Simple monocular door detection and tracking

Sekkal, Rafiq; Pasteau, Franccois; Babel, Marie; Brun, Baptiste; Leplumey, Ivan

doi:10.1109/icip.2013.6738809

Cited by 15 publications

(9 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Unfortunately, their methods were available for closed doors. Sekkal, Pasteau, Babel, Brun, and Leplumey (2013) aimed to detect doors situated in a corridor via a monocular camera. They first determined boundaries between wall and floor.…”

Section: Vision-based Approachesmentioning

confidence: 99%

Iç Ortamlarda Kapilarin Tespi̇ti̇ İçi̇n Deri̇n Öğrenme Tekni̇kleri̇ni̇n Karşilaştirilmasi

Kaleci

Turgut

2021

Eskişehir Osmangazi Üniversitesi Mühendislik Ve Mimarlık Fakültesi Dergisi

View full text Add to dashboard Cite

In indoor environments, the detection of doors (open, semi-opened, and closed) is a crucial task for a variety of fields such as robotics, computer vision, and architecture. The studies that are addressed the door detection problem can be divided into three major categories: 1) closed doors via visual data, 2) open doors via range data, and 3) open, semi-opened, and closed doors via point cloud data. Although some successful studies have been proposed being detected doors via visual and range data under specific circumstances, in this study, we exploited point cloud data due to its ability to describe the 3D characteristic of scenes. The main contribution of this study is two-fold. Firstly, we mainly intended to discover the potential of point-based deep learning architectures such as PointNet, PointNet++, Dynamic Graph Convolutional Neural Network (DGCNN), PointCNN, and Point2Sequence, in contrast to previous studies that generally defined a set of rules depending on the type of door and characteristics of the data. Secondly, the OGUROB DOORS dataset is constructed, which contains point cloud data captured in the GAZEBO simulation environment in different robot positions and orientations. We used precision, recall, and F1-score metrics to analyze the merit and demerit aspects of these architectures. Also, some visual results were given to describe the characteristics of these architectures. The test results showed that all architectures are capable of classifying open, semi-opened, and closed doors over 98% accuracy.

show abstract

Section: Vision-based Approachesmentioning

confidence: 99%

Iç Ortamlarda Kapilarin Tespi̇ti̇ İçi̇n Deri̇n Öğrenme Tekni̇kleri̇ni̇n Karşilaştirilmasi

Kaleci

Turgut

2021

Eskişehir Osmangazi Üniversitesi Mühendislik Ve Mimarlık Fakültesi Dergisi

View full text Add to dashboard Cite

show abstract

“…In [12], the authors apply a door detection algorithm through a Line Segment Detection (LSD) to guide terrestrial robots through a corridor when dealing with indoor environments.…”

Section: Related Workmentioning

confidence: 99%

Comparison between digital image processing and learning techniques on a door detection task

Kappel¹,

Ferreira²

2020

Proceedings of the III Brazilian Humanoid Robot Workshop (BRAHUR) and IV Brazilian Workshop on Service Robotics (BRASERO)

View full text Add to dashboard Cite

Door detection is a core task for any indoor autonomous robot at any level, such as assistive and domestic robots. However, the application of machine learning techniques can face hard constraints for embedded devices or autonomous platforms such as processing, memory, and energy. This paper aims to analyze and discuss the viability of two different approaches to the problem, a straight Digital Image Processing technique, and a Machine Learning based technique. Both strategies got compared under an Nvidia Jetson Nano. Therefore, after analyzing the resultant data, the Machine Learning based technique has shown the best overall mAP when compared to the Digital Image Processing technique (0.45 and 0.21, respectively). Also, the Machine Learning approach has proven to be more stable time-wise, which is another positive feature.

show abstract

“…For two segments, this process is done by taking into account the slope and extremities, and if they are close enough, they are merged to form a unique line. More details are given in [24].…”

Section: Estimation Of X Fmentioning

confidence: 99%

“…Consequently, we use a door detection and tracking framework specifically developed for indoor navigation tasks [24]. This framework uses a set of information including the vanishing point to estimate a 3-D geometrical structure of the corridor.…”

Section: Door Recognition and Trackingmentioning

confidence: 99%

A visual servoing approach for autonomous corridor following and doorway passing in a wheelchair

Pasteau

Narayanan

Babel

et al. 2016

Robotics and Autonomous Systems

Self Cite

View full text Add to dashboard Cite

International audienceNavigating within an unknown indoor environment using an electric wheelchair is a challenging task, especially if the user suffers from severe disabilities. In order to reduce fatigability and increase autonomy, control architectures have to be designed that would assist users in wheelchair navigation. We present a framework for vision-based autonomous indoor navigation in an electric wheelchair capable of following corridors, and passing through open doorways using a single doorpost. Visual features extracted from cameras on board the wheelchair are used as inputs for image based controllers built-in the wheelchair. It has to be noted that no a-priori information is utilised except for the assumption that the wheelchair moves in a typical indoor environment while the system is coarsely calibrated. The designed control schemes have been implemented onto a robotized wheelchair and experimental results show the robust behaviour of the designed system

show abstract

Simple monocular door detection and tracking

Cited by 15 publications

References 12 publications

Iç Ortamlarda Kapilarin Tespi̇ti̇ İçi̇n Deri̇n Öğrenme Tekni̇kleri̇ni̇n Karşilaştirilmasi

Iç Ortamlarda Kapilarin Tespi̇ti̇ İçi̇n Deri̇n Öğrenme Tekni̇kleri̇ni̇n Karşilaştirilmasi

Comparison between digital image processing and learning techniques on a door detection task

A visual servoing approach for autonomous corridor following and doorway passing in a wheelchair

Contact Info

Product

Resources

About