Authors:
Mingkang Li
1
;
Zhaofei Feng
2
;
Martin Stolz
2
;
Martin Kunert
2
;
Roman Henze
3
and
Ferit Küçükay
3
Affiliations:
1
Advanced Engineering Sensor Systems, Robert Bosch GmbH and Technische Universität Braunschweig, Germany
;
2
Advanced Engineering Sensor Systems and Robert Bosch GmbH, Germany
;
3
Technische Universität Braunschweig, Germany
Keyword(s):
Automotive Radar Sensor, Environmental Perception, Occupancy Grid, Free Space Detection, Imaging
Radar.
Abstract:
The high-resolution radar sensors have the ability to detect thousands of reflection points per cycle, which
promotes the perception capability on a pixel level similar to video systems. In this paper, an occupancy
grid map is created to model the static environment. The reflection amplitudes of all detection points are
compensated, normalized, and then converted to the detection probability based on a radar sensor model.
According to the movement of the ego vehicle, the a posteriori occupancy probability is computed to build
the occupancy grid map. Thereafter the occupancy grid map is converted to the binary grid map, where the
grids in the obstacle areas are defined as occupied. In order to eliminate the outliers, the connected occupied
grids are clustered using the Connected-Component Labelling algorithm. Through the Moore-Neighbour
Tracing algorithm the boundaries of the clustered occupied grids are recognized. Based on the boundaries,
the interval-based free space detection is p
erformed using the Bresenham's line algorithm. As mentioned,
the occupancy grid map and the free space detection results obtained from radar road measurements match
with the real scenarios.
(More)