Proceedings of the 6th ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation 2019
DOI: 10.1145/3360322.3360863
|View full text |Cite
|
Sign up to set email alerts
|

Smart Surface Classification for Accessible Routing through Built Environment

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1

Citation Types

0
4
0

Year Published

2020
2020
2024
2024

Publication Types

Select...
3
2
1

Relationship

0
6

Authors

Journals

citations
Cited by 13 publications
(4 citation statements)
references
References 29 publications
0
4
0
Order By: Relevance
“…In such cases, a crowd-sensing approach is often used, which involves collecting data about the qualities of path while target user participants (wheelchair users etc.) travel along the routes [51], [52]. While it had previously been difficult to implement routing systems based on such qualities in scale due to the effort required by participants, recent improvements in machine learning have led to the development of techniques which allow various accessibility and safety qualities to be inferred automatically from public data sets (such as identifying zebra-crossings from satellite images [83], [84]) or with less effort by participants (such as a passive crowdsensing approach proposed by Kamaldin et al [85] which automatically detects surface type conditions for wheelchair users or the Moving Wheels [86] which automatically detects obstacles such as steps or ramps from crowd-sourced wheelchair users).…”
Section: Discussionmentioning
confidence: 99%
See 2 more Smart Citations
“…In such cases, a crowd-sensing approach is often used, which involves collecting data about the qualities of path while target user participants (wheelchair users etc.) travel along the routes [51], [52]. While it had previously been difficult to implement routing systems based on such qualities in scale due to the effort required by participants, recent improvements in machine learning have led to the development of techniques which allow various accessibility and safety qualities to be inferred automatically from public data sets (such as identifying zebra-crossings from satellite images [83], [84]) or with less effort by participants (such as a passive crowdsensing approach proposed by Kamaldin et al [85] which automatically detects surface type conditions for wheelchair users or the Moving Wheels [86] which automatically detects obstacles such as steps or ramps from crowd-sourced wheelchair users).…”
Section: Discussionmentioning
confidence: 99%
“…For example, if the navigation system aims to recommend safe routes, the authors could test whether crime has indeed occurred on the recommended routes by referring to past crime statistics. In other studies, the authors themselves manually evaluated routes generated by the system to see if the objective of their proposed algorithm was met [10], [37], [52] (for example, to see if the generated routes have indeed reduced heat exposure in comparison to the shortest path [37] or to determine whether the trade off in terms of safety is worth the added distance [10]). Alternatively, simulations could be carried out in which agents with pre-programmed sets of behaviours are used to evaluate the quality of the routes [43].…”
Section: Evaluation Of Route Navigation Systemsmentioning
confidence: 99%
See 1 more Smart Citation
“…Most research has focused on whether there are accessible routes for wheelchair users [51]. Navigation models [52] or methods to classify accessible or inaccessible surfaces (built or natural) [53] have been developed. Computational methods have also been developed that compile datasets from different sources to provide users with personalized and accessible pedestrian routes and maps [54].…”
Section: Introductionmentioning
confidence: 99%