Method, device and electronic device for detecting stationary object

Abstract

The embodiment of the invention discloses a detection method, a device and an electronic device of a stationary object. The method comprises the following steps: acquiring point cloud data of a sceneand characteristic information of each data point in the point cloud data; connecting the data points in the point cloud data with triangulation network, the triangulation network model being generated, and the preset camera being used to photograph the triangulation network model, and the image being obtained; acquiring a first data point corresponding to each pixel point in the image, and obtaining a feature map of point cloud data according to the feature information of each first data point; the feature map being inputted into the classification model, and the data points corresponding tothe stationary objects in the point cloud data being obtained. That is, in this embodiment, by acquiring the feature map of the point cloud data of the scene and taking the feature map as the input ofthe classification model, the still object in the scene is accurately detected, and the generation accuracy of the still map is improved.

Description

technical field [0001] The embodiments of the present invention relate to the technical field of data processing, and in particular, to a detection method, device and electronic equipment for a stationary object. Background technique [0002] Static map is a way of expressing fixed objects in physical space, and it describes the static and constant objects in the scene. In the generation of static maps, not only moving dynamic objects should be eliminated, but also dynamic objects that are currently stationary but may change in a short period of time (for example, currently stationary cars, automatic vehicles, etc. ). According to actual data statistics, stationary cars account for more than 75% of all stationary objects. Therefore, whether stationary vehicles can be completely eliminated is one of the key elements to evaluate the quality of static maps, and it is also an important part of safe driving of unmanned vehicles. [0003] The existing method for detecting statio...

AI Technical Summary

Problems solved by technology

However, the existing Bounding Box detection method will regard the Bounding Box that is slightly larger or smaller than the vehicle as the correct identification, which will cause missed or false detections, resulting in the static map not being able to reflect the real world and poor accuracy

Images