Semantic Map Annotation Through UAV Video Analysis Using Deep Learning Models in ROS

Kakaletsis, Efstratios; Tzelepi, Maria; Kaplanoglou, Pantelis I.; Symeonidis, Charalampos; Nikolaidis, Nikos; Tefas, Anastasios; Pitas, Ioannis

doi:10.1007/978-3-030-05716-9_27

Cited by 9 publications

(7 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Discriminant Analysis (DA) and Minimum Enclosed Ball (MEB) regularizers are specific instances of this framework, introduced and described in detail in [139]. Training is performed in the typical manner for feedforward neural networks, using error back-propagation and Stochastic Gradient Descent on the Crowd-Drone dataset [63]. This dataset includes Youtube videos depicting crowded events (e.g.marathon, festival, parade, political rally, protests, etc).…”

Section: Crowd Detector (Cd)mentioning

confidence: 99%

“…Recently, the robotics community has focused on the presence of semantics in maps [108] [13] [102], to develop autonomous robots capable of understanding the semantic representation [110], [25], [93] and relationships between the objects in the environment, besides exploiting occupancy grid maps for navigation. Indeed, a 3D map representing the UAV flight environment could be enriched with semantic region annotations relating to safety, such as crowd gathering locations [63] or no-fly zones in general. This is crucial for drone path planning and navigation.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Computer Vision for Autonomous UAV Flight Safety: An Overview and a Vision-based Safe Landing Pipeline Example

KakaletsisEfstratios

SymeonidisCharalampos

TzelepiMaria

et al. 2021

ACM Comput. Surv.

Self Cite

View full text Add to dashboard Cite

Recent years have seen an unprecedented spread of Unmanned Aerial Vehicles (UAVs, or “drones”), which are highly useful for both civilian and military applications. Flight safety is a crucial issue in UAV navigation, having to ensure accurate compliance with recently legislated rules and regulations. The emerging use of autonomous drones and UAV swarms raises additional issues, making it necessary to transfuse safety- and regulations-awareness to relevant algorithms and architectures. Computer vision plays a pivotal role in such autonomous functionalities. Although the main aspects of autonomous UAV technologies (e.g., path planning, navigation control, landing control, mapping and localization, target detection/tracking) are already mature and well-covered, ensuring safe flying in the vicinity of crowds, avoidance of passing over persons, or guaranteed emergency landing capabilities in case of malfunctions, are generally treated as an afterthought when designing autonomous UAV platforms for unstructured environments. This fact is reflected in the fragmentary coverage of the above issues in current literature. This overview attempts to remedy this situation, from the point of view of computer vision. It examines the field from multiple aspects, including regulations across the world and relevant current technologies. Finally, since very few attempts have been made so far towards a complete UAV safety flight and landing pipeline, an example computer vision-based UAV flight safety pipeline is introduced, taking into account all issues present in current autonomous drones. The content is relevant to any kind of autonomous drone flight (e.g., for movie/TV production, news-gathering, search and rescue, surveillance, inspection, mapping, wildlife monitoring, crowd monitoring/management), making this a topic of broad interest.

show abstract

Section: Crowd Detector (Cd)mentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Computer Vision for Autonomous UAV Flight Safety: An Overview and a Vision-based Safe Landing Pipeline Example

KakaletsisEfstratios

SymeonidisCharalampos

TzelepiMaria

et al. 2021

ACM Comput. Surv.

Self Cite

View full text Add to dashboard Cite

show abstract

“…In order to validate the importance of the novel BF and FAI components of the proposed method, a "no-fusion" variant was also evaluated which accumulates the 3D annotations derived from all drones over time and simply combines them using an OR operator. Thus, the "no-fusion" variant is more of an elaborate engineering pipeline [55].…”

Section: Performance Evaluationmentioning

confidence: 99%

Multiview vision-based human crowd localization for UAV fleet flight safety

Kakaletsis

Mademlis

Nikolaidis

et al. 2021

Signal Processing: Image Communication

Self Cite

View full text Add to dashboard Cite

“…This process can also be integrated into the vision-group, using a deep neural network running on GP-GPU in real-time [56] [57]. Subsequently, the detected crowd ROI (in pixel coordinates) may be corresponded to the relevant terrain areas of the 3D map by perspective back-projection [58], so as to achieve a semantic annotation of the map [59]. This is important, due to legal regulations restricting UAV flight above human crowds.…”

Section: A Perceptionmentioning

confidence: 99%

Autonomous UAV Cinematography

et al. 2019

Self Cite

View full text Add to dashboard Cite

The emerging field of autonomous UAV cinematography is examined through a tutorial for non-experts, which also presents the required underlying technologies and connections with different UAV application domains. Current industry practices are formalized by presenting a UAV shot-type taxonomy composed of framing shot types, single-UAV camera motion types, and multiple-UAV camera motion types. Visually pleasing combinations of framing shot types and camera motion types are identified, while the presented camera motion types are modeled geometrically and graded into distinct energy consumption classes and required technology complexity levels for autonomous capture. Two specific strategies are prescribed, namely focal length compensation and multidrone compensation , for partially overcoming a number of issues arising in UAV live outdoor event coverage, deemed as the most complex UAV cinematography scenario. Finally, the shot types compatible with each compensation strategy are explicitly identified. Overall, this tutorial both familiarizes readers coming from different backgrounds with the topic in a structured manner and lays necessary groundwork for future advancements.

show abstract

Semantic Map Annotation Through UAV Video Analysis Using Deep Learning Models in ROS

Cited by 9 publications

References 23 publications

Computer Vision for Autonomous UAV Flight Safety: An Overview and a Vision-based Safe Landing Pipeline Example

Computer Vision for Autonomous UAV Flight Safety: An Overview and a Vision-based Safe Landing Pipeline Example

Multiview vision-based human crowd localization for UAV fleet flight safety

Autonomous UAV Cinematography

Contact Info

Product

Resources

About