On the Role of Field of View for Occlusion Removal with Airborne Optical Sectioning

Seits, Francis; Kurmi, Indrajit; Nathan, Rakesh John Amala Arokia; Ortner, Rudolf; Bimber, Oliver

doi:10.48550/arxiv.2204.13371

Cited by 3 publications

(4 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the presence of strong occlusion, targets like lost people, animals, vehicles, architectural structures, or ground fires cannot be detected in aerial images (neither visually nor automatically). With Airborne Optical Sectioning (AOS) [1][2][3][4][5][6][7], we have introduced a synthetic aperture imaging technique that removes occlusion in real time (cf. Figure 1a).…”

Section: Introductionmentioning

confidence: 99%

Synthetic Aperture Anomaly Imaging for Through-Foliage Target Detection

Amala Arokia Nathan,

Bimber

2023

Remote Sensing

View full text Add to dashboard Cite

The presence of foliage is a serious problem for target detection with drones in application fields such as search and rescue, surveillance, early wildfire detection, or wildlife observation. Visual as well as automatic computational methods, such as classification and anomaly detection, fail in the presence of strong occlusion. Previous research has shown that both benefit from integrating multi-perspective images recorded over a wide synthetic aperture to suppress occlusion. In particular, commonly applied anomaly detection methods can be improved by the more uniform background statistics of integral images. In this article, we demonstrate that integrating the results of anomaly detection applied to single aerial images instead of applying anomaly detection to integral images is significantly more effective and increases target visibility as well as precision by an additional 20% on average in our experiments. This results in enhanced occlusion removal and outlier suppression, and consequently, in higher chances of detecting targets that remain otherwise occluded. We present results from simulations and field experiments, as well as a real-time application that makes our findings available to blue-light organizations and others using commercial drone platforms. Furthermore, we outline that our method is applicable for 2D images as well as for 3D volumes.

show abstract

Section: Introductionmentioning

confidence: 99%

Synthetic Aperture Anomaly Imaging for Through-Foliage Target Detection

Amala Arokia Nathan,

Bimber

2023

Remote Sensing

View full text Add to dashboard Cite

show abstract

“…Airborne Optical Sectioning (AOS) [1][2][3][4][5][6][7][8][9][10][11][12][13] is a synthetic aperture sensing technique that computationally removes occlusion in real-time by registering and integrating multiple images captured within a large synthetic aperture area above forest (cf. Fig.…”

Section: Introductionmentioning

confidence: 99%

Evaluation of Color Anomaly Detection in Multispectral Images for Synthetic Aperture Sensing

Seits

Kurmi

Bimber

2022

Eng

View full text Add to dashboard Cite

In this article, we evaluate unsupervised anomaly detection methods in multispectral images obtained with a wavelength-independent synthetic aperture sensing technique called Airborne Optical Sectioning (AOS). With a focus on search and rescue missions that apply drones to locate missing or injured persons in dense forest and require real-time operation, we evaluate the runtime vs. quality of these methods. Furthermore, we show that color anomaly detection methods that normally operate in the visual range always benefit from an additional far infrared (thermal) channel. We also show that, even without additional thermal bands, the choice of color space in the visual range already has an impact on the detection results. Color spaces such as HSV and HLS have the potential to outperform the widely used RGB color space, especially when color anomaly detection is used for forest-like environments.

show abstract

“…With Airborne Optical Sectioning (AOS) [48][49][50][51][52][53][54][55][56][57][58][59][60], we introduced an optical synthetic aperture imaging technique that captures an unstructured light field with an aircraft, such as a drone. We utilized manually, automatically [48][49][50][51][52][53][54][55][56]58,59], or fully autonomously [57] operated camera drones that sample multispectral (RGB and thermal) images within a certain (synthetic aperture) area above occluding vegetation (such as forest) and combined their signals computationally to remove occlusion.…”

Section: Introductionmentioning

confidence: 99%

“…So far, AOS has been applied to the visible [48,59] and the far-infrared (thermal) spectrum [51] for various applications, such as archeology [48,49], wildlife observation [52], and search and rescue [55,56]. By employing a randomly distributed statistical model [50,57,60] the limits of AOS and its efficacy with respect to its optimal sampling parameters can be explained. Common image processing tasks, such as classification with deep neural networks [55,56] or color anomaly detection [59] are proven to perform significantly better when applied to AOS integral images compared with conventional aerial images.…”

Section: Introductionmentioning

confidence: 99%

Inverse Airborne Optical Sectioning

Nathan

Kurmi

Bimber

2022

Drones

View full text Add to dashboard Cite

We present Inverse Airborne Optical Sectioning (IAOS), an optical analogy to Inverse Synthetic Aperture Radar (ISAR). Moving targets, such as walking people, that are heavily occluded by vegetation can be made visible and tracked with a stationary optical sensor (e.g., a hovering camera drone above forest). We introduce the principles of IAOS (i.e., inverse synthetic aperture imaging), explain how the signal of occluders can be further suppressed by filtering the Radon transform of the image integral, and present how targets’ motion parameters can be estimated manually and automatically. Finally, we show that while tracking occluded targets in conventional aerial images is infeasible, it becomes efficiently possible in integral images that result from IAOS.

show abstract

On the Role of Field of View for Occlusion Removal with Airborne Optical Sectioning

Cited by 3 publications

References 0 publications

Synthetic Aperture Anomaly Imaging for Through-Foliage Target Detection

Synthetic Aperture Anomaly Imaging for Through-Foliage Target Detection

Evaluation of Color Anomaly Detection in Multispectral Images for Synthetic Aperture Sensing

Inverse Airborne Optical Sectioning

Contact Info

Product

Resources

About