Target detection method and system based on millimeter wave radar and video fusion

Abstract

The invention provides a target detection method and system based on millimeter-wave radar and video fusion, and the method comprises the steps: firstly filtering invalid targets obtained by the millimeter-wave radar and a camera, and reducing the target detection range; under the condition that spatial synchronization of the millimeter-wave radar and the camera is ensured, target matching of detection results of the millimeter-wave radar and the camera is carried out; and calculating a target detection intersection-union ratio, judging the accuracy of target matching according to the target detection intersection-union ratio, and further performing second target matching by adopting a global nearest neighbor data association algorithm under the condition that the recognition accuracy cannot be judged, thereby realizing target matching of detection objects of the millimeter wave radar and the camera as many as possible. The missed detection rate of the target object can be reduced, and the accuracy of identification matching is ensured at the same time.

Description

technical field [0001] The invention relates to the technical field of target detection, in particular to a target detection method and system based on millimeter wave radar and video fusion. Background technique [0002] At present, the environmental perception devices used in smart transportation mainly include cameras and millimeter-wave radars. Millimeter-wave radar has the ability to detect target distance, speed, azimuth angle, etc., and at the same time quantitatively tests the target reflection ability at a specific incident angle, and estimates the target size from the echo scattering characteristics of millimeter-wave radar. [0003] Cameras often use multi-sensors for information fusion, and use multi-sensor information fusion technology to realize the complementary advantages of each sensor, and collect the color, size, size, projection outline and other dimensional information of the target accurately to the greatest extent, and improve the comprehensiveness and...

AI Technical Summary

Problems solved by technology

[0005] In order to solve the above technical problems, this application proposes a target detection method and system based on millimeter-wave radar and video fusion. First, the invalid targets acquired by the millimeter-wave radar and camera are filtered to narrow the range of detection targets; In the case of camera space synchronization, the target matching of the millimeter-wave radar and camera detection results is performed; the target detection intersection ratio is calculated, and the accuracy of the target matching is judged according to the target detection intersection ratio. For the situation where the recognition accuracy cannot be judged, further use The global nearest neighbor data association algorithm performs the second target matching, so as to achieve as many target matching as possible between the detection objects of the millimeter-wave radar and the camera, which helps to reduce the missed detection rate of target objects, and at the same time ensures the accuracy of recognition and matching

Images