Tracking of Extended Objects with High-Resolution Doppler Radar

Kellner, Dominik; Barjenbruch, Michael; Klappstein, Jens; Dickmann, Jürgen; Dietmayer, Klaus

doi:10.1109/tits.2015.2501759

Cited by 58 publications

(25 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Yet, the entire procedure introduces a local search for best fitting extent and allows an easy adaption of each particle's extent estimate. 8…”

Section: Estimating the Single Object Densitiesmentioning

confidence: 99%

“…Several of such approaches have been proposed for radar-based tracking. These include clustering and extraction of reference points as in [1], [2], or fitting bounding boxes and L-shapes [3], [4], reflection center models [5], or velocity profiles [6]- [8] to the data. While preprocessing routines are oftentimes effective, computationally fast, and lead to clearly separable system architectures, they face difficulties if the data from a single time step is ambiguous and the correct meta-measurement cannot be easily extracted.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Tracking Multiple Vehicles Using a Variational Radar Model

Scheel

Dietmayer

2019

IEEE Trans. Intell. Transport. Syst.

Self Cite

View full text Add to dashboard Cite

High-resolution radar sensors are able to resolve multiple detections per object and therefore provide valuable information for vehicle environment perception. For instance, multiple detections allow to infer the size of an object or to more precisely measure the object's motion. Yet, the increased amount of data raises the demands on tracking modules: measurement models that are able to process multiple detections for an object are necessary and measurement-to-object associations become more complex. This paper presents a new variational radar model for tracking vehicles using radar detections and demonstrates how this model can be incorporated into a Random-Finite-Setbased multi-object filter. The measurement model is learned from actual data using variational Gaussian mixtures and avoids excessive manual engineering. In combination with the multiobject tracker, the entire process chain from the raw measurements to the resulting tracks is formulated probabilistically. The presented approach is evaluated on experimental data and it is demonstrated that the data-driven measurement model outperforms a manually designed model.

show abstract

“…Yet, the entire procedure introduces a local search for best fitting extent and allows an easy adaption of each particle's extent estimate. 8…”

Section: Estimating the Single Object Densitiesmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Tracking Multiple Vehicles Using a Variational Radar Model

Scheel

Dietmayer

2019

IEEE Trans. Intell. Transport. Syst.

Self Cite

View full text Add to dashboard Cite

show abstract

“…Using the orientation it is possible to detect lane changes faster than with a conventional tracking filter, as the filter usually needs several steps to predict the motion correctly. With two radar sensors it is even possible to estimate the complete motion state, for example the orientation and the movement vector including the yaw rate of a target vehicle [17].…”

Section: Estimation Of Target Vehiclesmentioning

confidence: 99%

Radar Sensors for Autonomous Driving: Modulation Schemes and Interference Mitigation

Roos¹,

Bechter²,

Knill³

et al. 2019

IEEE Microwave

134

View full text Add to dashboard Cite

“…We elaborate a list containing 64 SFs for PTW application from available safety systems/technologies and conceptual ones (Appendix C). The review explored the automotive market, specialized literature in vehicular safety (Bayly et al, 2006;Anderson et al, 2011;Savino et al, 2012;Van Elslande et al, 2012;Savino et al, 2014Savino et al, , 2016Corno et al, 2008;Gail, 2009), inertial sensors (Corke et al, 2007), PTW safety technologies (Montanari et al, 2011;Garcia et al, 2013;Corno et al, 2015;Mukhtar et al, 2015), and how remote sensing for scene understanding (Mukhtar et al, 2015) could be beneficial, mainly based in stereo vision (Suganuma and Fujiwara, 2007;Barth et al, 2009;Rovira-Más et al, 2009;Pfeiffer and Franke, 2011), LIDAR (Homm et al, 2011;Navarro et al, 2016) and RADAR (Schneider, 2005;Andres et al, 2012;Kellner et al, 2016). Finally, we ensure that the safety solutions evaluated in the PISa project all fit at least in one of the SFs of our broader list.…”

Section: List Of Safety Functionsmentioning

confidence: 99%

Are automatic systems the future of motorcycle safety? A novel methodology to prioritize potential safety solutions based on their projected effectiveness

Gil

Savino

Piantini

et al. 2017

Traffic Injury Prevention

View full text Add to dashboard Cite

Current results revealed that automatic systems have the greatest potential to improve motorcycle safety. Accumulating and encoding expertise in crash analysis from a range of disciplines into a scalable and reusable analytical tool, as proposed with the use of KBMS, has the potential to guide research and development of effective safety systems. As the expert assessment of the crash scenarios is decoupled from the regional crash database, the expert assessment may be reutilized, thereby allowing rapid reanalysis when new crash data become available. In addition, the KBMS methodology has potential application to injury forecasting, driver/rider training strategies, and redesign of existing road infrastructure.

show abstract

Tracking of Extended Objects with High-Resolution Doppler Radar

Cited by 58 publications

References 13 publications

Tracking Multiple Vehicles Using a Variational Radar Model

Tracking Multiple Vehicles Using a Variational Radar Model

Radar Sensors for Autonomous Driving: Modulation Schemes and Interference Mitigation

Are automatic systems the future of motorcycle safety? A novel methodology to prioritize potential safety solutions based on their projected effectiveness

Contact Info

Product

Resources

About