Computer Vision Data Science Image Processing

Object Counting with TensorFlow Using Python

TensorFlow object counting

Object Counting with TensorFlow

The TensorFlow Object Counting API is an open-source platform for developing object counting systems based on TensorFlow. The TensorFlow Object Detection API was used to build object detection and classification. Trained color Histogram Features were used to construct object color prediction using OpenCV and the K-Nearest Neighbours Machine Learning Classification Algorithm.

TensorFlow is an open-source software framework that uses data flow graphs to do numerical computations. The graph’s nodes represent mathematical operations, while the graph’s edges represent the multidimensional data arrays that are exchanged between them.

OpenCV is a free software library for computer vision and machine learning. OpenCV was created to offer a standard infrastructure for computer vision applications and to let commercial goods incorporate machine perception more quickly.

All in One

This project includes:

  • All objects detect and counting
  • Targeted object detection and count
    • Vehicle
    • Pedestrians
    •  Animals etc 
  • Predict the color of all objects and predict the color of  targeted object
  • Predict the speed of all objects and predict the speed a targeted object
  • Save and store the results of counting object
  • Count object from both (Images and videos) in real time
  • Process new images and videos

Features

  • Run in Real Time Environment
  • Lightweight  
  • Well-designed and Scalable framework

Requirement

  • Python
  • Jupyter notebook
  • Matplotlib
  • Tensorflow

Download Link

Leave a Comment