Real-Time 3D Door Detection and Classification on a Low-Power Device

Ramôa, Gaspar; Alexandre, Luı́s A.; Mogo, S.

doi:10.1109/icarsc49921.2020.9096155

Cited by 7 publications

(11 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The manuscript presented is the extended version of [6]. Three new methods of door detection and classification of their degree of opening are proposed and compared.…”

Section: Discussionmentioning

confidence: 99%

“…This repository is the Hello AI guide for deploying deep-learning inference networks into NVIDIA Jetson systems. These networks are based We did not use the semantic segmentation algorithms of method A [6], since the first one: [23], was not compatible with Jetson Nano and the other algorithm: [24], was not capable of detecting all of the doors in the test set of the previous work dataset.…”

Section: Methods C-2d Door Detection and 2d Door State Classificationmentioning

confidence: 99%

“…In our previous work, [6], we built two datasets, one for the 3D object classification algorithm, PointNet and the other for the semantic segmentation algorithms.…”

Section: Datasetsmentioning

confidence: 99%

“…Our methods work in real-time, despite running in low-power systems with weak GPU and are based in 2D and 3D object classification, 2D object detection and 2D semantic segmentation methods. We improved our previous work dataset [6], with 3D and RGB images with three different state classes: open doors, closed doors and semi-open doors. The images were captured using a 3D Realsense Camera.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Real-time 2D–3D door detection and state classification on a low-power device

et al. 2021

Self Cite

View full text Add to dashboard Cite

In this paper, we propose three methods for door state classification with the goal to improve robot navigation in indoor spaces. These methods were also developed to be used in other areas and applications since they are not limited to door detection as other related works are. Our methods work offline, in low-powered computers as the Jetson Nano, in real-time with the ability to differentiate between open, closed and semi-open doors. We use the 3D object classification, PointNet, real-time semantic segmentation algorithms such as, FastFCN, FC-HarDNet, SegNet and BiSeNet, the object detection algorithm, DetectNet and 2D object classification networks, AlexNet and GoogleNet. We built a 3D and RGB door dataset with images from several indoor environments using a 3D Realsense camera D435. This dataset is freely available online. All methods are analysed taking into account their accuracy and the speed of the algorithm in a low powered computer. We conclude that it is possible to have a door classification algorithm running in real-time on a low-power device.

show abstract

“…The manuscript presented is the extended version of [6]. Three new methods of door detection and classification of their degree of opening are proposed and compared.…”

Section: Discussionmentioning

confidence: 99%

Section: Methods C-2d Door Detection and 2d Door State Classificationmentioning

confidence: 99%

“…In our previous work, [6], we built two datasets, one for the 3D object classification algorithm, PointNet and the other for the semantic segmentation algorithms.…”

Section: Datasetsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Real-time 2D–3D door detection and state classification on a low-power device

et al. 2021

Self Cite

View full text Add to dashboard Cite

show abstract

“…In recent years, 3D door detection has received more attention than 2D door detection. In [ 24 ], the authors used 3D information with PointNet, FastFCN, and FC-HarDNet for door detection and classification on a low-power device. Much of the literature uses a geometry-based approach to door detection without the aid of machine or deep learning.…”

Section: Related Researchmentioning

confidence: 99%

Introduction to Door Opening Type Classification Based on Human Demonstration

Šimundić

Džijan

Pejić

et al. 2023

Sensors

View full text Add to dashboard Cite

Opening doors and drawers will be an important ability for future service robots used in domestic and industrial environments. However, in recent years, the methods for opening doors and drawers have become more diverse and difficult for robots to determine and manipulate. We can divide doors into three distinct handling types: regular handles, hidden handles, and push mechanisms. While extensive research has been done on the detection and handling of regular handles, the other types of handling have not been explored as much. In this paper, we set out to classify the types of cabinet door handling types. To this end, we collect and label a dataset consisting of RGB-D images of cabinets in their natural environment. As part of the dataset, we provide images of humans demonstrating the handling of these doors. We detect the poses of human hands and then train a classifier to determine the type of cabinet door handling. With this research, we hope to provide a starting point for exploring the different types of cabinet door openings in real-world environments.

show abstract

Deep learning model for doors detection: A contribution for context-awareness recognition of patients with Parkinson’s disease

Gonçalves¹,

Santos²

2023

Expert Systems with Applications

View full text Add to dashboard Cite

Real-Time 3D Door Detection and Classification on a Low-Power Device

Cited by 7 publications

References 10 publications

Real-time 2D–3D door detection and state classification on a low-power device

Real-time 2D–3D door detection and state classification on a low-power device

Introduction to Door Opening Type Classification Based on Human Demonstration

Deep learning model for doors detection: A contribution for context-awareness recognition of patients with Parkinson’s disease

Contact Info

Product

Resources

About