Cross-Dimensional Object-Level Matching Method for Buildings in Airborne Optical Image and LiDAR Point Cloud

Yan, Yiming; Wang, Wenxuan; Su, Nan; Wang, Zilu

doi:10.1109/lgrs.2022.3144474

Cited by 1 publication

(3 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Similar to the SDD, [36] the Spatial Occupancy Probability Feature (SOPF) is used to describe the three-dimensional structure of the building, that is, the probability of the current sampling point being inside the model. Therefore, the SOPF of the sampling points outside the model surface is set to 0, and that inside is set to 1 (100%), as shown in Figure 2c.…”

Section: Sddmentioning

confidence: 99%

“…By directly binding handcrafted 3D descriptors to learned image descriptors, cross-dimensional descriptors for object-level retrieval tasks were generated. The authors of [36] proposed a deep-learning-based cross-dimensional objectlevel descriptor space occupancy probability descriptor (SOPD) which uses the occupancy probability of each unit space of the object as the cross-dimensional descriptor.…”

Section: Introductionmentioning

confidence: 99%

“…To achieve cross-dimensional BM, a corresponding database is required. Although Yan et al [36] proposed a 2D-3D object-level building-matching data set, only its 3D point clouds were obtained from the real world. We constructed a fully real-world 2D-3D crossdimensional object-level building-matching data set called 2D-3D-CDOBM.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A Novel Object-Level Building-Matching Method across 2D Images and 3D Point Clouds Based on the Signed Distance Descriptor (SDD)

et al. 2023

View full text Add to dashboard Cite

In this work, a novel object-level building-matching method using cross-dimensional data, including 2D images and 3D point clouds, is proposed. The core of this method is a newly proposed plug-and-play Joint Descriptor Extraction Module (JDEM) that is used to extract descriptors containing buildings’ three-dimensional shape information from object-level remote sensing data of different dimensions for matching. The descriptor is named Signed Distance Descriptor (SDD). Due to differences in the inherent properties of different dimensional data, it is challenging to match buildings’ 2D images and 3D point clouds on the object level. In addition, features extracted from the same building in images taken at different angles are usually not exactly identical, which will also affect the accuracy of cross-dimensional matching. Therefore, the question of how to extract accurate, effective, and robust joint descriptors is key to cross-dimensional matching. Our JDEM maps different dimensions of data to the same 3D descriptor SDD space through the 3D geometric invariance of buildings. In addition, Multi-View Adaptive Loss (MAL), proposed in this paper, aims to improve the adaptability of the image encoder module to images with different angles and enhance the robustness of the joint descriptors. Moreover, a cross-dimensional object-level data set was created to verify the effectiveness of our method. The data set contains multi-angle optical images, point clouds, and the corresponding 3D models of more than 400 buildings. A large number of experimental results show that our object-level cross-dimensional matching method achieves state-of-the-art outcomes.

show abstract

Section: Sddmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%