QYOLO: Contextual Query-Assisted Object Detection in High-Resolution Images
Open Access
- 12 September 2024
- journal article
- research article
- Published by MDPI AG in Information
- Vol. 15 (9) , 563
Abstract
High-resolution imagery captured by drones can detect critical components on high-voltage transmission towers, providing inspection personnel with essential maintenance insights and improving the efficiency of power line inspections. The high-resolution imagery is particularly effective in enhancing the detection of fine details such as screws. The QYOLO algorithm, an enhancement of YOLOv8, incorporates context queries into the feature pyramid, effectively capturing long-range dependencies and improving the network’s ability to detect objects. To address the increased network depth and computational load introduced by query extraction, Ghost Separable Convolution (GSConv) is employed, reducing the computational expense by half and further improving the detection performance for small objects such as screws. The experimental validation using the Transmission Line Accessories Dataset (TLAD) developed for this project demonstrates that the proposed improvements increase the average precision (AP) for small objects by 5.5% and the F1-score by 3.5%. The method also enhances detection performance for overall targets, confirming its efficacy in practical applications.Keywords
Funding Information
- Shanghai Science and Technology Innovation Action Plan 2022 (22511100600, PKJ2023-C02)
- Shanghai Pudong New Area Science and Technology Development Fund for People’s Livelihood Research (22511100600, PKJ2023-C02)
This publication has 35 references indexed in Scilit:
- Accurate road user localization in aerial images captured by unmanned aerial vehiclesAutomation in Construction, 2023
- CPA-YOLOv7: Contextual and pyramid attention-based improvement of YOLOv7 for drones scene target detectionJournal of Visual Communication and Image Representation, 2023
- UAV small target detection algorithm based on an improved YOLOv5s modelJournal of Visual Communication and Image Representation, 2023
- A performance comparison of YOLOv8 models for traffic sign detection in the Robotaxi-full scale autonomous vehicle competitionMultimedia Tools and Applications, 2023
- Object Detection in 20 Years: A SurveyProceedings of the IEEE, 2023
- FINet: An Insulator Dataset and Detection Benchmark Based on Synthetic Fog and Improved YOLOv5IEEE Transactions on Instrumentation and Measurement, 2022
- Attention mechanisms in computer vision: A surveyComputational Visual Media, 2022
- Faster R-Transformer: An efficient method for insulator detection in complex aerial environmentsMeasurement, 2022
- EAPT: Efficient Attention Pyramid Transformer for Image ProcessingIEEE Transactions on Multimedia, 2021
- BiFNet: Bidirectional Fusion Network for Road SegmentationIEEE Transactions on Cybernetics, 2021