Improved Object Detection Method Utilizing YOLOv7-Tiny for Unmanned Aerial Vehicle Photographic Imagery
Open Access
- 14 November 2023
- journal article
- research article
- Published by MDPI AG in Algorithms
- Vol. 16 (11) , 520
Abstract
In unmanned aerial vehicle photographs, object detection algorithms encounter challenges in enhancing both speed and accuracy for objects of different sizes, primarily due to complex backgrounds and small objects. This study introduces the PDWT-YOLO algorithm, based on the YOLOv7-tiny model, to improve the effectiveness of object detection across all sizes. The proposed method enhances the detection of small objects by incorporating a dedicated small-object detection layer, while reducing the conflict between classification and regression tasks through the replacement of the YOLOv7-tiny model’s detection head (IDetect) with a decoupled head. Moreover, network convergence is accelerated, and regression accuracy is improved by replacing the Complete Intersection over Union (CIoU) loss function with a Wise Intersection over Union (WIoU) focusing mechanism in the loss function. To assess the proposed model’s effectiveness, it was trained and tested on the VisDrone-2019 dataset comprising images captured by various drones across diverse scenarios, weather conditions, and lighting conditions. The experiments show that mAP@0.5:0.95 and mAP@0.5 increased by 5% and 6.7%, respectively, with acceptable running speed compared with the original YOLOv7-tiny model. Furthermore, this method shows improvement over other datasets, confirming that PDWT-YOLO is effective for multiscale object detection.Keywords
Funding Information
- Shanxi Provincial Science and Technology Department (201903D121171, 61976134)
- National Natural Science Foundation of China (201903D121171, 61976134)
This publication has 35 references indexed in Scilit:
- A novel spatio-temporal saliency approach for robust dim moving target detection from airborne infrared image sequencesInformation Sciences, 2016
- SSD: Single Shot MultiBox Detector2016
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal NetworksIEEE Transactions on Pattern Analysis and Machine Intelligence, 2016
- Deep Residual Learning for Image Recognition2016
- You Only Look Once: Unified, Real-Time Object Detection2016
- Deep Convolutional Neural Networks for Computer-Aided Detection: CNN Architectures, Dataset Characteristics and Transfer LearningIEEE Transactions on Medical Imaging, 2016
- Fast R-CNN2015
- Going deeper with convolutions2015
- Spatial Pyramid Pooling in Deep Convolutional Networks for Visual RecognitionIEEE Transactions on Pattern Analysis and Machine Intelligence, 2015
- Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation2014