2023年10月19日，Elsevier 旗下国际著名期刊《ISPRS摄影测量和遥感杂志》(ISPRS Journal of Photogrammetry and Remote Sensing)在线发表了云南师范大学信息学院杨扬教授最新研究成果《Scene-aware refinement network for unsupervised monocular depth estimation in ultra-low altitude oblique photography of UAV》。

https://doi.org/10.1016/j.isprsjprs.2023.10.010

Abstract

Using depth estimation joint target detection networks to locate targets in the UAV field of view is a novel application in the depth estimation research field. The presence of more depth variations and low-texture regions in the ultra-low altitude oblique photographic images make them trickier to train for an excellent depth estimation network compared to autonomous driving scenarios. This presents a challenge in achieving optimal training. This study investigates the problem of unsupervised monocular depth estimation for ultra-low altitude oblique photography images. It aims to make subsequent advanced vision tasks better benefit from excellent depth estimation results in terms of overcoming complex scenes. The lack of effective back-projection directionality in training using adjacent frames is attributed to the extensive low-textured areas contained in the training data for complex ultra-low altitude oblique photography. We propose a self-supervised scene-aware refinement learning architecture from the perspective of enhancing feature perception to deal with such problems. The architecture consists of a multi-resolution feature fusion depth network and a perceptual refinement network (PRNet), together with a pose network to enhance regional differences in complex environments from a refined feature context perspective to obtain higher quality depth maps. We rethink the problem of depth information recovery and design the edge information aggregation (EIA) module, which is configured in the decoder section to refine the local region depth detail representation. We design several loss terms to constrain the training of the network in order to improve the quality of depth estimation. Our method is compared with six state-of-the-art self-supervised monocular depth estimation methods on three datasets (UAVid 2020, WildUAV, UAV ula). The experimental results demonstrate that our model achieves the best performance in most scenarios. The code and the private dataset (UAV ula) can be publicly available at https://github.com/takisu0916/MRFEDepth.

扩展阅读：

云师大杨扬教授2023年在国际权威期刊《Information Fusion》上再次发表图像处理最新研究成果

https://blog.sciencenet.cn/blog-454141-1389009.html

云师大杨扬教授在国际权威期刊《Information Fusion》发表最新研究成果

https://blog.sciencenet.cn/blog-454141-1378515.html

云南师范大学青年研究者之——杨扬

https://blog.sciencenet.cn/blog-454141-1195875.html

国际摄影测量与遥感学会（International Society for Photogrammetry and Remote Sensing）是一个以推动摄影测量、遥感与空间信息科学领域国际合作交流为宗旨的非政府和非营利性科学组织。,《ISPRS摄影测量和遥感杂志》（ISPRS Journal of Photogrammetry and Remote Sensing）(影响因子：12.7）)：是学会在摄影测量和遥感方向的官方出版物，论文同行评审，每年出版12期，刊登科学、技术及综述论文。成立于1910年，是该领域历史最为悠久的国际专业组织。目前有92个国家会员、13个准会员、14个地区会员和62个赞助会员。