Effective World Modeling: Multisensor Data Fusion Methodology for Automated Driving

Elfring, Jos; Appeldoorn, Rpw Rein; Dries, S Sjoerd van den; Kwakkernaat, Mrjae Maurice

doi:10.3390/s16101668

Cited by 33 publications

(21 citation statements)

References 57 publications

(81 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the autonomous car industry MDF is standard -it already started in the 1980 with work by Dickmans (2007) on the than much less powerful computer than todays systems (e.g. Bertozzi et al, 2000;Elfring et al, 2016). The author forecast that in less than 15 years from now we will have AI-ML models which will generate geomorphometric parameters at various scales autonomously.…”

Section: Futurementioning

confidence: 99%

Geomorphometry-10 years after the book-challenges ahead ?

Reuter

2018

Preprint

View full text Add to dashboard Cite

In 2008 the Geomorphometry book was published after several years of work on it. 10 years have passed since the book has been published, many more years since the early work of the grandfathers of this domain. One of the key definition in the book was the following: Geomorphometry is the science of digital terrain modelling, analysis and quantitative land surface analysis.The author argues that this definition still holds true. The paper discusses past developments and future questions and argues that we need to move to a predicted space-time geomorphomerty parameters based approach.

show abstract

Section: Futurementioning

confidence: 99%

Geomorphometry-10 years after the book-challenges ahead ?

Reuter

2018

Preprint

View full text Add to dashboard Cite

show abstract

“…High quality measurements can be obtained using expensive sensors (Elfring et al, 2016), as installed in the well-known Google Car. This vehicle includes an advanced laser range finder, between other sensors, able to process the environment real time (Poczter and Jankovic, 2014).…”

Section: Introductionmentioning

confidence: 99%

Neural Network Based Uncertainty Prediction for Autonomous Vehicle Application

Zhang

Martínez²,

Clarke³

et al. 2019

Front. Neurorobot.

View full text Add to dashboard Cite

This paper proposes a framework for uncertainty prediction in complex fusion networks, where signals become available sporadically. Assuming there is no information of the sensor characteristics available, a surrogated model of the sensor uncertainty is yielded directly from data through artificial neural networks. The strategy developed is applied to autonomous vehicle localization through odometry sensors (speed and orientation), so as to determine the location uncertainty in the trajectory. The results obtained allow for fusion of autonomous vehicle location measurements, and effective correction of the accumulated odometry error in most scenarios. The neural networks applicability and generalization capacity are proven, evidencing the suitability of the presented methodology for uncertainty estimation in non-linear and intractable processes.

show abstract

“…Recently, these areas have shown an active development towards unmanned transportation solutions (Car autonomy SAE Level 4). In this context, perception is a critical task since it provides meaningful, complete and reliable information about the vehicle surroundings [1,2]. Several studies have demonstrated that vision perception is an essential sensing method for scene analysis [3,4,5].…”

Section: Introductionmentioning

confidence: 99%

Track-Before-Detect Framework-Based Vehicle Monocular Vision Sensors

Gonzalez

Rodríguez

Elouardi

2019

Sensors

View full text Add to dashboard Cite

This paper proposes a Track-before-Detect framework for a multibody motion segmentation (named TbD-SfM). Our contribution relies on a tightly coupled tracking before detection strategy intended to reduce the complexity of existing Multibody Structure from Motion approaches. Efforts were done towards an algorithm variant closer and aimed to a further embedded implementation for dynamic scene analysis while enhancing processing time performances. This generic motion segmentation approach can be transposed to several transportation sensor systems since no constraints are considered on segmented motions (6-DOF model). The tracking scheme is analyzed and its performance is evaluated under thorough experimental conditions including full-scale driving scenarios from known and available datasets. Results on challenging scenarios including the presence of multiple and simultaneous moving objects observed from a moving camera are reported and discussed.

show abstract

Effective World Modeling: Multisensor Data Fusion Methodology for Automated Driving

Cited by 33 publications

References 57 publications

Geomorphometry-10 years after the book-challenges ahead ?

Geomorphometry-10 years after the book-challenges ahead ?

Neural Network Based Uncertainty Prediction for Autonomous Vehicle Application

Track-Before-Detect Framework-Based Vehicle Monocular Vision Sensors

Contact Info

Product

Resources

About