Sökning: "semantisk segmentering"

Visar resultat 16 - 20 av 58 uppsatser innehållade orden semantisk segmentering.

1. 16. Deep Learning Semantic Segmentation of 3D Point Cloud Data from a Photon Counting LiDAR

   Master-uppsats, Linköpings universitet/Datorseende

   Författare :Caspian Süsskind; [2022]
   Nyckelord :Deep Learning; Machine Learning; Computer vision; Semantic Segmentation; Photon Counting LiDAR; LiDAR; Point Cloud; 3D Data; Point Cloud Segmentation; Point Classification; Convolutional Neural Network; CNN; SPVCNN; Djupinlärning; LiDAR; fotonräknande LiDAR; semantisk segmentering; datorseende; punktmoln; maskininlärning;

   Sammanfattning : Deep learning has shown to be successful on the task of semantic segmentation of three-dimensional (3D) point clouds, which has many interesting use cases in areas such as autonomous driving and defense applications. A common type of sensor used for collecting 3D point cloud data is Light Detection and Ranging (LiDAR) sensors. LÄS MER

3. 17. Forest Growth And Volume Estimation Using Machine Learning

   Master-uppsats, Linköpings universitet/Datorseende

   Författare :Gustav Dahmén; Erica Strand; [2022]
   Nyckelord :machine learning; computer vision; forest; object detection; semantic segmentation; forest inventory; forest type; maskinlärning; datorseende; skog; objektdetektion; semantisk segmentering; skogsinventering; skogstyp;

   Sammanfattning : Estimation of forest parameters using remote sensing information could streamline the forest industry from a time and economic perspective. This thesis utilizes object detection and semantic segmentation to detect and classify individual trees from images over 3D models reconstructed from satellite images. LÄS MER

4. 18. Teaching an AI to recycle by looking at scrap metal : Semantic segmentation through self-supervised learning with transformers

   Master-uppsats, Linköpings universitet/Institutionen för datavetenskap

   Författare :Edwin Forsberg; Carl Harris; [2022]
   Nyckelord :AI; self-supervised learning; SSL; Machine vision; ML; Semantic segmentation; Transformer; Swin-transformer; Barlow twins; DINO; SwAV; Recycling; AI; SSL; Datoreseende; maskininlärning; semantisk segmentering; Transformer; Swin-transformer; Barlow twins; DINO; SwAV; Återvinning;

   Sammanfattning : Stena Recycling is one of the leading recycling companies in Sweden and at their facility in Halmstad, 300 tonnes of refuse are handled every day where aluminium is one of the most valuable materials they sort. Today, most of the sorting process is done automatically, but there are still parts of the refuse that are not correctly sorted. LÄS MER

5. 19. Point Cloud Data Augmentation for 4D Panoptic Segmentation

   Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)

   Författare :Wangkang Jin; [2022]
   Nyckelord :Point Cloud; Data Augmentation; 4D panoptic segmentation; Deep Learning; 3D Perception; Autonomous Driving; Punktmoln; Dataökning; 4D panoptisk segmentering; Djup lärning; 3D Perception; 3D Uppfattning; Autonom körning;

   Sammanfattning : 4D panoptic segmentation is an emerging topic in the field of autonomous driving, which jointly tackles 3D semantic segmentation, 3D instance segmentation, and 3D multi-object tracking based on point cloud data. However, the difficulty of collection limits the size of existing point cloud datasets. LÄS MER

7. 20. Knowledge Distillation for Semantic Segmentation and Autonomous Driving. : Astudy on the influence of hyperparameters, initialization of a student network and the distillation method on the semantic segmentation of urban scenes.

   Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)

   Författare :Juan Sanchez Nieto; [2022]
   Nyckelord :Knowledge Distillation; Autonomous Driving; Semantic Segmentation; Cityscapes.; Kunskapsdestillation; Autonom Körning; Semantisk Segmentering; Stadslandskap.;

   Sammanfattning : Reducing the size of a neural network whilst maintaining a comparable performance is an important problem to be solved since the constrictions on resources of small devices make it impossible to deploy large models in numerous real-life scenarios. A prominent example is autonomous driving, where computer vision tasks such as object detection and semantic segmentation need to be performed in real time by mobile devices. LÄS MER