2014 IEEE/RSJ International Conference on Intelligent Robots and Systems 2014
DOI: 10.1109/iros.2014.6942558
|View full text |Cite
|
Sign up to set email alerts
|

Visual localization within LIDAR maps for automated urban driving

Abstract: Abstract-This paper reports on the problem of map-based visual localization in urban environments for autonomous vehicles. Self-driving cars have become a reality on roadways and are going to be a consumer product in the near future. One of the most significant road-blocks to autonomous vehicles is the prohibitive cost of the sensor suites necessary for localization. The most common sensor on these platforms, a three-dimensional (3D) light detection and ranging (LIDAR) scanner, generates dense point clouds wit… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

2
163
0

Year Published

2016
2016
2020
2020

Publication Types

Select...
8
2

Relationship

0
10

Authors

Journals

citations
Cited by 324 publications
(165 citation statements)
references
References 21 publications
(26 reference statements)
2
163
0
Order By: Relevance
“…Of course, this aspect is also tightly linked to the cost of those sensors. An interesting perspective in that sense is multi-modality where a map could be built by an expensive 3D laser but then exploited by a simple camera as proposed in [273]. Another interesting challenge is to build flexible architectures in which a decision system can choose what are the sensors, detectors or maps to favor depending on the context.…”
Section: Discussionmentioning
confidence: 99%
“…Of course, this aspect is also tightly linked to the cost of those sensors. An interesting perspective in that sense is multi-modality where a map could be built by an expensive 3D laser but then exploited by a simple camera as proposed in [273]. Another interesting challenge is to build flexible architectures in which a decision system can choose what are the sensors, detectors or maps to favor depending on the context.…”
Section: Discussionmentioning
confidence: 99%
“…This evaluation method is used due to the accuracy of laser sensors. Research in [21,22,23] introduced the use of laser scanning to solve the problem of visual localization within LiDAR maps, extraction of road markings and lane detection respectively. To this end, Table 3 shows the computed RMSE value between the laser and camera.…”
Section: Methodsmentioning
confidence: 99%
“…To help aid the SA process, FA car prototypes currently under development typically use detailed databases of the road environment to reduce the need for and guide the perception 13 . Far awareness, at least awareness of what static features to expect, is largely obtained from stored data.…”
Section: B Maneuver Loop Comparisonmentioning
confidence: 99%