Abstract
Remote sensing image target detection is widely used for both civil and military purposes. However, two factors need to be considered for remote sensing image target detection: real-time and accuracy for detecting targets that occupy few pixels. Considering the two above issues, the main research objective of this paper is to improve the performance of the YOLO algorithm in remote sensing image target detection. The reason is that the YOLO models can guarantee both detection speed and accuracy. More specifically, the YOLOv3 model with an auxiliary network is further improved in this paper. Our model improvement consists of four main components. Firstly, an image blocking module is used to feed fixed size images to the YOLOv3 network; secondly, to speed up the training of YOLOv3, DIoU is used, which can speed up the convergence and increase the training speed; thirdly, the Convolutional Block Attention Module (CBAM) is used to connect the auxiliary network to the backbone network, making it easier for the network to notice specific features so that some key information is not easily lost during the training of the network; and finally, the adaptive feature fusion (ASFF) method is applied to our network model with the aim of improving the detection speed by reducing the inference overhead. The experiments on the DOTA dataset were conducted to validate the effectiveness of our model on the DOTA dataset. Our model can achieve satisfactory detection performance on remote sensing images, and our model performs significantly better than the unimproved YOLOv3 model with an auxiliary network. The experimental results show that the mAP of the optimised network model is 5.36% higher than that of the original YOLOv3 model with the auxiliary network, and the detection frame rate was also increased by 3.07 FPS.
Highlights
Target detection is a hot topic in the field of computer vision
The improvement of the network structure consists of three main components: Firstly, an image blocking module is added to the network input so that the remote sensing image (RSI) fed into the network are a fixed size; secondly, replacing the SE attention mechanism in the auxiliary network [36] with Convolutional Block Attention Module (CBAM) [37] allows the network to better learn specific target features; and adaptive feature fusion is used at the rear, which serves to filter conflicting information spatially to suppress inconsistency when gradient backpropagation is used, improving the scale invariance of the features and reducing the inference overhead
The Bounding Box of YOLOv3 with the auxiliary network excludes some of the shadows from the box, but the Faster R-convolutional neural networks (CNNs) has all the shadows in the box, so the Bounding Box of YOLOv3 with the auxiliary network has better regression results
Summary
Target detection is a hot topic in the field of computer vision. With the development of target detection algorithms, remote sensing image (RSI) target detection has evolved tremendously. Remote sensing image target detection technology is widely used in practical applications, such as environmental supervision, disaster assessment, military investigations, and urban planning [1,2]. Benefits from the development of convolutional neural networks (CNNs), machine learning-based target detection algorithms have been further developed, resulting in extensive research in the field of computer vision, especially in target detection. CNN models exhibit powerful feature extraction capabilities and excellent performance that have led to their tremendous development in the field of target detection, and they are gradually being applied to RSI target detection
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: 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.
