Skip to content
/ LaneDetection Public

This repo contains tensorflow implementation of UNET architecture for semantic segmentation of lanes

1 star 0 forks Branches Tags Activity
Star
Notifications You must be signed in to change notification settings

soumilchugh/LaneDetection

BranchesTags

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

10 Commits

Car1.png

Car1.png

 
 

Car2.png

Car2.png

 
 

Car3.png

Car3.png

 
 

Car4.png

Car4.png

 
 

FeatureVisualisation1.png

FeatureVisualisation1.png

 
 

FeatureVisualisation2.png

FeatureVisualisation2.png

 
 

FeatureVisualisation3.png

FeatureVisualisation3.png

 
 

FeatureVisualisation4.png

FeatureVisualisation4.png

 
 

FeatureVisualisation5.png

FeatureVisualisation5.png

 
 

FeatureVisualisation6.png

FeatureVisualisation6.png

 
 

FinalOutput1.png

FinalOutput1.png

 
 

FinalOutput2.png

FinalOutput2.png

 
 

FinalOutput3.png

FinalOutput3.png

 
 

FinalOutput4.png

FinalOutput4.png

 
 

Label1.png

Label1.png

 
 

Label2.png

Label2.png

 
 

Label3.png

Label3.png

 
 

Label4.png

Label4.png

 
 

LabelOnImage3.png

LabelOnImage3.png

 
 

LabelOnImage4.png

LabelOnImage4.png

 
 

LabelonImage1.png

LabelonImage1.png

 
 

LabelonImage2.png

LabelonImage2.png

 
 

Output1.png

Output1.png

 
 

Output2.png

Output2.png

 
 

Output3.png

Output3.png

 
 

Output4.png

Output4.png

 
 

README.md

README.md

 
 

Unet.py

Unet.py

 
 

checkpoint

checkpoint

 
 

generateBoundingBox.py

generateBoundingBox.py

 
 

generateLabels.py

generateLabels.py

 
 

inference.py

inference.py

 
 

model.ckpt.data-00000-of-00001

model.ckpt.data-00000-of-00001

 
 

model.ckpt.index

model.ckpt.index

 
 

model.ckpt.meta

model.ckpt.meta

 
 

Repository files navigation

LaneDetection

Dataset - BDD100K

Usage

  • Generate labels for each of the trained images using Canny edge detector
  • Train a semantic segmentation model on these train images

Examples of Raw images

Examples of Labels for the Segmentation model

Labels superimposed on the original images

Output from the Trained Model

Output Superimposed on the images

Feature Map Visualisation of some of the layers of the network

About

This repo contains tensorflow implementation of UNET architecture for semantic segmentation of lanes

Topics

python computer-vision tensorflow cnn autoencoder segmentation autonomous-vehicles unet lane-detection semantic-segmentation tensorflow-models stochastic-gradient-descent

Resources

Readme
Activity

Stars

1 star

Watchers

1 watching

Forks

0 forks
Report repository

Releases

No releases published

Packages

No packages published

Languages