Noise determination method and device, computer equipment and storage medium
A noise and equipment technology, applied in the field of multi-sensor fusion, can solve the problems of inability to accurately detect abnormal data in measurement data, limited algorithm running speed, and inaccuracy.
Pending Publication Date: 2022-07-29
SHANGHAI SENSETIME LINGANG INTELLIGENT TECH CO LTD
View PDF0 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Online estimation of the noise of the current measurement data requires the use of historical measurement data. For example, the noise of the current measurement data is the average value of the historical measurement error data. However, the calculated noise of the current measurement data has a time delay and is not accurate enough. Therefore, , unable to accurately detect abnormal data in the measurement data, reducing the sensor fusion results
[0004] Offline noise estimation can store the sample measurement data and the measurement error data corresponding to the sample measurement data offline in a k-dimensional tree (kd-tree). When running the algorithm online, the measurement data of each sensor will be obtained from kd- Find the k nearest sample measurement data and the corresponding sample error data in the tree, and use the sample error data to estimate the noise. However, this type of algorithm often requires a large memory space to store a large number of offline sample measurement data and the corresponding sample measurement data. Measuring error data, resulting in limited algorithm running speed and reducing the efficiency of noise estimation
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0097] In order to make the purposes, technical solutions and advantages of the embodiments of the present disclosure more clear, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present disclosure. Obviously, the described embodiments are only These are some, but not all, embodiments of the present disclosure. The components of the disclosed embodiments generally described and illustrated in the drawings herein may be arranged and designed in a variety of different configurations. Therefore, the following detailed description of the embodiments of the disclosure provided in the accompanying drawings is not intended to limit the scope of the disclosure as claimed, but is merely representative of selected embodiments of the disclosure. Based on the embodiments of the present disclosure, all other embodiments obtained by those skilled in the ar...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention provides a noise determination method and device, computer equipment and a storage medium, and the method comprises the steps: obtaining measurement data collected by preset equipment, and a pre-constructed decision tree model; the decision tree model comprises a plurality of internal nodes, optimal segmentation information corresponding to each internal node, a plurality of leaf nodes and noise parameter information corresponding to each leaf node; determining a target leaf node corresponding to the measurement data based on the optimal segmentation information corresponding to each internal node; and determining target noise information of the measurement data based on the noise parameter information corresponding to the target leaf node.
Description
technical field [0001] The present disclosure relates to the technical field of multi-sensor fusion, and in particular, to a noise determination method, apparatus, computer equipment and storage medium. Background technique [0002] Multi-sensor fusion is an essential part of autonomous vehicles for robust perception in complex scenes. However, the measurement data of sensors often carry noise, and the influence of noise will cause abnormality in the measurement data. Usually, noise can be used to find abnormal data in the measurement data. Therefore, by accurately estimating the noise, abnormal data in the measurement data can be accurately found, thereby improving the multi-sensor fusion results. [0003] The existing noise estimation methods are mainly divided into two categories, namely online noise estimation and offline noise estimation. Among them, the online noise estimation can use the adaptive Kalman filter algorithm to estimate the noise of the measurement data ...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Applications(China)
IPC IPC(8): G06K9/00G06K9/62
CPCG06F2218/04G06F18/251
Inventor 马全盟张世权蒋沁宏石建萍
Owner SHANGHAI SENSETIME LINGANG INTELLIGENT TECH CO LTD