Research internship in semantic segmentation of panoramic images

Computer-Vision-Research-Project (GitHub) • Computer-Vision-Research-Project (Wiki) • LVSN (Research Laboratory) • Institut intelligence et données (IID) (research Institute) • Sentinelle Nord (Project) • J-F Lalonde Group (Team) • Algorithmic Photography (Course)

isabelleysseric (GitHub) • isabelleysseric.com (Portfolio) • isabelleysseric (LinkedIn)

Author: Isabelle Eysseric

Project objective: Generate masks for semantic segmentation

Results: Generate masks for semantic segmentation, depth estimation and position estimation

The project took place in 3 phases:

• Phase 0: Training on IA, DL and CV
• Phase 1: Research and analysis of semantic segmentation
• Phase 2: Tests on the two selected models
• Phase 3: Generate masks

In this repository there are 3 folders, one for the code, one for the data, one for the images to be viewed in the wiki and another for the final report.

Computer-Vision-Research-Project

• code
  
  • infer_depth_all.ipynb
    
  • infer_layout_all.ipynb
    
  • infer_sem_all.ipynb
    
  • README.md
    

• data
  
  • applications
    
    • 1.COCO_detection
      
      • API COCO Python
        
      • README.md
        
    • 2.Matterport3D
      
      • image_1.png
        
      • ...
        
      • image_n.png
        
      • README.md
        
    • 3.Stanford2D3D
      
      • image_1.png
        
      • ...
        
      • image_n.png
        
      • README.md
        
  • input
    
    • image_1.png
      
    • ...
      
    • image_n.png
      
  • output
    
    • image_1.png
      
    • ...
      
    • image_n.png
      
  • panocontext
    
    • pano_asmasuxybohhcj.png
      
  • README.md
    

• images
  
  • image_1.png
    
  • ...
    
  • image_n.png
    

• rapport
  
  • Rapport_final_de_stage.pdf
    
  • README.md