Abstract: Remote sensing-based object detection faces chal-lenges in arbitrary orientations, complex backgrounds, dense distributions, and large aspect ratios. Considering these issues, this paper introduces a novel method called D2-Net, which incorporates a transformer structure into a convolutional neural network. First, a new feature extraction module called dilated contextual transformer block is designed to minimize the loss of object information due to complex backgrounds and dense tar-gets. In addition, an efficient approach using depth-wise separable deconvolution as an up-sampling method is developed to recover lost feature information effectively. Finally, the circular smooth label is incorporated to compute the angular loss to complete the rotated detection of remote sensing images. Experimental evaluations are conducted on the DOTA and HRSC2016 datasets. On the DOTA dataset, the proposed method achieves 79.2%and 78.00% accuracy in horizontal and rotated object detection, respectively; it achieves 94.00% accuracy in the rotated detection of the HRSC2016 dataset. The proposed model shows a significant performance improvement over other comparative models on the dataset, which verifies the effectiveness of our proposed approach.

Huaping Zhou, Qi Zhao and Kelei Sun, “D2-Net: Dilated Contextual Transformer and Depth-wise Separable Deconvolution for Remote Sensing Imagery Detection” International Journal of Advanced Computer Science and Applications(IJACSA), 14(11), 2023. http://dx.doi.org/10.14569/IJACSA.2023.01411134

@article{Zhou2023,
title = {D2-Net: Dilated Contextual Transformer and Depth-wise Separable Deconvolution for Remote Sensing Imagery Detection},
journal = {International Journal of Advanced Computer Science and Applications},
doi = {10.14569/IJACSA.2023.01411134},
url = {http://dx.doi.org/10.14569/IJACSA.2023.01411134},
year = {2023},
publisher = {The Science and Information Organization},
volume = {14},
number = {11},
author = {Huaping Zhou and Qi Zhao and Kelei Sun}
}