Residual Spatial Reduced Transformer Based on YOLOv5 for UAV Images Object Detection
- 1 April 2024
- journal article
- research article
- Published by World Scientific Pub Co Pte Ltd in International Journal of Pattern Recognition and Artificial Intelligence
- Vol. 38 (05)
Abstract
Object detection on unmanned aerial vehicle (UAV) images is an important branch of object detection, belonging to small object detection in a broad sense. Detecting objects in UAV images poses a greater challenge due to the predominance of small objects and dense occlusion caused by UAV capturing images from varying heights and angles. To solve the above problems, we propose Residual Spatial Reduced Transformer based on YOLOv5 (RSRT-YOLOv5). Specifically, Slice Aided Enhancement Module (SAEM) is introduced to enhance the feature quality of small objects. Secondly, a Global attention-based Bi-directional Feature Fusion (GBFF) module is proposed. In the Neck architecture, an efficient Residual Spatial Reduced Transformer (RSRT) module is integrated in order to achieve more efficient feature representation and richer global contextual associations. Finally, our method is evaluated on the Visdrone2019 dataset, and the experimental results show that RSRT-YOLOv5 outperforms the baseline model (yolov5) and successfully improves the detection performance of UAV images.Keywords
Funding Information
- National Key R&D Program of China (2022ZD0119900)
- Shanghai Science and Technology Program (22015810300)
- Hainan Province Science and Technology Special Fund (ZDYF2021GXJS041)
- Scientific research fund of Hainan University (KYQD(ZR)23025)
- National Natural Science Foundation of China (U2141234)
This publication has 36 references indexed in Scilit:
- GTR-GA: Harnessing the power of graph-based neural networks and genetic algorithms for text augmentationExpert Systems with Applications, 2023
- RFLA: Gaussian Receptive Field Based Label Assignment for Tiny Object Detection2022
- Feedback-driven loss function for small object detectionImage and Vision Computing, 2021
- Sentiment analysis on product reviews based on weighted word embeddings and deep neural networksConcurrency and Computation: Practice and Experience, 2020
- Sentiment analysis on massive open online course evaluations: A text mining and deep learning approachComputer Applications in Engineering Education, 2020
- Mining opinions from instructor evaluation reviews: A deep learning approachComputer Applications in Engineering Education, 2019
- CornerNet: Detecting Objects as Paired Keypoints2018
- CBAM: Convolutional Block Attention Module2018
- A multiobjective weighted voting ensemble classifier based on differential evolution algorithm for text sentiment classificationExpert Systems with Applications, 2016
- Ensemble of keyword extraction methods and classifiers in text classificationExpert Systems with Applications, 2016