Skip to content

Using Tenserflow and OpenCV for obstacle Detection for Dashcam in car

License

Notifications You must be signed in to change notification settings

SrivatsaAdarsh/Obstacle-Detection-using-CNN

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

9 Commits
 
 
 
 
 
 
 
 

Repository files navigation

Obstacle-Detection-using-CNN

Object detection and identification is a fundamental workflow in Computer vision. Proposed system specifies the methods that have been used to overcome the disadvantages that were present in the old methodologies like: e.g R-CNN, KNN etc.

Training is done via convolutional neural network with inception-v3 model with the labels of their respective object. Segmentation is applied as a pre-processing stepwhere the image is divided into equal patches. A rectangle is drawn on the image showing the patches of image data. Image is cropped using the co-ordinates of the rectangle. This method increases accuracy because only the part of an image is used for CNN.

About

Using Tenserflow and OpenCV for obstacle Detection for Dashcam in car

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages