Multi-Sensor Data Fusion Using Triangulation Method and K-Means Algorithm
- Resource Type
- Conference
- Authors
- Kaity, Sourav; Das, Lalatendu; Jana, Biswapati; Bharti, J S; Gupta, Shilpa; Matharia, Ajay
- Source
- 2023 3rd International Conference on Range Technology (ICORT) Range Technology (ICORT), 2023 3rd International Conference on. :1-6 Feb, 2023
- Subject
- Aerospace
Communication, Networking and Broadcast Technologies
Components, Circuits, Devices and Systems
Computing and Processing
Engineering Profession
Fields, Waves and Electromagnetics
Photonics and Electrooptics
Power, Energy and Industry Applications
Robotics and Control Systems
Signal Processing and Analysis
Target tracking
Data integration
Clustering algorithms
Position measurement
Object recognition
Electo-optic effects
Data Fusion
Triangulation
Target Tracking
Electro-Optical Sensor (EOS)
K-means Clustering
- Language
A combined group of items that have similar data sets is known as a cluster. The principal objective of data fusion is to combine several pieces of information to find out a more precise result. Generally, Electro-Optical Sensors(EOS) are used to find out the position of a flying object. A single sensor can only provide the direction of an object, therefore at least two sensors are required for the identification of the target location. Tracking information from various sensors is combined and calculated the position of the moving object. In this paper, we presented a study to improve the accuracy of a moving target by using the triangulation method with the help of the K-means clustering algorithm. The primary focus is to identify and eliminate the effect of an erroneous sensor measurement by applying K-means clustering. The accurate position of the flying object can be obtained from the cluster formed by combining a group of all similar measurements. A comparison study of errors with respect to the actual value and calculated value were drawn to validate the results.