Editing Sensor fusion (section)

== Applications ==

One application of sensor fusion is [[GPS/INS]], where [[Global Positioning System]] and [[inertial navigation system]] data is fused using various different methods, e.g. the [[extended Kalman filter]].  This is useful, for example, in determining the attitude of an aircraft using low-cost sensors.<ref>{{cite journal|last=Gross|first=Jason|author2=Yu Gu |author3=Matthew Rhudy |author4=Srikanth Gururajan |author5=Marcello Napolitano |title=Flight Test Evaluation of Sensor Fusion Algorithms for Attitude Estimation|journal=IEEE Transactions on Aerospace and Electronic Systems|date=July 2012|volume=48|issue=3|pages=2128–2139|doi=10.1109/TAES.2012.6237583|bibcode=2012ITAES..48.2128G|s2cid=393165}}</ref> Another example is using the [[data fusion]] approach to determine the traffic state (low traffic, traffic jam, medium flow) using road side collected acoustic, image and sensor data.<ref>{{cite conference|author=Joshi, V., Rajamani, N., Takayuki, K., Prathapaneni, N., Subramaniam, L. V. |year= 2013|title= Information Fusion Based Learning for Frugal Traffic State Sensing|conference=Proceedings of the Twenty-Third International Joint Conference on Artificial Intelligence}}</ref> In the field of autonomous driving, sensor fusion is used to combine the redundant information from complementary sensors in order to obtain a more accurate and reliable representation of the environment.<ref name=mmp>{{cite journal | last1=Mircea Paul| first1=Muresan| last2=Ion| first2=Giosan| last3=Sergiu| first3=Nedevschi | title=Stabilization and Validation of 3D Object Position Using Multimodal Sensor Fusion and Semantic Segmentation | journal=Sensors | volume=20 | issue=4 | pages=1110| date=2020-02-18| doi=10.3390/s20041110 | pmid=32085608| pmc=7070899| bibcode=2020Senso..20.1110M| doi-access=free}}</ref>

Although technically not a dedicated sensor fusion method, modern [[convolutional neural network]] based methods can simultaneously process  many channels of sensor data (such as [[hyperspectral imaging]] with hundreds of bands <ref name=Ran>{{cite journal | last1=Ran | first1=Lingyan | last2=Zhang | first2=Yanning | last3=Wei | first3=Wei | last4=Zhang | first4=Qilin | title=A Hyperspectral Image Classification Framework with Spatial Pixel Pair Features | journal=Sensors | volume=17 | issue=10 | pages=2421 | date=2017-10-23 | doi=10.3390/s17102421 | pmid=29065535 | pmc=5677443 | bibcode=2017Senso..17.2421R | doi-access=free }}</ref>) and fuse relevant information to produce classification results.