Vehicle target identification method and storage medium
A target recognition and vehicle technology, applied in the field of data processing, can solve the problems of reduced recognition accuracy and inability to provide 3D geometric information, and achieve the effects of ensuring accuracy, reducing data processing volume, and reducing quantity
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0050] It should be noted that, in the coordinate system of this embodiment, the forward direction of the scanner is taken as the X-axis, and the elevation direction is taken as the Z-axis.
[0051] Such as figure 1 As shown, a vehicle target recognition method includes:
[0052] Step 1: Build a feature database, use the feature database to train the support vector machine model, and obtain a classification model; wherein, the feature vectors in the feature database include global features, position features, eigenvalue features, and multi-view projection features.
[0053] The global feature is used to describe the shape, geometric size and other attributes of the entire independent ground object. For vehicles, its geometric shape features are obviously different from other ground objects, and its global feature design includes length L, width W, and height H features and the ratio between length, width, and height, volume, relative density, minimum height, and height diffe...
Embodiment 2
[0088] The difference from Embodiment 1 is that in this embodiment, in step 3 of the vehicle target recognition method, when the point cloud data is scanned repeatedly and the overlap between the front and rear frames is higher than the preset threshold, the offline frame point cloud can be automatically selected. The processing method is calculated; when the overlapping degree of the front and rear frames is lower than the set threshold, this scheme automatically determines that it is real-time frame data; when switching between the implementation frame and the offline frame, the overlapping area is automatically calculated to avoid repeated identification of the overlapping area.
[0089] Through such settings, the application can automatically distinguish real-time frames from offline frames. If the driving speed is slow, such as traffic jams, etc., the point cloud data is scanned repeatedly, and the overlap between the front and rear frames is higher than the set threshold,...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 
