Intelligent video system analysis using computer vision

Project Title

Intelligent video system analysis using computer vision

Project Area of Specialization Artificial IntelligenceProject Summary

IVSA is security system aimed to design for building security. Buildings include shopping malls, offices, institutes etc. With an increase in the crime rate and other incidents, IVSA can generate early alarms to inform the user before a possible disaster. It notifies the owner at the instant when it detects some fire, weapon or unsupervised child. IVSA composed of the one master system connected with 1-2 surveillance camera.Master system will be composed of a trained deep learning model made to detect unsupervised child, fire, weapons and human relocation (extended scope) in real time footage. The deep learning model used in this project to perform the above-mentioned tasks is Faster RCNN (Regional Convolutional Neural Network).

Project Objectives

Security system aimed to design for building security. Buildings include shopping malls, offices, institutes etc.

1. Fire detection in any building.
2. Weapon Detection in public place.
3. Human Recognition.
4. Unsupervised child Identification.

Project Implementation Method

The deep learning model used in this project to perform the above-mentioned tasks is Faster RCNN (Regional Convolutional Neural Network). There are many other models available for performing the object detection and classification but we decided to choose Faster RCNN because we have limited hardware resources and its state-of-the-art accuracy. There is a master CPU with whom Cameras on different locations are connected.

Benefits of the Project

Buildings include shopping malls, offices, institutes etc any where, where cameras are availabe. With an increase in the crime rate and other incidents, IVSA can generate early alarms to inform the user before a possible disaster.

Like the detection of fire at any place, human recognition for security purpose, in any mall or oublic place, if any child is unsupervised system will intelligently detect that child before any incident happen like kidnapping etc.

To shorten these problems, we have to use creative approaches to utilize innovation. This is where MassSurveillance through IVSA will plays it part. (Not to be mistaken for home security which is restricted to homes only). IVSA is going to cater all these problems with the help of deep learning, by training the model to detect unsupervised child, accidental fire, guns in the public places and Human relocation in real time video footage through CCTV cameras.

Technical Details of Final Deliverable

The computer vision plays its part here. We are trained our model using Faster-RCNN technique. 

This is where MassSurveillance through IVSA will plays it part. (Not to be mistaken for home security which is restricted to homes only). IVSA is going to cater all these problems with the help of deep learning, by training the model to detect unsupervised child, accidental fire, guns in the public places and Human relocation in real time video footage through CCTV cameras.

A product is known if it has a social responsibility. With an expansion in the crime percentage of abducting, murders and theft and fire episodes. IVSA will contribute by reducing the number of kidnapping case and child missing cases out in the open stops and shopping centers. Early warning will be generated, if it detects a weapon in public places. Ina place where there are no fire detectors IVSA can detect fire before it gets uncontrollable, recognizing fire before it gets wild can help spare a great many lives.

Final Deliverable of the Project Hardware SystemCore Industry SecurityOther Industries Others Core Technology Artificial Intelligence(AI)Other TechnologiesSustainable Development Goals Sustainable Cities and CommunitiesRequired Resources

Item Name	Type	No. of Units	Per Unit Cost (in Rs)	Total (in Rs)
			Total in (Rs)	40400
Nvidia GTX-1060	Equipment	1	32000	32000
3x Logitech C270, 720p HD Webcam	Equipment	3	2800	8400