Husheng Dong

Husheng Dong

Auto-generated profile, based on publicly available information

Husheng Dong


Research Focus & Metrics

Academic Career Length

1Year (2026-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
18 September 2026 in SSRN Electronic Journal
Verified
Preprint
Open access
HCHui Chen
Hui Chen
XCXuanlin Chen
Xuanlin Chen
SLShengxi Li
Shengxi Li
HDHusheng Dong
Husheng Dong
Chongbo ZhouChongbo Zhou
Chongbo Zhou
NYNing Yang
Ning Yang
Conventional 2D visual inspection suffers from inherent depth ambiguity, while mainstream UAV-borne RTK solutions are prone to signal lock loss under complex occlusion or strong interference, and incur prohibitive deployment costs. To address these challenges, this paper proposes SGA-Loc, a cross-modal framework that precisely maps 2D defect detections onto 3D PV spatial coordinates. The framework synergistically integrates two complementary modalities: highresolution 2D imagery—rich in semantic defect features and thermal cues—and PV point clouds that provide metric scale and explicit geometric structure. This hybrid design overcomes the depth limitation of 2D vision while compensating for the paucity of surface-defect semantics in point clouds, all at reduced hardware overhead. Speciffcally, we extract robust 3D physical corners from noise-contaminated point clouds via an iterative reweighted least squares (IRLS) method coupled with a convex-hull-guided sequential RANSAC strategy. Defect points are then projected from 2D image space to 3D physical space using normalized direct linear transformation (N-DLT) followed by orthonormal basis lifting. Extensive evaluations on a digital-twin simulation and two real-world PV datasets demonstrate that the proposed method achieves a boundary extraction mean corner error (MCE) within 1 cm on synthetic data, and defect localization root-mean-square errors (RMSE) of 0.913 cm and 3.219 cm on two real PV scenes, respectively. On the simulation dataset, absolute coordinate errors for both visible and infrared channels remain below 2.5 cm. These results meet or exceed state-of-the-art performance, validating the effectiveness and robustness of SGA-Loc for outdoor PV defect localization.