object detection with machine learning

Project Title

object detection with machine learning

Project Area of Specialization Software EngineeringProject Summary

Object detection is a computer technology related to computer vision and image processing that deals with detecting instances of semantic objects of a certain class. For Object detection machine learning is being widely used all around the world, for this approach a module is trained to make predictions about the object. This module will be able to detect the selected objects in every background and environment. In this project we will use machine learning to detect custom objects using Arduino boards. After the module is training it will be can to detect items and differentiate between them. Python has been the go-to choice for Machine Learning and Artificial Intelligence developers for a long time. Python offers a broad set of libraries for machine learning: TensorFlow, Numpy, SciPy, Theano, Keras and PyTorch. in this project using tensorflow for object detection.

Project Objectives Object detection also finds use in tracking of objects through video sequences like prediction of object’s future position after detecting it in the past video frames, automatic annotating of faces in live video for further analysis (recognition and labeling) etc. Object detection is technique used for identifying the type of object in an image and also exact location of the object inside image. It is used in autonomous vehicle driving to detect pedestrians walking or jogging on the street to avoid accidents. Here is image with 3 pedestrians correct detected by object detection and enclosed in green rectangles. Project Implementation Method

The starting step towards the completion of our project would be the learning of python language and getting a complete efficiency in this regard. We must be completely proficient in using the machine learning libraries like TensorFlow, Numpy, SciPy, Scikit-learn, Theano, Keras, PyTorch, Pandas, Matplotlib and OpenCV.

Next is the development of environment for implementation of machine learning algorithms working together. For this purpose, their compatibility must be matched and for this reason a complete research on the documentation of each libraries and dependencies must be done.

Next step would be the gathering and selection of data. The data should be appropriate and must be optimize enough to give a module a complete set of information for its training.

Finally, the machine learning algorithm then implemented to detect the objects using camera.

Benefits of the Project

• Surveillance Industry, by monitoring any suspicious activity automatically.

• Self-driven Cars, by identifying the road or obstacles to avoid.

• Industrial Sorting, by sorting between different products in industry.

• Medical Industry, for diagnosis using report images

• Robotics, to equip the robot with environmental based reaction.

• Online Tracking, to track any object using its pictures.

• Ball Tracking in Sports, to automatically move the camera where the ball goes

Technical Details of Final Deliverable

S. No.	Elapsed time from start (in months) of the project	Milestone	Deliverables
01	2	Python learning	Proficiency in using Python
02	5	Setting up Development Environment	Integrated TensorFlow module with all compatibilities fulfilled
03	6	Completion of Data	The data must be collected and transferred into suitable format for module training
04	9	Module Training	Module recognizing and identifying objects

S. No.

01

02

03

04

Final Deliverable of the Project Software SystemCore Industry TransportationOther Industries Agriculture Core Technology OthersOther Technologies Internet of Things (IoT)Sustainable Development Goals Quality Education, Decent Work and Economic Growth, Industry, Innovation and InfrastructureRequired Resources

Elapsed time in (days or weeks or month or quarter) since start of the project	Milestone	Deliverable
Month 1	python learning	proficiency in using python
Month 2	python learning	proficiency in using python
Month 3	setting up development environment	Integrated TensorFlow module with all compatibilities fulfilled
Month 4	setting up development environment	Integrated TensorFlow module with all compatibilities fulfilled
Month 5	setting up development environment	Integrated TensorFlow module with all compatibilities fulfilled
Month 6	Completion of Data	The data must be collected and transferred into suitable format for module training
Month 7	Module Training	Module recognizing and identifying objects
Month 8	Module Training	Module recognizing and identifying objects
Month 9	Module Training	Module recognizing and identifying objects
Month 2	python learning	proficiency in using python
Month 3	setting up development environment	Integrated TensorFlow module with all compatibilities fulfilled
Month 4	setting up development environment	Integrated TensorFlow module with all compatibilities fulfilled
Month 5	setting up development environment	Integrated TensorFlow module with all compatibilities fulfilled
Month 6	Completion of Data	The data must be collected and transferred into suitable format for module training
Month 7	Module Training	Module recognizing and identifying objects
Month 8	Module Training	Module recognizing and identifying objects
Month 9	Module Training	Module recognizing and identifying objects