Abstract
In order to solve the problems of poor detection algorithms, high network model complexity, and difficult deployment of algorithms in the field of aerial image target detection. In this paper, based on YOLOv7-tiny algorithm, a lightweight target detection network for UAV aerial images is designed. Partial convolutional PConv is introduced into the network, and the feature extraction block ELAN is improved, which reduces the computational volume of convolution and the number of model parameters in the feature extraction process, thus solving the problem of model lightweight. The feature fusion part of the network is optimal to improve the feature extraction ability of the network for small targets. At the same time, the large target detection layer in the original network is replaced with the small target detection layer in the aerial images, and the attention mechanism is embedded in the backbone network, which solves the problem of imperfect detection algorithms in aerial images. The loss function of the network is improved so that the prediction frames generated by the detection network and the truth frames match each other in the regression process, thus improving the training process of the network. The experimental results on the publicly available dataset VisDrone2019 dataset show that compared with the YOLOv7-tiny algorithm, the detection accuracy of the proposed model is improved by 0.7%, the recall R is improved by 2.2%, the F1 value is improved by 1.6%, the average detection accuracy mean is improved by 2.3%, and the number of parameters is reduced by 52.1%. Moreover, the image detection speed FPS reaches 66/f.s-1, which meets the real-time requirements of the aerial image detection model detection, and provides a research idea for the field of UAV aerial image detection.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.