Skip to content

This is a demonstration of a MobileNetSDD object detector for achieving a very high frame per secons(FPS)

Notifications You must be signed in to change notification settings

inayatkh/realTimeObjectDetection

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

6 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Real-time Object Detection with deep MobileNetSSD detector

This is an efficient use of a deep detector usinf python 3, Caffe and openCV.

In order to achieve a very high frame rate (FPS) , we have used VideoStream class of imutils for python 3.

A class name SSD has been implemented for loading the MobileNetSSD model using Caffe, and manipulating other required pre and post processing.

To run this code, follow these steps

  • Step 1: Using pip install these packages

    • imtuils
    • caffe
    • opencv ver 3.2
  • Step 2: Run the detector $ pyton3 deepDetectVideo -v ./videos//Kids-Truck-Bus-video.mkv

  • you can find a sample in the vdieos folder obtained from youtube

An example of the output is shown bellow

you can watch the full video here

About

This is a demonstration of a MobileNetSDD object detector for achieving a very high frame per secons(FPS)

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages