Remote sensing for image object detection has numerous important applications. However, complex backgrounds and large object-scale differences pose considerable challenges in the detection task. To overcome these issues, we proposed a one-stage remote sensing image object detection model: a multi-feature information complementary detector (MFICDet). This detector contains a positive and negative feature guidance module (PNFG) and a global feature information complementary module (GFIC). Specifically, the PNFG is used to refine features that are beneficial for object detection and explore the noisy features in a complex background of abstract features. The proportion of beneficial features in the feature information stream is increased by suppressing noisy features. The GFIC uses pooling to compress the deep abstract features and improve the model’s ability to resist feature displacement and rotation. The pooling operation has the disadvantage of losing detailed feature information; thus, dilated convolution is introduced for feature complementation. Dilated convolution increases the receptive field of the model while maintaining an unchanged spatial resolution. This can improve the ability of the model to recognize long-distance dependent information and establish spatial location relationships between features. The detector proposed also improves the detection performance of objects at different scales in the same image using a dual multi-scale feature fusion strategy. Finally, classification and regression tasks are decoupled in space using a decoupled head. We experimented on the DIOR and NWPU VHR-10 datasets to demonstrate that the newly proposed MFICDet achieves competitive performance compared to current state-of-the-art detectors.
Object detection is used widely in remote sensing image interpretation. Although most models used for object detection have achieved high detection accuracy, computational complexity and low detection speeds limit their application in real-time detection tasks. This study developed an adaptive feature-aware method of object detection in remote sensing images based on the single-shot detector architecture called adaptive feature-aware detector (AFADet). Self-attention is used to extract high-level semantic information derived from deep feature maps for spatial localization of objects and the model is improved in localizing objects. The adaptive feature-aware module is used to perform adaptive cross-scale depth fusion of different-scale feature maps to improve the learning ability of the model and reduce the influence of complex backgrounds in remote sensing images. The focal loss is used during training to address the positive and negative sample imbalance problem, reduce the influence of the loss value dominated by easily classified samples, and enhance the stability of model training. Experiments are conducted on three object detection datasets, and the results are compared with those of the classical and recent object detection algorithms. The mean average precision(mAP) values are 66.12%, 95.54%, and 86.44% for three datasets, which suggests that AFADet can detect remote sensing images in real-time with high accuracy and can effectively balance detection accuracy and speed.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
customersupport@researchsolutions.com
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.