Pedestrian distance detection method and device

Abstract

The invention discloses a pedestrian distance detection method and device. The method comprises the following steps: calculating a rectangle feature of a pedestrian image shot by a monocular camera, and training the rectangle feature to obtain multiple weak classifiers; combining the multiple weak classifiers into a strong classifier via a cascade algorithm; acquiring pixel coordinates of a pedestrian in the pedestrian image via the strong classifier; and calculating the distance between the monocular camera and the pedestrian according to the parameter of the monocular camera and the pixel coordinates of the pedestrian. The method can improve the instantaneity and robustness of pedestrian distance detection.

Description

Technical field [0001] The present invention relates to the technical field of intelligent vehicles, in particular to a method and device for detecting pedestrian distance. Background technique [0002] With the development of smart vehicle technology, modern vehicles are becoming more intelligent. During the driving of the vehicle, the vehicle can collect surrounding image information through machine vision, so that it can analyze the information that is helpful for driving based on the image information. For example, the user can be reminded or emergency braking can be performed directly according to the analyzed obstacle information to ensure driving safety. [0003] Most vehicles use monocular cameras to collect image information. If the distance between the vehicle and pedestrians can be analyzed from the image information collected by the monocular camera, it will undoubtedly greatly improve the safety of driving. [0004] At present, related technologies have been able to id...

AI Technical Summary

Problems solved by technology

However, the images of pedestrians collected by the monocular camera will be affected by the surrounding environment, and will have other elements such as traffic signs, license plates and buildings, and it is difficult to accurately distinguish pedestrians from such images in related technologies.

Moreover, the related technology has a slow recognition speed for pedestrians in the image, so the robustness and real-time performance of pedestrian distance detection are poor, and it is difficult to be applied to actual products.

Images