On account of the remarkable performance of convolutional neural network (CNN) features for natural image searches, utilizing it for other images collected with the anamorphic lens has become a research hotspot. This article selects the aurora images generated from a circular fisheye lens as a typical example. By considering the imaging principle and geomagnetic information, a saliency-weighted region network (SWRN) is presented and introduced into the Mask R-CNN pipeline. Our SWRN selects salient regions with important semantic information and weights them both hierarchically and spatially. Hence, regions encompassing the search target are strengthened while uninformative regions are discarded, which benefits the suppression of background interference and reduction of computational complexity. In practice, by aggregating the outputs of SWRN with post-processing, a compact CNN feature is generated to represent the aurora image. Large-scale aurora image search experiments are conducted, and the results prove that our method performs better than the state-of-the-art methods on both accuracy and efficiency.

中文翻译：

---

使用显着性加权区域网络进行 Aurora 图像搜索

由于卷积神经网络 (CNN) 特征在自然图像搜索方面的卓越性能，将其用于其他使用变形镜头收集的图像已成为研究热点。本文选取圆形鱼眼镜头生成的极光图像作为典型示例。通过考虑成像原理和地磁信息，提出了显着加权区域网络（SWRN）并将其引入到 Mask R-CNN 管道中。我们的 SWRN 选择具有重要语义信息的显着区域，并在层次和空间上对它们进行加权。因此，包括搜索目标的区域被加强，而无信息区域被丢弃，这有利于抑制背景干扰和降低计算复杂度。在实践中，通过使用后处理聚合 SWRN 的输出，生成了一个紧凑的 CNN 特征来表示极光图像。进行了大规模的极光图像搜索实验，结果证明我们的方法在准确性和效率上都优于最先进的方法。