A novel mobile robot localization approach based on topological maps using classification with reject option in omnidirectional images

Marinho, Leandro Balby; Almeida, Jefferson S.; Souza, Joo Wellington M.; Albuquerque, Victor Hugo C. de; Filho, Pedro Pedrosa Rebouças

doi:10.1016/j.eswa.2016.12.007

Cited by 51 publications

(30 citation statements)

References 68 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…At the rear (stern), there was a servo motor (5) connected to the rudder (6). Further, from the stern comes the data cable (7) and a mini float (8), connecting the probes (9).…”

Section: Vector: the Boatmentioning

confidence: 99%

Development of a Robotic Airboat for Online Water Quality Monitoring in Lakes

et al. 2019

View full text Add to dashboard Cite

Maintenance of water resources through collection of water followed by laboratory analysis, is a key factor in the measurement of water quality. The main difficulty for water collection and analysis is the logistics of the process, since the collections are often made by mall boats in very distant aquifers, applying manual processes, and are sometimes based on few samples. In this paper, the development, construction, and implementation of a robotic airboat to measure water quality in lakes has been described. The airboat was developed in the form of a mini-boat, in a fiberglass structure, whose interior housed a battery, a Raspberry Pi mini-computer, a Wi-Fi router for connection to a notebook, tablet or cell phone, and sensors connected to the Arduino platform. The airboat was validated in two lagoons in Fortaleza, and in a reservoir in the city of Pacatuba. The results were collected with the purpose of analyzing the parameters of each lagoon. The main contribution of this work was the development of an autonomous system of acquiring water parameters from several points of the lagoon.

show abstract

“…At the rear (stern), there was a servo motor (5) connected to the rudder (6). Further, from the stern comes the data cable (7) and a mini float (8), connecting the probes (9).…”

Section: Vector: the Boatmentioning

confidence: 99%

Development of a Robotic Airboat for Online Water Quality Monitoring in Lakes

et al. 2019

View full text Add to dashboard Cite

show abstract

“…They are increasingly used in many scenarios in the past few years, such as street view capture and indoor monitor. Panoramas also played an efficient role in the scientific researches like robot localization field (Marinho, Almeida, Souza, Albuquerque, & Rebouças Filho, 2017) and 3D structure reconstruction (Pintore, Ganovelli, Gobbetti, & Scopigno, 2016) for their inner three-dimensional information. But they have been rarely used in the conventional object identification in street environment.…”

Section: Introductionmentioning

confidence: 99%

Fully Convolutional Networks for Street Furniture Identification in Panorama Images

Wang

Zhou

et al. 2019

Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

Panoramic images are widely used in many scenes, especially in virtual reality and street view capture. However, they are new for street furniture identification which is usually based on mobile laser scanning point cloud data or conventional 2D images. This study proposes to perform semantic segmentation on panoramic images and transformed images to separate light poles and traffic signs from background implemented by pre-trained Fully Convolutional Networks (FCN). FCN is the most important model for deep learning applied on semantic segmentation for its end to end training process and pixel-wise prediction. In this study, we use FCN-8s model that pre-trained on cityscape dataset and finetune it by our own data. The results show that in both pre-trained model and fine-tuning, transformed images have better prediction results than panoramic images.

show abstract

“…Hao and colleagues have studied the orientation of mobile service robots in a closed environment using artificial labels based on QR code, using a relational method between objects. In their work, they have been able to locate the service robot using a hybrid mapping with QR coding technique [6]. Rostkowska and Topolski have followed the QR code for robots in the workplace using a low cost camera.…”

Section: Introductionmentioning

confidence: 99%

Path Planning of Mobile Robots Based on QR Code

Atali¹,

Garip²,

Özkan³

et al. 2018

acperpro

View full text Add to dashboard Cite

The place and importance of mobile robots in today's industry is increasing day by day. The use of mobile robots for industrial purposes such as sorting, moving and placing is no longer a preference but a necessity. With methods such as line, magnetic field, infrared ray or image tracking, positioning of mobile robots and path planning are possible. The use of these methods depends on the application fields. The industry started with mobile line following robot&rsquo;s application at the beginning, gradually they have been developing day by day, and pursuits for different methods. If the topic examined under the heading of Industry 4.0, it is necessary to equip mobile robots with innovative technologies. The need for mobile robots that can provide fast, effective and practical solutions is being investigated by academics and commercial product developers.In this study, it is aimed to carry out a QR code based study on path planning of industrial mobile robots with distributed mobility. For this purpose, coordinates of the mobile robot work area are represented by QR labels and prepared in the form of a matrix. This way, developed path planning algorithm can be evaluated as a derivative of existing algorithms.

show abstract

A novel mobile robot localization approach based on topological maps using classification with reject option in omnidirectional images

Cited by 51 publications

References 68 publications

Development of a Robotic Airboat for Online Water Quality Monitoring in Lakes

Development of a Robotic Airboat for Online Water Quality Monitoring in Lakes

Fully Convolutional Networks for Street Furniture Identification in Panorama Images

Path Planning of Mobile Robots Based on QR Code

Contact Info

Product

Resources

About