Semantic Scene Change Detection: Evaluation through Classical & Machine Learning Algorithms

Examensarbete för masterexamen

Please use this identifier to cite or link to this item: https://hdl.handle.net/20.500.12380/304578
Download file(s):
File Description SizeFormat 
CSE 21-167 Sreekumar Desai.pdfSemantic Scene Change Detection: Evaluation through Classical & Machine Learning Algorithms16.46 MBAdobe PDFView/Open
Full metadata record
DC FieldValueLanguage
dc.contributor.authorSreekumar, Jithinraj-
dc.contributor.authorDesai, Shreya-
dc.contributor.departmentChalmers tekniska högskola / Institutionen för data och informationstekniksv
dc.date.accessioned2022-05-17T09:36:27Z-
dc.date.available2022-05-17T09:36:27Z-
dc.date.issued2021sv
dc.date.submitted2020-
dc.identifier.urihttps://hdl.handle.net/20.500.12380/304578-
dc.description.abstractScene change detection helps to detect changes in a pair of multitemporal images of the same scene. We apply the concept of scene change detection to detect misplaced objects in a passenger vehicle. Deep learning neural networks have been extensively used in scene change detection. We study scene change detection using the classical Watershed algorithm and machine learning algorithms. In machine learning, we exploit the feature extraction capability of ResNet and Spatial Pyramid Pooling to predict the scene change. The performance of the classical and machine learning algorithms are also compared. The models are trained on a custom dataset and evaluated using the metrics, dice coefficient, mean intersection over union (mIoU) and pixel accuracy. We infer that the machine learning model significantly outperforms the classical model in terms of mIoU score.sv
dc.language.isoengsv
dc.setspec.uppsokTechnology-
dc.subjectscene change detectionsv
dc.subjectmachine learningsv
dc.subjectsemantic segmentationsv
dc.subjectconvolutional neural networksv
dc.subjectresidual neural networksv
dc.subjectsiamese networksv
dc.subjectspatial pyramid poolingsv
dc.titleSemantic Scene Change Detection: Evaluation through Classical & Machine Learning Algorithmssv
dc.type.degreeExamensarbete för masterexamensv
dc.type.uppsokH-
dc.contributor.examinerSeger, Carl-Johan-
dc.contributor.supervisorDamaschke, Peter-
dc.identifier.coursecodeDATX05sv
Collection:Examensarbeten för masterexamen // Master Theses



Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.