An appropriate detection network is required to extract building information in remote sensing images and to relieve the issue of poor detection effects resulting from the deficiency of detailed features. Firstly, we embed a transposed convolution sampling module fusing multiple normalization activation layers in the decoder based on the SegFormer network. This step alleviates the issue of missing feature semantics by adding holes and fillings, cascading multiple normalizations and activation layers to hold back over-fitting regularization expression and guarantee steady feature parameter classification. Secondly, the atrous spatial pyramid pooling decoding module is fused to explore multi-scale contextual information and to overcome issues such as the loss of detailed information on local buildings and the lack of long-distance information. Ablation experiments and comparison experiments are performed on the remote sensing image AISD, MBD, and WHU dataset. The robustness and validity of the improved mechanism are demonstrated by control groups of ablation experiments. In comparative experiments with the HRnet, PSPNet, U-Net, DeepLabv3+ networks, and the original detection algorithm, the mIoU of the AISD, the MBD, and the WHU dataset is enhanced by 17.68%, 30.44%, and 15.26%, respectively. The results of the experiments show that the method of this paper is superior to comparative methods such as U-Net. Furthermore, it is better for integrity detection of building edges and reduces the number of missing and false detections.
Water body extraction is a significant direction of application in information monitoring of water resources. Thus, on the basis of high-resolution UAV remote sensing images and self-build inland water body datasets, this paper designs a water body extraction method fused atrous spatial pyramid pooling. First, SegFormer detection network is improved, and the semantic segmentation network is adopted to mine water body semantic information of high-resolution UAV remote sensing images; second, the atrous spatial pyramid pooling decoding module is fused to explore multi-scale contextual information, solve the problems such as feature information loss of water body and deficiency of long-distance information, and come true the coverage of more geometric information whilst responding to semantic features; finally, the semantic segmentation dataset of the inland water body is self-established on the basis of the UAV remote sensing images in Dengzhou, Henan, and the experiment is conducted. Then the validity of the proposed water body extraction method is validated via the comparative ablation experiment with Hrnet, PSPNet, UNet, Deeplabv3+ and the original detection algorithm. According to experimental results, the improved method is superior to the comparative detection methods such as UNet, and has a better effect on the integrity detection of water body edges and the reduction of missing detection and false detection of small water bodies and tributaries.
On the basis of establishing direct geo-positioning model for three-line array sensor ADS40/80 images, in order to optimize the positioning accuracy, the self-calibration technology was used to update the ADS40/80 sensor imaging parameters. Moreover, the ADS40/80 camera error model and self-calibration bundle adjustment model were set up. Multi-groups of ADS40 data over the Songshan experimental field were used for direct geo-positioning and parameter updating experiments. Experimental results proved that the self-calibration adjustment technique can effectively update sensor imaging parameters and significantly improve image direct positioning accuracy.
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.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.