Data fusion for environmental model generation

1 . A method for fusion of radar and visual information, the method comprises:

obtaining visual information and radar information about a three dimensional (3D) space located within a field of view of a camera that acquired the visual information and within a field of view of a radar that acquired the radar information;

finding, following the obtaining and based on the visual information, estimated visual-detection-based (VDB) objects and estimated VDB locations of the estimated VDB objects within the 3D space; wherein the finding of the estimated VDB locations exhibits a distance inaccuracy that are represented by a distance ambiguity that is either a certain percent of the distance inaccuracy or certain amount of distance;

determining, following the obtaining, hybrid-detection-based (HDB) objects and HDB locations of the HDB objects, based on (i) the radar information, (ii) the estimated VDB objects, and (iii) the estimated VDB locations of the VDB objects, wherein determining the HDB objects and HDB locations comprises solving the distance ambiguity of the estimated VDB locations using the radar information by searching for radar-detection-based (RDB) objects within regions of interest defined by the estimated VDB locations and the distance ambiguity of the estimated VDB locations; wherein the distance ambiguity is a range inaccuracy associated with estimation of locations that are based solely estimated VDB locations.

2 . The method according to claim 1 , further comprising displaying a radar angle to range (RAR) display and an image overlaid with radar points aggregated from multiple radar scans.

3 . The method according to claim 1 , further comprising displaying the regions of interest as spatial regions in the 3D space that extend radially from the camera along directions corresponding to the estimated VDB locations, with radial extents determined by the distance ambiguity.

4 . The method according to claim 1 wherein the determining of the HDB objects and the HDB locations of the HDB objects comprises finding radar-detection-based (RDB) objects.

5 . The method according to claim 4 comprising pairing RDB objects with VDB objects to provide the HDB objects and the HDB locations of the HDB objects.

6 . The method according to claim 4 wherein the finding of the RDB objects is preceded by aggregating radar points from different points of time within a time window.

7 . The method according to claim 4 wherein the finding of the RDB objects comprises aggregating radar points from different points of time within a time window.

8 . The method according to claim 1 comprising responding to the determining of the HDB objects.

9 . The method according to claim 8 wherein the responding comprises at least one of autonomously driving the vehicle based on the determining or performing an advanced driver assistance system (ADAS) operation.

10 . The method according to claim 2 further comprising displaying, within an enlarged RAR display, the regions of interest as spatial regions in the 3D space that extend radially from the camera along directions corresponding to the estimated VDB locations, with radial extents determined by the distance ambiguity.

11 . A non-transitory computer readable medium for fusion of radar and visual information, the non-transitory computer readable medium stores instructions for:

obtaining visual information and radar information about a three dimensional (3D) space located within a field of view of a camera that acquired the visual information and within a field of view of a radar that acquired the radar information;

finding, following the obtaining and based on the visual information, estimated visual-detection-based (VDB) objects and estimated VDB locations of the estimated VDB objects within the 3D space; wherein the finding of the estimated VDB locations exhibits a distance inaccuracy that are represented by a distance ambiguity that is either a certain percent of the distance inaccuracy or certain amount of distance; and

determining, following the obtaining, hybrid-detection-based (HDB) objects and HDB locations of the HDB objects, based on (i) the radar information, (ii) the estimated VDB objects, and (iii) the estimated VDB locations of the VDB objects, wherein determining the HDB objects and HDB locations comprises solving the distance ambiguity of the estimated VDB locations using the radar information by searching for radar-detection-based (RDB) objects within regions of interest defined by the estimated VDB locations and the distance ambiguity of the estimated VDB locations.

12 . The non-transitory computer readable medium according to claim 11 , that further stores instructions for displaying the regions of interest as spatial regions in the 3D space that extend radially from the camera along directions corresponding to the estimated VDB locations, with radial extents determined by the distance ambiguity.

13 . The non-transitory computer readable medium according to claim 11 wherein the determining of the HDB objects and the HDB locations of the HDB objects comprises searching for radar-detection-based (RDB) objects within regions of interest defined by the estimated VDB locations of the estimated VDB objects and the distance ambiguity of the estimated VDB locations of the VDB objects.

14 . The non-transitory computer readable medium according to claim 11 wherein the determining of the HDB objects and the HDB locations of the HDB objects comprises finding radar-detection-based (RDB) objects.

15 . The non-transitory computer readable medium according to claim 14 that stores instructions for pairing RDB objects with VDB objects to provide the HDB objects and the HDB locations of the HDB objects.

16 . The non-transitory computer readable medium according to claim 14 wherein the finding of the RDB objects is preceded by aggregating radar points from different points of time within a time window.

17 . The non-transitory computer readable medium according to claim 14 wherein the finding of the RDB objects comprises aggregating radar points from different points of time within a time window.

18 . The non-transitory computer readable medium according to claim 11 that stores instructions for responding to the determining of the HDB objects.

19 . The non-transitory computer readable medium according to claim 17 wherein the responding comprises autonomously driving the vehicle based on the determining.

20 . The non-transitory computer readable medium according to claim 17 wherein the responding comprises performing an advanced driver assistance system (ADAS) operation.

21 . A system for fusion of radar and visual information, the system comprises a visual sensor, a radar and a processor;

wherein the visual sensor is configured to acquire visual information about a three dimensional (3D) space;

wherein the radar is configured to acquire radar information about the 3D space;

wherein the processor is configured to find, based on the visual information, estimated visual-detection-based (VDB) objects and estimated VDB locations of the estimated VDB objects within the 3D space; wherein the finding of the estimated VDB locations exhibits a distance inaccuracy that are represented by a distance ambiguity that is either a certain percent of the distance inaccuracy or certain amount of distance; and

wherein the processor is configured to determine, following an acquiring of the visual information and of the radar information, hybrid-detection-based (HDB) objects and HDB locations of the HDB objects, based on (i) the radar information, (ii) the estimated VDB objects, and (iii) the estimated VDB locations of the VDB objects, wherein determining the HDB objects and HDB locations comprises solving the distance ambiguity of the estimated VDB locations using the radar information by searching for radar-detection-based (RDB) objects within regions of interest defined by the estimated VDB locations and the distance ambiguity of the estimated VDB locations.