arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2008.00878cs.CV
收藏

基于深度与非深度融合的卫星图像快速超分辨率

Fusion of Deep and Non-Deep Methods for Fast Super-Resolution of Satellite Images

Indian Institute of Science(印度科学理工学院)

Gaurav Kumar Nayak, Saksham Jain, R Venkatesh Babu, Anirban Chakraborty

摘要:

在新兴的商业空间工业中,获得低成本卫星图像的机会急剧增加。卫星图像的价格取决于传感器质量和重访率。这项工作提出了通过超分辨率(SR)提高图像质量来弥合图像质量和价格之间的差距。最近,已经提出了一些深SR技术来增强卫星图像。然而,这些方法都没有利用区域级上下文信息,对图像中的每个区域给予同等的重要性。这一点,以及大多数最先进的SR方法是复杂和繁琐的深度模型的事实,处理非常大的卫星图像所花费的时间可能是不切实际的高。我们建议通过设计一个SR框架来应对这一挑战,该框架分析低分辨率图像的每个补丁上的区域信息内容,并明智地选择使用计算更复杂的深度模型来超分辨率图像上结构更丰富的区域,同时在非显着区域上使用资源密集度更低的非深度方法。通过对大型卫星图像进行广泛的实验,我们显示推理时间大幅减少,同时在PSNR、MSE和SSIM等几个评估指标上实现了与现有深度SR方法相似的性能。

英文摘要:

In the emerging commercial space industry there is a drastic increase in access to low cost satellite imagery. The price for satellite images depends on the sensor quality and revisit rate. This work proposes to bridge the gap between image quality and the price by improving the image quality via super-resolution (SR). Recently, a number of deep SR techniques have been proposed to enhance satellite images. However, none of these methods utilize the region-level context information, giving equal importance to each region in the image. This, along with the fact that most state-of-the-art SR methods are complex and cumbersome deep models, the time taken to process very large satellite images can be impractically high. We, propose to handle this challenge by designing an SR framework that analyzes the regional information content on each patch of the low-resolution image and judiciously chooses to use more computationally complex deep models to super-resolve more structure-rich regions on the image, while using less resource-intensive non-deep methods on non-salient regions. Through extensive experiments on a large satellite image, we show substantial decrease in inference time while achieving similar performance to that of existing deep SR methods over several evaluation measures like PSNR, MSE and SSIM.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑