Proceedings of the 20th International Workshop on Mobile Computing Systems and Applications 2019
DOI: 10.1145/3301293.3302365
|View full text |Cite
|
Sign up to set email alerts
|

Towards Drone-sourced Live Video Analytics for the Construction Industry

Abstract: This paper investigates the use of drones for live inspection in the construction industry. The key technical challenge is the real-time registration of the drone video feed to the architectural plan. We present and evaluate three different approaches for registration and propose an edge-based prototype using visual features. Our evaluations show that GPS alone is not sufficient for accurate registration, but with visual features, accuracies within ten centimeters can be achieved.

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1
1

Citation Types

0
7
0

Year Published

2020
2020
2024
2024

Publication Types

Select...
5
2

Relationship

0
7

Authors

Journals

citations
Cited by 13 publications
(7 citation statements)
references
References 16 publications
0
7
0
Order By: Relevance
“…On one hand, computer vision accuracy has been improved by deep learning at the cost of increased compute demand. On the other hand, low prices of high-definition network-connected cameras make them widely deployed in traffic monitoring [27], video analytics in retail stores [12], and inspection of warehouses or remote industrial sites [38]. Thus, the camera operators must scale out the compute costs of analyzing ever more camera feeds [2,6,21].…”
Section: Video Streaming For Video Analyticsmentioning
confidence: 99%
“…On one hand, computer vision accuracy has been improved by deep learning at the cost of increased compute demand. On the other hand, low prices of high-definition network-connected cameras make them widely deployed in traffic monitoring [27], video analytics in retail stores [12], and inspection of warehouses or remote industrial sites [38]. Thus, the camera operators must scale out the compute costs of analyzing ever more camera feeds [2,6,21].…”
Section: Video Streaming For Video Analyticsmentioning
confidence: 99%
“…In traffic monitoring [2] it is useful to have timely insights, appropriately tuning γi and γi . In construction survey [3] there are no strict time deadlines, so γi = 0.…”
Section: A Mission Scheduling Problem (Msp)mentioning
confidence: 99%
“…Unmanned Aerial Vehicles (UAVs), also called drones, are enabling a wide range of applications in smart cities [1], such as traffic monitoring [2], construction surveys [3], package delivery [4], localization [5], and disaster (including COVID-19) management [6], assisted by 5G wireless roll-out [7]. The mobility, agility, and hovering capabilities of drones allow them to rapidly fly to points of interest (i.e., waypoints) in the city to accomplish specific activities.…”
Section: Introductionmentioning
confidence: 99%
“…Unmanned aerial vehicles (also known as drones) are gaining momentum to serve as moving eyes in the sky. They fly in the low sky above a target area and perform real-time video surveillance for a wide variety of authorized and even critical activities such as large event (e.g., sports, concert, festival) surveillance, infrastructure safety inspection, search and rescue, wildfire surveillance, law enforcement and public safety assistance, to name many [2][3][4][5][6]. Drones possess unique advantages over its counterparts -cameras pre-deployed on the ground: a drone can cruise at a much higher altitude with a broader field of view (FoV) and an unparalleled perspective (birds' eye view) for surveillance; It is always available to operate on demand.…”
Section: Introductionmentioning
confidence: 99%
“…To this end, a promising paradigm is to offload heavy computing tasks to the edge [1,4,6,15]. As illustrated in Figure 1, the drone is responsible for recording and streaming the captured video to the edge while the edge performs heavy analytical tasks over the received video frames.…”
Section: Introductionmentioning
confidence: 99%