CCTV Search System

Project Title

CCTV Search System

Project Area of Specialization Artificial IntelligenceProject Summary

Crime rates are increasing day by day in our society, People who went missing are searched through the recorded video by matching the faces of recorded people by system with image provided. All these practices are performed manually and results are either successful or failed.

Our software system will allow its users to use the system in secure way by providing them trusted server in an encrypted format. User will be able to provide the image of suspect person. The provided image will be stored in database. CCTV cameras will be inserted in desired locations. These System cameras will capture the picture and compare it with the image in database. This process will be carried out by live stream video; camera will lock the faces, capture the picture and match the faces pattern with image provided for detection. CCTV Search system will record and stream video and detect automatically. CCTV Search system will focus on both ways of image processing using live video feed and it will also take picture and process it with image processing tool. After the detection process is carried out successfully, the system will generate trigger to administration. The content of trigger consist of these attributes: Detected location, captured image, date and time and camera id.

Project Objectives

The main objective of our project is to automate the manual working of CCTV search system. Our purpose is to provide the security to authenticated user. This is done by using HOG algorithm and artificial neural network. These algorithms are used for face detection and face recognition. Our main aim is to deliver an automated CCTV search system which ensure the security as CCTV search system will detect wanted person by image fed in database. On detection it will generate acknowledgement and send it to authority.  We are adopting trending methodologies and technologies to detect them efficiently, Surveillance camera will act as a guard 24/7 and will help the law enforcements to detect or recognize suspect of the case if no thumbprint present on the scene. Image of wanted person will be fed in database by registered user and camera will detect person passing by. If the person is located and match accordingly then it will generate a message and send it to administration along with video, time and that specific location.The main objective of our project is to automate the manual working of CCTV search system. Our purpose is to provide the security to authenticated user. This is done by using HOG algorithm and artificial neural network. These algorithms are used for face detection and face recognition. Our main aim is to deliver an automated CCTV search system which ensure the security as CCTV search system will detect wanted person by image fed in database. On detection it will generate acknowledgement and send it to authority.  We are adopting trending methodologies and technologies to detect them efficiently, Surveillance camera will act as a guard 24/7 and will help the law enforcements to detect or recognize suspect of the case if no thumbprint present on the scene. Image of wanted person will be fed in database by registered user and camera will detect person passing by. If the person is located and match accordingly then it will generate a message and send it to administration along with video, time and that specific location.

Project Implementation Method

The system architecture which our project is based upon is “3-tier Architecture” and the design methodology for the project is procedural. The main reason to choose this methodology is that it consists of a set of procedure calls and a set of code for each procedure. We have used the fundamental concepts of Object Oriented Programming. All the coding is implemented in Python using Pycharm framework. The approach we have used in our project is bottom-up. We have developed each module separately and broke our modules in several chunks that is the main reason for using this approach.

Benefits of the Project

Our System is the first one to be using centralized DVR for multiple cameras in real time. The system is fully automated, saving time and available on desktop based application. Using automated facial recognition technology, my system allows the user to upload an image of a face and perform an automatic search in all live stream CCTV. On successful detection of face-match, the system captures and save video clips of that specific missing person containing date, time and location. The system then immediately triggers notification to the administration with the details. With the help of this system, it can be used to assist in identifying suspects from crime scenes. However even with the current increase in CCTV, there is inadequate availability to locate a suspect instantly, only after watching the CCTV afterwards.

Technical Details of Final Deliverable

As far as final deliverable is concerned, with the completion of the project in the given period of time. We have submitted our full-fledged SRS along with the final report of the project. We have also described our software behavior with the help of test cases. Different tests are performed on the project in order to check its functionality. Our final project is working with the help of DVR , cameras and router . Our project can be use with multiple cameras as well , as we have used multithreading in it . As far as it’s working is concerned it detected the face of suspicion person through live-streaming from the cameras attached to it , after detecting and recognising any suspicious face in front of camera it generates the alarming message to admin along with the video of suspected person including date , time and location of it . We have developed our final project with the help of Artificial Intelligence, dlib and HOG.

Final Deliverable of the Project HW/SW integrated systemType of Industry Security Technologies Artificial Intelligence(AI)Sustainable 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)	10200
DVR	Equipment	1	5100	5100
Camera	Equipment	2	1400	2800
Router	Equipment	1	2300	2300