Research of Dynamic Weighing System Based on Multi-Sensor Data Fusion Technology

2013 ◽  
Vol 721 ◽  
pp. 479-482 ◽  
Author(s):  
Yan Xia Wang ◽  
Chun Hui Bao ◽  
Chun Ling Fan
Keyword(s):  
Data Fusion ◽  
Electromagnetic Interference ◽  
New Method ◽  
Sensor Data ◽  
Fusion Technology ◽  
Sensor Data Fusion ◽  
Multi Sensor Data Fusion ◽  
Load Cells ◽  
Noise Vibration ◽  
Dynamic Weighing

The multi-sensor data fusion techniques is discussed in dynamic weighing system based on the data measured from ultrasonic sensors, speed sensors, capacitive sensors and load cells. This new method can greatly increase the measure precision of the dynamic weighing systems, at the same time it can effectively reduce noise, vibration, electromagnetic interference and other environmental factors on the influence of dynamic weighing system measurement. Judging from the simulation result, this new method proves to be more accurate and stable than ordinary processing methods.

scholarly journals One-Stage Multi-Sensor Data Fusion Convolutional Neural Network for 3D Object Detection

Sensors ◽  
2019 ◽  
Vol 19 (6) ◽  
pp. 1434 ◽  
Author(s):  
Minle Li ◽  
Yihua Hu ◽  
Nanxiang Zhao ◽  
Qishu Qian
Keyword(s):  
Neural Network ◽  
Feature Extraction ◽  
Data Fusion ◽  
Object Detection ◽  
Sensor Data ◽  
3D Object ◽  
Sensor Data Fusion ◽  
One Stage ◽  
Multi Sensor Data Fusion ◽  
3D Object Detection

Three-dimensional (3D) object detection has important applications in robotics, automatic loading, automatic driving and other scenarios. With the improvement of devices, people can collect multi-sensor/multimodal data from a variety of sensors such as Lidar and cameras. In order to make full use of various information advantages and improve the performance of object detection, we proposed a Complex-Retina network, a convolution neural network for 3D object detection based on multi-sensor data fusion. Firstly, a unified architecture with two feature extraction networks was designed, and the feature extraction of point clouds and images from different sensors realized synchronously. Then, we set a series of 3D anchors and projected them to the feature maps, which were cropped into 2D anchors with the same size and fused together. Finally, the object classification and 3D bounding box regression were carried out on the multipath of fully connected layers. The proposed network is a one-stage convolution neural network, which achieves the balance between the accuracy and speed of object detection. The experiments on KITTI datasets show that the proposed network is superior to the contrast algorithms in average precision (AP) and time consumption, which shows the effectiveness of the proposed network.

Study on Leak Detecting System for Oil Pipeline Based on Multi-Sensor Data Fusion Technique

2012 ◽  
Vol 220-223 ◽  
pp. 1898-1901
Author(s):  
Jie Zhang ◽  
Xiao Wang ◽  
Zhen Zhao
Keyword(s):  
Wavelet Transform ◽  
Data Fusion ◽  
Real Time ◽  
Sensor Data ◽  
Time Signal ◽  
Fusion Technology ◽  
Transform Method ◽  
Oil Pipeline ◽  
Sensor Data Fusion ◽  
Multi Sensor Data Fusion

In this paper, based on the wavelet transform method, the multi-sensor data fusion technology is adopted to solve some key problems in pipeline leak detection system. Compared with the traditional filtering method, the wavelet transform method can better remove the pipeline leakage signal noise. When the corresponding wavelet is selected, after FPGA realized, the method has the advantages of fast speed, arbitrarily data width set, which can better meet the needs of real-time signal processing requirements of pipeline leak. At the same time, VHDL language has the characteristics of portability, greater generality. When multi-sensor fusion technology is used in the paper, the relation, correlation, estimation and integrated processing is done in turn to the information from multiple data sources, the system can achieve better detection performance than a system using the single sensor, so as to form a more complete, reliable pipeline real time detecting conclusion.

Sign in / Sign up

Export Citation Format

Share Document