An effective approach to unmanned aerial vehicle navigation using visual topological map in outdoor and indoor environments

Han, Tao; Almeida, Jefferson S.; Silva, Suane Pires P. da; Filho, Paulo Honório; Rodrigues, Antonio Wendell De Oliveira; Albuquerque, Victor Hugo C. de; Filho, Pedro Pedrosa Rebouças

doi:10.1016/j.comcom.2019.12.026

Cited by 7 publications

(4 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…RF spent significantly more time training the model than the other methods, which verifies previous research [82][83][84]. KNN spent significantly more time testing the model compared to NB and DT, which is consistent with existing research [85,86]. These differences align with previous research about machine learning algorithm complexity [59].…”

Section: Comparison Of Timesupporting

confidence: 89%

Mapping Urban Floods via Spectral Indices and Machine Learning Algorithms

Li,

Woodley,

Chappell

2024

Sustainability

View full text Add to dashboard Cite

Throughout history, natural disasters have caused severe damage to people and properties worldwide. Flooding is one of the most disastrous types of natural disasters. A key feature of flood assessment has been making use of the information derived from remote-sensing imagery from optical sensors on satellites using spectral indices. Here, a study was conducted about a recent spectral index, the Normalised Difference Inundation Index, and a new ensemble spectral index, the Concatenated Normalised Difference Water Index, and two mature spectral indices: Normalised Difference Water Index and the differential Normalised Difference Water Index with four different machine learning algorithms: Decision Tree, Random Forest, Naive Bayes, and K-Nearest Neighbours applied to the PlanetScope satellite imagery about the Brisbane February 2022 flood which is in urban environment. Statistical analysis was applied to evaluate the results. Overall, the four algorithms provided no significant difference in terms of accuracy and F1 score. However, there were significant differences when some variations in the indices and the algorithms were combined. This research provides a validation of existing measures to identify floods in an urban environment that can help to improve sustainable development.

show abstract

Section: Comparison Of Timesupporting

confidence: 89%

Mapping Urban Floods via Spectral Indices and Machine Learning Algorithms

Li,

Woodley,

Chappell

2024

Sustainability

View full text Add to dashboard Cite

show abstract

“…+h l ϕ ϕ ϕ min arg (7) In the boundary extraction procedure, some gaps may exist in the extracted boundary. When the line MN rotates through these gaps, there are no intersection points.…”

Section: ( ) ( ) (mentioning

confidence: 99%

“…A reasonable indoor map model generally enables people to find the shortest path connecting two indoor locations, while avoiding collisions with obstacles [6]. Currently, most individuals have been enjoying the advantages of outdoor LBS such as Google map based on comprehensive outdoor map networks [7], but indoor maps have not been fully developed [8]. Although many applications require indoor maps to provide more powerful functions for end-users, the intelligent generation of indoor maps remains a challenging task due to the complexity of the indoor environment.…”

Section: Introductionmentioning

confidence: 99%

Extracting 3D Indoor Maps with Any Shape Accurately Using Building Information Modeling Data

Qiu

Wang

Qing-sheng

et al. 2021

IJGI

View full text Add to dashboard Cite

Indoor maps lay the foundation for most indoor location-based services (LBS). Building Information Modeling (BIM) data contains multiple dimensional computer-aided design information. Some studies have utilized BIM data to automatically extract 3D indoor maps. A complete 3D indoor map consists of both floor-level maps and cross-floor paths. Currently, the floor-level indoor maps are mainly either grid-based maps or topological maps, and the cross-floor path generation schemes are not adaptive to building elements with irregular 3D shapes. To address these issues, this study proposes a novel scheme to extract an accurate 3D indoor map with any shape using BIM data. Firstly, this study extracts grid-based maps from BIM data and generates the topological maps directly through the grid-based maps using image thinning. A novel hybrid indoor map, termed Grid-Topological map, is then formed by the grid-based maps and topological maps jointly. Secondly, this study obtains the cross-floor paths from cross-floor building elements by a four-step process, namely X-Z projection, boundary extraction, X-Z topological path generation, and path-BIM intersection. Finally, experiments on eight typical types of cross-floor building elements and three multi-floor real-world buildings were conducted to prove the effectiveness of the proposed scheme, the average accuracy rates of the evaluated paths are higher than 88%. This study will advance the 3D indoor maps generation and inspire the application of indoor maps in indoor LBS, indoor robots, and 3D geographic information systems.

show abstract

“…Nevertheless, some drifting problems occur forcing the system to be constantly corrected. For their part, Han et al [ 40 ] proposed to use topological maps although they get a high accuracy, the processing does not work in real-time, making it inappropriate for our goal. An extended Kalman filter (EKF)-based multi-sensor fusion framework was used in [ 41 ] and in this case, a simple map consisting of pose information of attached tags is the base of a warehouse inventory application.…”

Section: Introductionmentioning

confidence: 99%

The UJI Aerial Librarian Robot: A Quadcopter for Visual Library Inventory and Book Localisation

Martínez-Martín

Ferrer

Vasilev

et al. 2021

Sensors

View full text Add to dashboard Cite

Over time, the field of robotics has provided solutions to automate routine tasks in different scenarios. In particular, libraries are awakening great interest in automated tasks since they are semi-structured environments where machines coexist with humans and several repetitive operations could be automatically performed. In addition, multirotor aerial vehicles have become very popular in many applications over the past decade, however autonomous flight in confined spaces still presents a number of challenges and the use of small drones has not been reported as an automated inventory device within libraries. This paper presents the UJI aerial librarian robot that leverages computer vision techniques to autonomously self-localize and navigate in a library for automated inventory and book localization. A control strategy to navigate along the library bookcases is presented by using visual markers for self-localization during a visual inspection of bookshelves. An image-based book recognition technique is described that combines computer vision techniques to detect the tags on the book spines, followed by an optical character recognizer (OCR) to convert the book code on the tags into text. These data can be used for library inventory. Misplaced books can be automatically detected, and a particular book can be located within the library. Our quadrotor robot was tested in a real library with promising results. The problems encountered and limitation of the system are discussed, along with its relation to similar applications, such as automated inventory in warehouses.

show abstract

An effective approach to unmanned aerial vehicle navigation using visual topological map in outdoor and indoor environments

Cited by 7 publications

References 13 publications

Mapping Urban Floods via Spectral Indices and Machine Learning Algorithms

Mapping Urban Floods via Spectral Indices and Machine Learning Algorithms

Extracting 3D Indoor Maps with Any Shape Accurately Using Building Information Modeling Data

The UJI Aerial Librarian Robot: A Quadcopter for Visual Library Inventory and Book Localisation

Contact Info

Product

Resources

About