Limits...
Radar Sensing for Intelligent Vehicles in Urban Environments.

Reina G, Johnson D, Underwood J - Sensors (Basel) (2015)

Bottom Line: Radar overcomes the shortcomings of laser, stereovision, and sonar because it can operate successfully in dusty, foggy, blizzard-blinding, and poorly lit scenarios.This paper presents a novel method for ground and obstacle segmentation based on radar sensing.The algorithm operates directly in the sensor frame, without the need for a separate synchronised navigation source, calibration parameters describing the location of the radar in the vehicle frame, or the geometric restrictions made in the previous main method in the field.

View Article: PubMed Central - PubMed

Affiliation: Department of Engineering for Innovation, University of Salento, via Arnesano, 73100 Lecce, Italy. giulio.reina@unisalento.it.

ABSTRACT
Radar overcomes the shortcomings of laser, stereovision, and sonar because it can operate successfully in dusty, foggy, blizzard-blinding, and poorly lit scenarios. This paper presents a novel method for ground and obstacle segmentation based on radar sensing. The algorithm operates directly in the sensor frame, without the need for a separate synchronised navigation source, calibration parameters describing the location of the radar in the vehicle frame, or the geometric restrictions made in the previous main method in the field. Experimental results are presented in various urban scenarios to validate this approach, showing its potential applicability for advanced driving assistance systems and autonomous vehicle operations.

No MeSH data available.


Example of good fit (SE = 94.0 dB2) (a), and poor fit (SE = 913.1 dB2) (b). Black: radar observation. Grey: Radar-Centric Ground Detection (RCGD) ground echo model.
© Copyright Policy
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC4507681&req=5

f6-sensors-15-14661: Example of good fit (SE = 94.0 dB2) (a), and poor fit (SE = 913.1 dB2) (b). Black: radar observation. Grey: Radar-Centric Ground Detection (RCGD) ground echo model.

Mentions: The idea is that a good fit (i.e., low SE) between the RCGD model and experimental data indicates high likelihood of ground, whereas a poor fit (i.e., high SE) indicates low confidence in ground. Two sample results are plotted in Figure 6. Specifically, in Figure 6a, the model matches the experimental data very well, thus attesting to the presence of ground. Conversely, Figure 6b shows an example where the SE is high; in this case a low confidence in ground echo is associated with the given observation. In practice, a threshold SEth is determined by inspection, and the observation j is labeled as ground if SE(j) exceeds SEth.


Radar Sensing for Intelligent Vehicles in Urban Environments.

Reina G, Johnson D, Underwood J - Sensors (Basel) (2015)

Example of good fit (SE = 94.0 dB2) (a), and poor fit (SE = 913.1 dB2) (b). Black: radar observation. Grey: Radar-Centric Ground Detection (RCGD) ground echo model.
© Copyright Policy
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC4507681&req=5

f6-sensors-15-14661: Example of good fit (SE = 94.0 dB2) (a), and poor fit (SE = 913.1 dB2) (b). Black: radar observation. Grey: Radar-Centric Ground Detection (RCGD) ground echo model.
Mentions: The idea is that a good fit (i.e., low SE) between the RCGD model and experimental data indicates high likelihood of ground, whereas a poor fit (i.e., high SE) indicates low confidence in ground. Two sample results are plotted in Figure 6. Specifically, in Figure 6a, the model matches the experimental data very well, thus attesting to the presence of ground. Conversely, Figure 6b shows an example where the SE is high; in this case a low confidence in ground echo is associated with the given observation. In practice, a threshold SEth is determined by inspection, and the observation j is labeled as ground if SE(j) exceeds SEth.

Bottom Line: Radar overcomes the shortcomings of laser, stereovision, and sonar because it can operate successfully in dusty, foggy, blizzard-blinding, and poorly lit scenarios.This paper presents a novel method for ground and obstacle segmentation based on radar sensing.The algorithm operates directly in the sensor frame, without the need for a separate synchronised navigation source, calibration parameters describing the location of the radar in the vehicle frame, or the geometric restrictions made in the previous main method in the field.

View Article: PubMed Central - PubMed

Affiliation: Department of Engineering for Innovation, University of Salento, via Arnesano, 73100 Lecce, Italy. giulio.reina@unisalento.it.

ABSTRACT
Radar overcomes the shortcomings of laser, stereovision, and sonar because it can operate successfully in dusty, foggy, blizzard-blinding, and poorly lit scenarios. This paper presents a novel method for ground and obstacle segmentation based on radar sensing. The algorithm operates directly in the sensor frame, without the need for a separate synchronised navigation source, calibration parameters describing the location of the radar in the vehicle frame, or the geometric restrictions made in the previous main method in the field. Experimental results are presented in various urban scenarios to validate this approach, showing its potential applicability for advanced driving assistance systems and autonomous vehicle operations.

No MeSH data available.