Semantic segmentation on Swiss3DCities: A benchmark study on aerial photogrammetric 3D pointcloud dataset

Can, Gulcan; Mantegazza, Dario; Abbate, Gabriele; Chappuis, Sébastien; Giusti, Alessandro

doi:10.1016/j.patrec.2021.06.004

Cited by 30 publications

(14 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…• Labelling of Scenes and Images: Triggering XR labels with image classification [195]. • Semantic Segmentation and Occlusion: Segmentation and occlusion of the specified objects [196]. • Object Detection: The object's extent and position in a scene can be estimated to form colliders and hitboxes to enable interactions between virtual and physical objects [197].…”

Section: E Multi-sensory Xr Applications Holographic Telepresencementioning

confidence: 99%

Applications of Explainable AI for 6G: Technical Aspects, Use Cases, and Research Challenges

Wang¹,

Qureshi²,

Miralles-Pechuaán³

et al. 2021

Preprint

View full text Add to dashboard Cite

When 5G began its commercialisation journey around 2020, the discussion on the vision of 6G also surfaced. Researchers expect 6G to have higher bandwidth, coverage, reliability, energy efficiency, lower latency, and, more importantly, an integrated "human-centric" network system powered by artificial intelligence (AI). Such a 6G network will lead to an excessive number of automated decisions made every second. These decisions can range widely, from network resource allocation to collision avoidance for self-driving cars. However, the risk of losing control over decision-making may increase due to high-speed data-intensive AI decision-making beyond designers and users' comprehension. The promising explainable AI (XAI) methods can mitigate such risks by enhancing the transparency of the black box AI decision-making process. This survey paper highlights the need for XAI towards the upcoming 6G age in every aspect, including 6G technologies (e.g., intelligent radio, zero-touch network management) and 6G use cases (e.g., industry 5.0). Moreover, we summarised the lessons learned from the recent attempts and outlined important research challenges in applying XAI for building 6G systems. This research aligns with goals 9, 11, 16, and 17 of the United Nations Sustainable Development Goals (UN-SDG) 1 , promoting innovation and building infrastructure, sustainable and inclusive human settlement, advancing justice and strong institutions, and fostering partnership at the global level.

show abstract

Section: E Multi-sensory Xr Applications Holographic Telepresencementioning

confidence: 99%

Applications of Explainable AI for 6G: Technical Aspects, Use Cases, and Research Challenges

Wang¹,

Qureshi²,

Miralles-Pechuaán³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…As a development of Geographic Information Technologies (GIT), LiDAR has shown great potential in the field of archaeology [7] (p. 1). The use of LiDAR is becoming increasingly more frequent in archaeological research, with technical advances in the field [8][9][10][11][12]. This non-invasive method facilitates archaeological surveys of sites that would not have been possible by means of a geophysical survey or aerial photography [13] (p. 27).…”

Section: Lidar a Tool Tailored To The Inaccessibility Of The Terrainmentioning

confidence: 99%

“…In the Istrian Peninsula, both in Croatia and Slovenia, hillforts dating from the Bronze and Iron Ages have been found [21] (p. 6) [22] (pp. [4][5][6][7][8][9][10][11][12]. Other examples are the LiDAR surveys performed in France in the Forest of Tronçais and the Garonne Valley.…”

Section: Lidar a Tool Tailored To The Inaccessibility Of The Terrainmentioning

confidence: 99%

“…In the Forest of Agre, Gallo-Roman structures, a potential fortified medieval enclosure, and a medieval church were found [24] (pp. [3][4][5][6][7][8][9][10][11][12][13][14]. In Colophon, Anatolia (modern-day Turkey), LiDAR was used to locate and map the wooded hills around the town, providing rich and detailed data of the terrain [25] (pp.…”

Section: Lidar a Tool Tailored To The Inaccessibility Of The Terrainmentioning

confidence: 99%

See 1 more Smart Citation

Revealing Archaeological Sites under Mediterranean Forest Canopy Using LiDAR: El Viandar Castle (husum) in El Hoyo (Belmez-Córdoba, Spain)

Checa

Moreno-Escribano

Gasparini

et al. 2021

Drones

View full text Add to dashboard Cite

Light detection and Ranging (LiDAR) technology is a valuable tool for archaeological prospection in areas covered by dense vegetation. Its capacity to penetrate dense forest environments enables it to detect archaeological remains scattered over orographically complex areas. LiDAR-derived digital terrain models (DTMs) have made an exceptional contribution towards identifying topographic landscapes of archaeological interest. In this study, we focus on an area of intense historic settlement from the Chalcolithic to the Middle Ages, which today is completely covered by Mediterranean forest. Due to the dense canopy, and the fact that it is a protected area on private land, it has never been analyzed. To reveal the settlement, we primarily used a series of LiDAR mapping surveys to gather data and analyzed other open access remote sensing resources from the National Geographic Institute of Spain (IGN). The IGN LiDAR data proved to be of particular interest. These resources enabled us to detect an ancient fortress (El Viandar Castle) and its surrounding settlement. LiDAR, in conjunction with other products, was fundamental in identifying the site. Equally, the mapping surveys enabled us to analyze the limits and scope of the IGN airborne LiDAR and other free access remote sensing products. Our background in this research demonstrates that low-cost products applied to LiDAR research in archaeology have major limitations when it is necessary to have a high level of spatial resolution in order to define the layout and the main components of an archaeological site.

show abstract

“…Swiss3DCities proposed by Can et al [112] for 3D semantic segmentation Swiss3DCities is a new outdoor urban 3D point clouds dataset generated by photogrammetry based on images acquired by the UAV equipped with high-resolution cameras in three Swiss cities. The point clouds in this dataset are more uniform and denser than the point clouds acquired by the ground LiDAR.…”

mentioning

confidence: 99%

The Fusion Strategy of 2D and 3D Information Based on Deep Learning: A Review

et al. 2021

View full text Add to dashboard Cite

Recently, researchers have realized a number of achievements involving deep-learning-based neural networks for the tasks of segmentation and detection based on 2D images, 3D point clouds, etc. Using 2D and 3D information fusion for the advantages of compensation and accuracy improvement has become a hot research topic. However, there are no critical reviews focusing on the fusion strategies of 2D and 3D information integration based on various data for segmentation and detection, which are the basic tasks of computer vision. To boost the development of this research domain, the existing representative fusion strategies are collected, introduced, categorized, and summarized in this paper. In addition, the general structures of different kinds of fusion strategies were firstly abstracted and categorized, which may inspire researchers. Moreover, according to the methods included in this paper, the 2D information and 3D information of different methods come from various kinds of data. Furthermore, suitable datasets are introduced and comparatively summarized to support the relative research. Last but not least, we put forward some open challenges and promising directions for future research.

show abstract

Semantic segmentation on Swiss3DCities: A benchmark study on aerial photogrammetric 3D pointcloud dataset

Cited by 30 publications

References 16 publications

Applications of Explainable AI for 6G: Technical Aspects, Use Cases, and Research Challenges

Applications of Explainable AI for 6G: Technical Aspects, Use Cases, and Research Challenges

Revealing Archaeological Sites under Mediterranean Forest Canopy Using LiDAR: El Viandar Castle (husum) in El Hoyo (Belmez-Córdoba, Spain)

The Fusion Strategy of 2D and 3D Information Based on Deep Learning: A Review

Contact Info

Product

Resources

About