Slika omota

Simultaneous Object Detection and Distance Estimation for Indoor Autonomous Vehicles

Spremljeno u:
Izdano u:Electronics vol. 12, no. 23 (2023), p. 4719
Glavni autor: Azurmendi, Iker
Daljnji autori: Zulueta, Ekaitz, Lopez-Guede, Jose Manuel, González, Manuel
Izdano:
MDPI AG
Teme:
Data augmentation
Datasets
Cameras
Labels
Deep learning
Autonomous vehicles
Sensors
Neural networks
Robots
Unmanned aerial vehicles
Algorithms
Telematics
Automation
Surveillance
Object recognition
Obstacle avoidance
Robotics
Online pristup:Citation/Abstract
Full Text + Graphics
Full Text - PDF
Oznake: Dodaj oznaku
Bez oznaka, Budi prvi tko označuje ovaj zapis!
Sažetak:Object detection is an essential and impactful technology in various fields due to its ability to automatically locate and identify objects in images or videos. In addition, object-distance estimation is a fundamental problem in 3D vision and scene perception. In this paper, we propose a simultaneous object-detection and distance-estimation algorithm based on YOLOv5 for obstacle detection in indoor autonomous vehicles. This method estimates the distances to the desired obstacles using a single monocular camera that does not require calibration. On the one hand, we train the algorithm with the KITTI dataset, which is an autonomous driving vision dataset that provides labels for object detection and distance prediction. On the other hand, we collect and label 100 images from a custom environment. Then, we apply data augmentation and transfer learning to generate a fast, accurate, and cost-effective model for the custom environment. The results show a performance of mAP0.5:0.95 of more than 75% for object detection and 0.71 m of mean absolute error in distance prediction, which are easily scalable with the labeling of a larger amount of data. Finally, we compare our method with other similar state-of-the-art approaches.
ISSN:2079-9292
Digitalni identifikator objekta:10.3390/electronics12234719
Izvor:Advanced Technologies & Aerospace Index