GPS-Assisted Feature Matching in Aerial Images with Highly Repetitive Patterns

Luzardo, Gonzalo; Vlaminck, Michiel; Lefkaditis, D.; Philips, Wilfried; Luong, Hiêp

doi:10.1109/igarss47720.2021.9553147

Cited by 2 publications

(1 citation statement)

References 9 publications

(19 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…They allow cost-effective yet sufficiently detailed surveying of scenes on the scale of small forests, fields and buildings. In addition they are ideally placed for infrastructure inspection of hard to reach places [1]- [6].…”

Section: Introductionmentioning

confidence: 99%

On the Optimal Mounting Angle for a Spinning LiDAR on a UAV

et al. 2022

View full text Add to dashboard Cite

UAV-based 3D LiDAR mapping has received increasing interest from both the research community and industrial operations for the 3D reconstruction of large and dangerous environments. When a LiDAR sensor is rigidly mounted to a UAV, one usually orients it such that the LiDAR's upward direction coincides with the UAV's flight direction. For a spinning LiDAR this fully specifies the mounting orientation because of circular symmetry. However, we argue in this paper that this configuration is suboptimal, especially when the LiDAR's full horizontal field of view is not important, either because of a limited field of view of other sensors in case of sensor fusion, or because the scene to (swath) map via LiDAR is less wide than the LiDAR's field of view. Indeed, in this situation many of the points the LiDAR samples are not of interest. Additionally, in the usual configuration the UAV's movement can compensate for the limited elevation resolution of the LiDAR, but much less so for the azimuth resolution. For a simplified theoretical model we introduce a quality metric for mounting angles. Using a simulation we then derive the optimal mounting angle, which we validate via real world flights. We suggest to rotate this standard mounting orientation over an angle of −84.5 • over the UAV's vertical direction.

show abstract

Section: Introductionmentioning

confidence: 99%

On the Optimal Mounting Angle for a Spinning LiDAR on a UAV

et al. 2022

View full text Add to dashboard Cite

show abstract

Region-Based CNN for Anomaly Detection in PV Power Plants Using Aerial Imagery

Vlaminck

Heidbuchel²,

Philips

et al. 2022

Sensors

View full text Add to dashboard Cite

Today, solar energy is taking an increasing share of the total energy mix. Unfortunately, many operational photovoltaic plants suffer from a plenitude of defects resulting in non-negligible power loss. The latter highly impacts the overall performance of the PV site; therefore, operators need to regularly inspect their solar parks for anomalies in order to prevent severe performance drops. As this operation is naturally labor-intensive and costly, we present in this paper a novel system for improved PV diagnostics using drone-based imagery. Our solution consists of three main steps. The first step locates the solar panels within the image. The second step detects the anomalies within the solar panels. The final step identifies the root cause of the anomaly. In this paper, we mainly focus on the second step comprising the detection of anomalies within solar panels, which is done using a region-based convolutional neural network (CNN). Experiments on six different PV sites with different specifications and a variety of defects demonstrate that our anomaly detector achieves a true positive rate or recall of more than 90% for a false positive rate of around 2% to 3% tested on a dataset containing nearly 9000 solar panels. Compared to the best state-of-the-art methods, the experiments revealed that we achieve a slightly higher true positive rate for a substantially lower false positive rate, while tested on a more realistic dataset.

show abstract

GPS-Assisted Feature Matching in Aerial Images with Highly Repetitive Patterns

Cited by 2 publications

References 9 publications

On the Optimal Mounting Angle for a Spinning LiDAR on a UAV

On the Optimal Mounting Angle for a Spinning LiDAR on a UAV

Region-Based CNN for Anomaly Detection in PV Power Plants Using Aerial Imagery

Contact Info

Product

Resources

About