Automatic driving data identification method and device, computer equipment and storage medium
A technology for automatic driving and data recognition, applied in the field of computer equipment and storage media, devices, and data recognition methods for automatic driving, can solve the problems of low efficiency and high cost of long-tail data, improve efficiency, ensure accuracy, and reduce costs. Effect
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0032] figure 1 It is a flow chart of an automatic driving data recognition method provided by Embodiment 1 of the present invention. This embodiment can be applied to the situation of using the teacher network and the student network to mine the long tail data of automatic driving. This method can be obtained from the automatic driving data The automatic driving data identification device can be implemented by software and / or hardware, and can be configured in a computer device, such as a server, a personal computer, etc., and specifically includes the following steps:
[0033] Step 101. Obtain raw data collected during automatic driving.
[0034] The vehicle in this embodiment can support automatic driving. The so-called automatic driving can refer to the ability of the vehicle itself to perceive the environment, plan the path and realize the vehicle control autonomously, that is, to use electronic technology to control the vehicle for humanoid driving.
[0035] According t...
Embodiment 2
[0117] image 3 It is a flowchart of a data recognition method for automatic driving provided by Embodiment 2 of the present invention. This embodiment is based on the foregoing embodiments, and further increases the operation of using long-tail data to train the student network. The method specifically includes the following steps:
[0118] Step 301. Obtain raw data collected during automatic driving.
[0119] Step 302, respectively determine the student network and the teacher network suitable for automatic driving.
[0120] Step 303 , calculating the difference between the student network and the teacher network in predicting the original data as the distribution difference.
[0121] Step 304: Identify the original data belonging to the long-tail data for automatic driving according to the distribution difference as the target data.
[0122] Step 305, labeling the target data.
[0123] In this embodiment, for the target data belonging to the long-tail data, it can be lab...
Embodiment 3
[0137] Figure 4 The structural block diagram of an automatic driving data recognition device provided in Embodiment 3 of the present invention may specifically include the following modules:
[0138] Raw data acquisition module 401, configured to acquire raw data collected during automatic driving;
[0139] A network determination module 402, configured to respectively determine a student network and a teacher network suitable for the automatic driving;
[0140] A distribution difference calculation module 403, configured to calculate the difference between the student network and the teacher network for predicting the original data as a distribution difference;
[0141] The original data identification module 404 is configured to identify the original data belonging to the long-tail data for the automatic driving as target data according to the distribution difference.
[0142] In one embodiment of the present invention, the network determination module 402 includes:
[0...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 


