OPTICS & OPTOELECTRONIC TECHNOLOGY, Volume. 18, Issue 5, 51(2020)
3DReconstructionofSceneBasedon MonocularMulti-ViewImage
Inthispaper,the3Dreconstructionofscenebasedonmonocularmultiviewimage,thekeyframesareextracted fromtheaerialimagesbyusingvariousinformationsuch asaircraftandcamera,andthenthekeyframesareextracted,the featurepointpairarematchedbyusingtheratioofnearestneighbor tonextneighbor.Atthesametime,inordertoimprove thematchingrobustness,theKCLDalgorithmisusedto eliminatethemismatchedpointpairs.Then,therotationtransition matrix between the two views is calculated by matching point pairs,so as to further calculate the position and oriention informationoftheviewinthe globalcoordinatesystem.Accordingtothe positionandorientationinformationof theview, the 3D sparse point between matching point pairs is calculated by triangulation,and then the optimal reprojection matrix obtained by using the bundling optimization strategy instead of iterative optimization,and the sparse point cloud is optimized.Finally,onthebasisofthesparsepointcloud,the3Dmultiperspectivestereovisionalgorithmbasedonpatchis usedfordensereconstruction,andthetextureispastedtoobtainvisualization.
Get Citation
Copy Citation Text
WUZheng-zheng, KOUZhan. 3DReconstructionofSceneBasedon MonocularMulti-ViewImage[J]. OPTICS & OPTOELECTRONIC TECHNOLOGY, 2020, 18(5): 51
Category:
Received: Apr. 9, 2020
Accepted: --
Published Online: Jan. 14, 2021
The Author Email: WUZheng-zheng (kouzhan_sdu@163.com)
CSTR:32186.14.