ROAD INFRASTRUCTURE OBJECT RECOGNITION SOFTWARE PACKAGE
Authors:
1.
Kazan National Research Technical University named after A.N. Tupolev
Type:
Article
Pages:
from 61
to 65
Status:
In work
Language:
Russian
Keywords:
OBJECT RECOGNITION, MOBILE APPLICATION, OPERATING SYSTEM, NEURAL NETWORK MODEL, SMARTPHONE
Abstract (English):
The article considers the problem of recognizing road infrastructure objects using the developed mobile application. The necessity of using YOLOv8 neural network models to solve this problem is substantiated. When implementing the mobile application, the Kotlin programming language and the Android Studio 2024.2.1 development environment were chosen. The Driver Assistant mobile application was developed on a laptop with an Intel Pentium CPU 3825U processor with a frequency of 1.9 GHz, 8 GB RAM, running the 64-bit Windows 10 Pro operating system. The main components of the mobile application are the camera module, the model selection module, and the experimental research module. The camera module includes permission to take photos or videos. The model selection module includes trained YOLOv8 neural network models (YOLOv8n, YOLOv8l, YOLOv8m, YOLOv8s, YOLOv8x). The experimental research module includes real-time object recognition and obtaining the result of its probability assessment. The main window of the mobile application includes the following tabs: «select YOLOv8 model modification», «processing time» (contains the object recognition time in milliseconds); «confidence threshold» (a value from 0 to 1 is set for the model's confidence that an object of a certain class is present in a given area of the image or video frame); «IoU (Jaccard coefficient)» (a value from 0 to 1 is set for the overlap between the predicted rectangle and the true frame). Examples of the mobile application functioning in real time are given. In the future, it is advisable to improve the «Driver Assistant» mobile application, as well as implement and use it in practice in companies producing land vehicles (cars and trucks), as well as public transport (buses, trolleybuses).
The article considers the problem of recognizing road infrastructure objects using the developed mobile application. The necessity of using YOLOv8 neural network models to solve this problem is substantiated. When implementing the mobile application, the Kotlin programming language and the Android Studio 2024.2.1 development environment were chosen. The Driver Assistant mobile application was developed on a laptop with an Intel Pentium CPU 3825U processor with a frequency of 1.9 GHz, 8 GB RAM, running the 64-bit Windows 10 Pro operating system. The main components of the mobile application are the camera module, the model selection module, and the experimental research module. The camera module includes permission to take photos or videos. The model selection module includes trained YOLOv8 neural network models (YOLOv8n, YOLOv8l, YOLOv8m, YOLOv8s, YOLOv8x). The experimental research module includes real-time object recognition and obtaining the result of its probability assessment. The main window of the mobile application includes the following tabs: «select YOLOv8 model modification», «processing time» (contains the object recognition time in milliseconds); «confidence threshold» (a value from 0 to 1 is set for the model's confidence that an object of a certain class is present in a given area of the image or video frame); «IoU (Jaccard coefficient)» (a value from 0 to 1 is set for the overlap between the predicted rectangle and the true frame). Examples of the mobile application functioning in real time are given. In the future, it is advisable to improve the «Driver Assistant» mobile application, as well as implement and use it in practice in companies producing land vehicles (cars and trucks), as well as public transport (buses, trolleybuses).
Keywords:
OBJECT RECOGNITION, MOBILE APPLICATION, OPERATING SYSTEM, NEURAL NETWORK MODEL, SMARTPHONE
OBJECT RECOGNITION, MOBILE APPLICATION, OPERATING SYSTEM, NEURAL NETWORK MODEL, SMARTPHONE
