Improving Sensor Fusion: A Parametric Method for the Geometric Coalignment of Airborne Hyperspectral and Lidar Data


Synergistic applications based mostly on integrated hyperspectral and lidar knowledge are receiving a growing interest from the remote-sensing community. A prerequisite for the optimum sensor fusion of hyperspectral and lidar information is an accurate geometric coalignment. The simple unadjusted integration of lidar elevation and hyperspectral reflectance causes a substantial loss of knowledge and does not exploit the total potential of each sensors. This paper presents a novel approach for the geometric coalignment of hyperspectral and lidar airborne knowledge, based on their respective adopted come intensity information. The complete approach incorporates ray tracing and subpixel procedures in order to overcome grid inherent discretization. It aims at the correction of extrinsic and intrinsic (camera resectioning) parameters of the hyperspectral sensor. In further to a tie-point-based coregistration, we have a tendency to introduce a ray-tracing-based back projection of the lidar intensities for space-based cost aggregation. The approach consists of 3 processing steps. 1st could be a coarse automatic tie-point-primarily based boresight alignment. The second step coregisters the hyperspectral information to the lidar intensities. Third may be a parametric coalignment refinement with an space-primarily based value aggregation. This hybrid approach of combining tie-purpose features and space-primarily based value aggregation methods for the parametric coregistration of hyperspectral intensity values to their corresponding lidar intensities leads to a root-mean-square error of one/three pixel. It indicates that a highly integrated and stringent combination of different coalignment methods results in an improvement of the multisensor coregistration.

Did you like this research project?

To get this research project Guidelines, Training and Code... Click Here

PROJECT TITLE : Improving I/O Complexity of Triangle Enumeration ABSTRACT: Many graph algorithms are now required to operate in external memory and deliver performance that does not significantly degrade with the scale of the
PROJECT TITLE : Improving Speech Emotion Recognition With Adversarial Data Augmentation Network ABSTRACT: When there aren't many training data to work with, it can be difficult to train a deep neural network without triggering
PROJECT TITLE : A Time-Series Feature-Based Recursive Classification Model to Optimize Treatment Strategies for Improving Outcomes and Resource Allocations of COVID-19 Patients ABSTRACT: This paper presents a novel Lasso Logistic
PROJECT TITLE : Recommender Systems and Scratch An integrated approach for enhancing computer programming learning ABSTRACT: Learning computer programming is a difficult task. Visual programming languages (VPLs), such as Scratch,
PROJECT TITLE : Using Cost-Sensitive Learning and Feature Selection Algorithms to Improve the Performance of Imbalanced Classification ABSTRACT: The problem of unbalanced data is common in network intrusion detection, spam filtering,

Ready to Complete Your Academic MTech Project Work In Affordable Price ?

Project Enquiry