This application provides a multisensor data fusion perception method and apparatus. Static feature data and dynamic feature data are obtained after received feature data collected by a plurality of types of sensors are preprocessed. Current static environment information is constructed based on the static feature data and reference dynamic target information, and current dynamic target information is constructed based on the dynamic feature data and reference static environment information. In other words, construction of a dynamic target and construction of a static environment are performed by referring to each other's construction results. Because a construction process not only uses the feature data at a lower level, but also uses the construction result at a higher level, for example, the reference dynamic target information or the reference static environment information, perception performance of multisensor data fusion can be improved. Further, a perception capability of a moving carrier is improved. The perception capability is for the dynamic target and the static environment that are in an environment in which the moving carrier is located.
MULTI-SENSOR DATA FUSION METHOD AND DEVICE
MEHRFACHSENSORDATENFUSIONSVERFAHREN UND -VORRICHTUNG
PROCÉDÉ ET DISPOSITIF DE FUSION DE DONNÉES À MULTIPLES CAPTEURS
2022-01-12
Patent
Elektronische Ressource
Englisch
Multi-sensor fusion mapping robot and data fusion method
Europäisches Patentamt | 2023
|IKBS in multi-sensor data fusion
Tema Archiv | 1985
|Statistical modelling of multi-sensor data fusion
IEEE | 2017
|