Are you ABLE to perform a life-long visual topological localization?

Arroyo, Roberto; Alcantarilla, Pablo F.; Bergasa, Luis M.; Romera, Eduardo

doi:10.1007/s10514-017-9664-7

Cited by 19 publications

(26 citation statements)

References 77 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Topological localization tackles the problem of recognizing places when we revisit a scene. Arroyo [19] and Li et al [20] realized outdoor topological localization with a visual sensor and a GPS respectively. Several binary feature descriptors were tested in [19].…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Indoor Topological Localization Based on a Novel Deep Learning Technique

Liu

et al. 2020

Cogn Comput

View full text Add to dashboard Cite

Introduction: Millions of people in the world suffer from vision impairment or vision loss. Traditionally, they rely on guide sticks or dogs to move around and avoid potential obstacles. However, both guide sticks and dogs are passive. They are unable to provide conceptual knowledge or semantic contents of an environment. Methods: To address this issue, this paper presents a visionbased cognitive system to support the independence of visually impaired people. More specifically, a 3D indoor semantic map is constructed first with a hand-held RGB-D sensor. The constructed map is then deployed for indoor topological localization. Convolutional Neural Networks are used for both semantic information extraction and location inference. We additionally use semantic information to further verify localization results and eliminate errors. The topological localization performance can thus be improved despite significant appearance changes within an environment. Results: Experiments have been conducted to verify that the proposed method can increase both precision and recall rates. Conclusions: The system can be potentially deployed by visually impaired people to help them move around independently.

show abstract

Section: Related Workmentioning

confidence: 99%

“…Arroyo [19] and Li et al [20] realized outdoor topological localization with a visual sensor and a GPS respectively. Several binary feature descriptors were tested in [19]. In terms of visual features, the BoW model has been widely used in recent SLAM systems [21].…”

Section: Related Workmentioning

confidence: 99%

Indoor Topological Localization Based on a Novel Deep Learning Technique

Liu

et al. 2020

Cogn Comput

View full text Add to dashboard Cite

show abstract

“…Instead of querying the most likely location from a single image, SeqSLAM [ 40 ] achieves localization by recognizing coherent sequences of best matching images. In a similar way, ABLE [ 7 ] concatenates adjacent image descriptors to build a final descriptor and located the current position by matching sequential images matching. Identifying localizations as sequences of images is not effective all the time, considering the query images are possibly recorded at different speed with those in database images.…”

Section: Related Workmentioning

confidence: 99%

“…The majority of visual localization approaches are designed for autonomous vehicles or robots [ 4 , 5 , 6 , 7 ]. In those scenarios, the typical environmental changes are shown in Figure 1 a,b.…”

Section: Introductionmentioning

confidence: 99%

Visual Localizer: Outdoor Localization Based on ConvNet Descriptor and Global Optimization for Visually Impaired Pedestrians

Lin

Cheng

Wang

et al. 2018

Sensors

View full text Add to dashboard Cite

Localization systems play an important role in assisted navigation. Precise localization renders visually impaired people aware of ambient environments and prevents them from coming across potential hazards. The majority of visual localization algorithms, which are applied to autonomous vehicles, are not adaptable completely to the scenarios of assisted navigation. Those vehicle-based approaches are vulnerable to viewpoint, appearance and route changes (between database and query images) caused by wearable cameras of assistive devices. Facing these practical challenges, we propose Visual Localizer, which is composed of ConvNet descriptor and global optimization, to achieve robust visual localization for assisted navigation. The performance of five prevailing ConvNets are comprehensively compared, and GoogLeNet is found to feature the best performance on environmental invariance. By concatenating two compressed convolutional layers of GoogLeNet, we use only thousands of bytes to represent image efficiently. To further improve the robustness of image matching, we utilize the network flow model as a global optimization of image matching. The extensive experiments using images captured by visually impaired volunteers illustrate that the system performs well in the context of assisted navigation.

show abstract

“…Localization is one of important research topics concerning autonomous vehicles [1], [2], robotics [3] and assistive navigation [4], [5]. Generally, GNSS (global navigation satellite system) is the straightforward way to localize the autonomous vehicles in the urban areas.…”

Section: Introductionmentioning

confidence: 99%

Panoramic Annular Localizer: Tackling the Variation Challenges of Outdoor Localization Using Panoramic Annular Images and Active Deep Descriptors

Cheng

Wang

Lin

et al. 2019

2019 IEEE Intelligent Transportation Systems Conference (ITSC)

View full text Add to dashboard Cite

Visual localization is an attractive problem that estimates the camera localization from database images based on the query image. It is a crucial task for various applications, such as autonomous vehicles, assistive navigation and augmented reality. The challenging issues of the task lie in various appearance variations between query and database images, including illumination variations, dynamic object variations and viewpoint variations. In order to tackle those challenges, Panoramic Annular Localizer into which panoramic annular lens and robust deep image descriptors are incorporated is proposed in this paper. The panoramic annular images captured by the single camera are processed and fed into the NetVLAD network to form the active deep descriptor, and sequential matching is utilized to generate the localization result. The experiments carried on the public datasets and in the field illustrate the validation of the proposed system.

show abstract

Are you ABLE to perform a life-long visual topological localization?

Abstract: Noname manuscript No.

Cited by 19 publications

References 77 publications

Indoor Topological Localization Based on a Novel Deep Learning Technique

Indoor Topological Localization Based on a Novel Deep Learning Technique

Visual Localizer: Outdoor Localization Based on ConvNet Descriptor and Global Optimization for Visually Impaired Pedestrians

Panoramic Annular Localizer: Tackling the Variation Challenges of Outdoor Localization Using Panoramic Annular Images and Active Deep Descriptors

Contact Info

Product

Resources

About