Lin Yuting, Zhang Jianxun, Huang Jiaming
Department of Computer Science and Engineering, Chongqing University of Technology, Chongqing, 400054, China.
Institute of Artificial Intelligence, Chongqing Business Vocational College, Chongqing, 401331, China.
Sci Rep. 2024 Jul 24;14(1):17021. doi: 10.1038/s41598-024-67451-6.
Target detection in satellite images is an essential topic in the field of remote sensing and computer vision. Despite extensive research efforts, accurate and efficient target detection in remote sensing images remains unsolved due to the large target scale span, dense distribution, and overhead imaging and complex backgrounds, which result in high target feature similarity and serious occlusion. In order to address the above issues in a comprehensive manner, within this paper, we first propose a Centralised Visual Processing Center (CVPC), this structure is a parallel visual processing center for Transformer encoder and CNN, employing a lightweight encoder to capture broad, long-range interdependencies. Pixel-level Learning Center (PLC) module is used to establish pixel-level correlations and improve the depiction of detailed features. CVPC effectively improves the detection efficiency of remote sensing targets with high feature similarity and severe occlusion. Secondly, we propose a centralised feature cross-layer fusion pyramid structure to fuse the results with the CVPC in a top-down manner to enhance the detailed feature representation capability at each layer. Ultimately, we present a Context Enhanced Adaptive Sparse Convolutional Network (CEASC), which improves the accuracy while ensuring the detection efficiency. Based on the above modules, we designed and conducted a series of experiments. These experiments are conducted on three challenging public datasets, DOTA-v1.0, DIOR, and RSDO, showing that our proposed 3CNet achieves a more advanced detection accuracy while balancing the detection speed (78.62% mAP for DOTA-v1.0, 79.12% mAP for DIOR, and 95.50% mAP for RSOD).
卫星图像中的目标检测是遥感和计算机视觉领域的一个重要课题。尽管进行了广泛的研究，但由于目标尺度跨度大、分布密集、俯视成像以及背景复杂，导致目标特征相似度高且遮挡严重，遥感图像中准确高效的目标检测问题仍未得到解决。为了全面解决上述问题，在本文中，我们首先提出了一种集中式视觉处理中心（CVPC），该结构是一种用于Transformer编码器和卷积神经网络（CNN）的并行视觉处理中心，采用轻量级编码器来捕获广泛的长距离依赖性。像素级学习中心（PLC）模块用于建立像素级相关性并改善详细特征的描述。CVPC有效地提高了具有高特征相似度和严重遮挡的遥感目标的检测效率。其次，我们提出了一种集中式特征跨层融合金字塔结构，以自上而下的方式将结果与CVPC融合，以增强各层的详细特征表示能力。最终，我们提出了一种上下文增强自适应稀疏卷积网络（CEASC），它在确保检测效率的同时提高了准确性。基于上述模块，我们设计并进行了一系列实验。这些实验在三个具有挑战性的公共数据集DOTA-v1.0、DIOR和RSDO上进行，结果表明我们提出的3CNet在平衡检测速度的同时实现了更先进的检测精度（DOTA-v1.0的平均精度均值为78.62%，DIOR为79.12%，RSOD为95.50%）。
