracking, detection, and recognition of dynamic gestures. Hence, this article focuses on the analysis and recognition of test actions in mobile application robot testing. Combined with the improved YOLOv5 algorithm and the ResNet-152 algorithm, a visual modeling method of mobile application test action based on machine vision is proposed. The precise localization of the hand is accomplished by injecting dynamic anchors, attention mechanism, and the weighted boxes fusion in the YOLOv5 algorithm. The improved algorithm recognition accuracy increased from 82.6% to 94.8%. By introducing the pyramid context awareness mechanism into the ResNet-152 algorithm, the accuracy of test action classification is improved. The accuracy of the test action classification was improved from 72.57% to 76.84%. Experiments show that this method can reduce the probability of multiple detections and missed detection of test actions, and improve the accuracy of test action recognition.https://doi.org/10.1177/15501329221115375
spellingShingle Tao Zhang
Zhengqi Su
Jing Cheng
Feng Xue
Shengyu Liu
Machine vision-based testing action recognition method for robotic testing of mobile application
International Journal of Distributed Sensor Networks
title Machine vision-based testing action recognition method for robotic testing of mobile application
title_full Machine vision-based testing action recognition method for robotic testing of mobile application
title_fullStr Machine vision-based testing action recognition method for robotic testing of mobile application
title_full_unstemmed Machine vision-based testing action recognition method for robotic testing of mobile application
title_short Machine vision-based testing action recognition method for robotic testing of mobile application
title_sort machine vision based testing action recognition method for robotic testing of mobile application
url https://doi.org/10.1177/15501329221115375
work_keys_str_mv AT taozhang machinevisionbasedtestingactionrecognitionmethodforrobotictestingofmobileapplication
AT zhengqisu machinevisionbasedtestingactionrecognitionmethodforrobotictestingofmobileapplication
AT jingcheng machinevisionbasedtestingactionrecognitionmethodforrobotictestingofmobileapplication
AT fengxue machinevisionbasedtestingactionrecognitionmethodforrobotictestingofmobileapplication
AT shengyuliu machinevisionbasedtestingactionrecognitionmethodforrobotictestingofmobileapplication