Multi-sensor based data fusion method, device and storage medium
A data fusion and multi-sensor technology, applied in the computer field, can solve problems such as poor data fusion effect, inability to adaptively adapt to the current scene, fixed weights, etc.
Active Publication Date: 2021-04-27
知行汽车科技(苏州)股份有限公司
View PDF4 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0005] This application provides a data fusion method, device, and storage medium based on multi-sensors, which can solve the problem that when performing feature fusion based on multi-sensor data, the weight corresponding to each sensor is fixed and cannot adaptively adapt to the current scene, resulting in data Problems with poor fusion
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
[0042] The specific implementations of the present application will be described in further detail below with reference to the accompanying drawings and embodiments. The following examples are used to illustrate the present application, but are not intended to limit the scope of the present application.
[0043] First, some terms involved in this application are introduced.
[0044] Feature Extraction: It is a process of finding the most effective features (invariance of similar samples, discrimination of different samples, robustness to noise) from the original features.
[0045] Neural Network: It is an algorithmic mathematical model that imitates the behavioral characteristics of animal neural networks and performs distributed parallel information processing.
[0046] Feature level fusion (Feature Level Fusion): refers to the multi-source heterogeneous sensors to extract their own features, and generate new features through a certain method to make the new features more ef...
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 present application relates to a data fusion method, device and storage medium based on multi-sensors, which belongs to the field of computer technology. The method includes: acquiring sensor data of the same detection range collected by n sensors respectively; Perform feature extraction to obtain the feature map corresponding to each sensor; determine the channel weight of each image channel in the target image area in each feature map; update the channel information of the feature map according to the channel weight to obtain the updated feature map; for each The target image area in the updated feature map corresponding to the sensor, determine the area weight of the target image area in the updated feature map; merge the target image areas in each updated feature map according to the area weight, and obtain the fused feature Figure; can solve the problem of poor data fusion effect of the existing multi-sensor based data fusion method; can improve the data fusion effect.
Description
technical field [0001] The present application relates to a multi-sensor-based data fusion method, device and storage medium, belonging to the technical field of computers. Background technique [0002] With the development of autonomous driving technology, vehicles currently have environmental perception functions, such as target detection and target recognition. The environment perception function of the vehicle is realized by the sensors installed on the vehicle. Usually, there are many types of sensors on a vehicle, so when performing environmental perception, it is necessary to perform data fusion on the data collected by a variety of sensors. [0003] At present, the data fusion methods for data collected by various sensors include: extracting features from the data collected by each sensor; then, combining each feature extraction result according to a fixed weight. Alternatively, feature extraction is performed on the data collected by each sensor; then, each featur...
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 Patents(China)
IPC IPC(8): G06K9/00G06K9/62
CPCG06V20/56G06F18/253
Inventor 陈伟
Owner 知行汽车科技(苏州)股份有限公司