| 摘要 |
PROBLEM TO BE SOLVED: To improve object detection accuracy by efficiently overlapping a sensing function of a radar device and a sensing function of a camera device.SOLUTION: A capture region calculation part 32 calculates a capture point, which is a maximum point of reflection intensity, from electric power profile information to obtain a capture region surrounding the capture point. An edge calculation part 34 obtains edges of at least one object from image data. A marker calculation part 35 obtains a marker from the capture region. A component region calculation part 36 uses the edges to extend the marker so as to obtain component regions. A grouping processing part 37 groups the component region belonging to the same object, among the component regions. An object determination part 38 determines a type (for example, large vehicle, small vehicle, two-wheel barrow, pedestrian, flying body, bird, etc.) of the at least one object on the basis of an object region, which is a result of the grouping.SELECTED DRAWING: Figure 3 |
