Human Recognition from Crowd using Video Analytics

Project Title

Human Recognition from Crowd using Video Analytics

Project Area of Specialization Software EngineeringProject Summary

Crowd behavior recognition is becoming an important research topic in video surveillance for public places. It has major importance in areas where security is the most important factor. Video surveillance solutions are more effective than ever before, providing new surveillance technology that is applicable to wide range end-users. In retail sectors, schools, homes, office campuses, industrial /transportation Systems and government sector.Our work consists of monitoring and classification of weapons and live track it once located. Operations of proposed project has three processing modules, first processing module is for object detection using Convolutional Neural Networks (CNN) and second processing module will handle the classification of weapons, monitoring and alarm operations will be carried out by the third processing module[1]. CCTV will monitor circular area and it will automatically perform all operations and be controlled. 
Shape detection algorithms and objects detection algorithms will be tested to find the accuracy in detection and analysis of processing time before implementing in such environment and results provide optimal accuracy in matching weapons and objects type with name and shape in predefined database.
A lot of incidents which happened in public places with the use of weapons can be reduced or quickly observed by this method. This work is only applicable in confined areas. This system provides the fully-automated detection and recognition of weapon in public places.

Project Objectives

Civilized and organized system for public.

Less waste of time.

Security in crowded areas.

Decrease crime rate.

Project Implementation Method

Python will be used for Back-end and web will be used as front end. Since most of the security systems are operated via desktops. So it will be suitable that our application is Desktop Based. 

• The development process will consist of testing the most accurate object classification techniques. The tool, which will be used, is pycharm.

• It will be Web based . For back-end, we will use python and front end we will use

Html, Css and javascipt because it contains many libraries and it is easier to design visually for front-end.

• The target platform will be Windows.

• Python will be used as programming language. Libraries such as Keras and Tensorflow will be used. TensorFlow compiles many different algorithms and models together, enabling the user to implement deep neural networks for use in tasks like image recognition/classification 

• In terms of Keras, a high-level API (application programming interface) can use .

For classification and vedio analytics we use yolo algorithm but if the this algorithm give not much accuracy we will use CNN algorithm.

Benefits of the Project

The main goal of the project is to detect weapons so that it can reduce the crime rate and help the police to find the person committing crime easily. It will detect the weapons when the person will be in the eyes of camera. It will be essential in areas where security is the most important factor and there is risk of criminal attacks.

Technical Details of Final Deliverable

 if we get edible funding for the hardware then we will implement our system on cctv.Otherwise we will make a system and twst and train it through the webcam.• Detects any weapons when the person is in the premises of the camera.

• Only the weapons present in the database will be detected.

• Once detected, it will generate an alarm.

• Pre-defined data sets will be used.

• Recorded videos will be used to test for weapon detection.

• For the final testing, we will make our own videos to test the accuracy of our program.

• Shape detection and object detection algorithms will be tested first to find accuracy.

Final Deliverable of the Project Hardware SystemCore Industry ITOther IndustriesCore Technology OthersOther TechnologiesSustainable Development Goals Peace and Justice Strong InstitutionsRequired Resources

Item Name	Type	No. of Units	Per Unit Cost (in Rs)	Total (in Rs)
			Total in (Rs)	50000
CCTV cameras	Equipment	1	50000	50000