Smart Suveillance System

BE CSE Project

2019

Designing a telemedicine solution to address the lack of accessible eye care in rural areas.

Team

Sriram Hemanth Kumar

Srinidhi Naraynan

Sridevi Shanmugam

Duration

2 Months

Programming Language

Abstract

Smart surveillance systems for road surveillance have become a topic of great interest. The proposed framework utilizes deep learning frameworks to monitor a specific scenario without upgrading the current hardware setup for faster identification of vehicles and capture a violent scene and report the same to the authority. It mainly focuses on physical assault or violence by way of bodily contact. By using the information captured from the stream, chances of identifying a vehicle can be improved drastically.

Problem Statement

  • Generally, the existing road surveillance systems require human intervention to verify the actions of the scene, which is time-consuming and inefficient.

  • The current proposal provides a solution by using efficient computer vision techniques to improve productivity and find lost motor vehicles and prevent physical abuse in a public place.

Concepts

Object detection

  • 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 (such as humans, buildings, or cars) in digital images and videos.

  • Well-researched domains of object detection include face detection and pedestrian detection. Object detection has applications in many areas of computer vision, including image retrieval and video surveillance.

  • It is widely used in computer vision tasks such as image annotation, activity recognition, face detection, face recognition, video object co-segmentation. It is also used in tracking objects, for example tracking a ball during a football match, tracking movement of a cricket bat, or tracking a person in a video.

License Plate Detection

• Vehicle Number Plate Detection aims at the detection of the License Plate present on a vehicle and then extracting the contents of that License Plate.

Optical character recognition or optical character read er(OCR) is the electronic or mechanical conversion of images of typed, handwritten, or printed text into machine-encoded text like, from a scene-photo.

  • Using OCR in the detection of license plates gives accuracy in the values.

Violence Detection

  • In public places, violent behaviors pose a serious threat to personal security and social stability.

  • At present, millions of equipment are applied in public places, leading to a huge pressure on the security attendants.

  • Therefore, it is of great significance to automatically detect violence events from the vast amounts of surveillance video data.

  • This task involves many related computer vision techniques, for instance, object detection, action recognition and classification.

  • The goal of violence detection is to automatically and effectively determine whether the violence occurs or not within a short video sequence.

Issues & Challenges

  • Longer training time is expected for higher accuracy.

  • Limited computational resources might affect the performance of the detectors.

  • Expensive components must be used for real-time calculation.

  • Training datasets depend on the power of the GPU used.

Proposed Work

The proposed work focuses on detecting and recognizing various objects and scenes, so it becomes feasible to recognize the type of the vehicle type, license plate and alert the authority (or) the concerned person when the incident takes place. By providing an application, users easily can get notified when violence is detected in a public place or even in a home and analyze the stream for investigating the scene.

Architecture

Module Implementation

How It Works

Input VIdeo

Reading input stream from user

FFMPEG is a leading multimedia framework able to decode, encode, transcode, mux, demux, stream, filter and play pretty anything that humans and machines have created

Extracting Frames

Reading input stream from user

Converting frames into workable format

For example in the above image you can see that the mirror of the car is nothing more than a matrix containing all the intensity values of the pixel points. How we get and store the pixels values may vary according to our needs, but in the end all images inside a computer world may be reduced to numerical matrices and other information describing the matrix itself. OpenCV is a computer vision library whose main focus is to process and manipulate this information.

Detecting objects from the extracted frame

Objects are detected using YOLO

Video Fingerprinting

0.000000: truck, car, person, 0.100100: truck, car, person, 0.200200: truck, car, person, 0.300300: truck, car, person, 0.400400: truck, car, person, 0.500500: truck, car, person

Conlusion

  • Identification of objects, extraction of the license plate, and detection of violence in a given video sequence are achieved.

  • Accuracy depends upon the techniques of object recognition, feature extraction, and classification along with the dataset used.

References

1. Ala Mhalla, Thierry Chateau, Sami Gazzah, and Najoua Essoukri Ben Amara, “An Embedded Computer-Vision System for Multi-Object Detection in Traffic Surveillance”, IEEE Transactions of intelligent transportation systems, 2017.


2. Muhammad Ramzan, Adnan Abid, Hikmat Ullah Khan, Shahid Mahmood Awan, Amina Ismail, Mahwish Ilyas, Ahsan Mahmood, “A Review on state-on-the-art Violence Detection Techniques” , IEEE Journal, 2019.


3. Guruh Fajar Shidik, Edi Noersasongko, Adhitya Nugraha, Pulung Nurtantio Ndono, Jumanto Jumanto, Edi Jaya Kusuma, “A Systematic Review of Intelligence Video Surveillance: Trends, Techniques, Frameworks, and Datasets” , IEEE , Dec 2019.


4. Shan Du, Member, Mahmoud Ibrahim, Mohamed Shehata, and Wael Badawy, ”Automatic License Plate Recognition (ALPR): A State of the Art Review ” In IEEE, 2014.

5. Shaoqing Ren, Kaiming He, Ross Girshick, and Jian Sun, "Faster R-CNN: Towards real- time object detection with region proposal networks" in Advances in Neural Information Processing Systems (NIPS), 2015.


6. Waqas Sultani , Chen Chen, Mubarak Shah, “Real-world Anomaly Detection in Surveillance Videos”,IEEE,2019.

Smart Suveillance System

BE CSE Project

2019

Designing a telemedicine solution to address the lack of accessible eye care in rural areas.

Team

Sriram Hemanth Kumar

Srinidhi Naraynan

Sridevi Shanmugam

Duration

2 Months

Programming Language

Abstract

Smart surveillance systems for road surveillance have become a topic of great interest. The proposed framework utilizes deep learning frameworks to monitor a specific scenario without upgrading the current hardware setup for faster identification of vehicles and capture a violent scene and report the same to the authority. It mainly focuses on physical assault or violence by way of bodily contact. By using the information captured from the stream, chances of identifying a vehicle can be improved drastically.

Problem Statement

  • Generally, the existing road surveillance systems require human intervention to verify the actions of the scene, which is time-consuming and inefficient.

  • The current proposal provides a solution by using efficient computer vision techniques to improve productivity and find lost motor vehicles and prevent physical abuse in a public place.

Concepts

Object detection

  • 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 (such as humans, buildings, or cars) in digital images and videos.

  • Well-researched domains of object detection include face detection and pedestrian detection. Object detection has applications in many areas of computer vision, including image retrieval and video surveillance.

  • It is widely used in computer vision tasks such as image annotation, activity recognition, face detection, face recognition, video object co-segmentation. It is also used in tracking objects, for example tracking a ball during a football match, tracking movement of a cricket bat, or tracking a person in a video.

License Plate Detection

• Vehicle Number Plate Detection aims at the detection of the License Plate present on a vehicle and then extracting the contents of that License Plate.

Optical character recognition or optical character read er(OCR) is the electronic or mechanical conversion of images of typed, handwritten, or printed text into machine-encoded text like, from a scene-photo.

  • Using OCR in the detection of license plates gives accuracy in the values.

Violence Detection

  • In public places, violent behaviors pose a serious threat to personal security and social stability.

  • At present, millions of equipment are applied in public places, leading to a huge pressure on the security attendants.

  • Therefore, it is of great significance to automatically detect violence events from the vast amounts of surveillance video data.

  • This task involves many related computer vision techniques, for instance, object detection, action recognition and classification.

  • The goal of violence detection is to automatically and effectively determine whether the violence occurs or not within a short video sequence.

Issues & Challenges

  • Longer training time is expected for higher accuracy.

  • Limited computational resources might affect the performance of the detectors.

  • Expensive components must be used for real-time calculation.

  • Training datasets depend on the power of the GPU used.

Proposed Work

The proposed work focuses on detecting and recognizing various objects and scenes, so it becomes feasible to recognize the type of the vehicle type, license plate and alert the authority (or) the concerned person when the incident takes place. By providing an application, users easily can get notified when violence is detected in a public place or even in a home and analyze the stream for investigating the scene.

Architecture

Module Implementation

How It Works

Input VIdeo

Reading input stream from user

FFMPEG is a leading multimedia framework able to decode, encode, transcode, mux, demux, stream, filter and play pretty anything that humans and machines have created

Extracting Frames

Reading input stream from user

Converting frames into workable format

For example in the above image you can see that the mirror of the car is nothing more than a matrix containing all the intensity values of the pixel points. How we get and store the pixels values may vary according to our needs, but in the end all images inside a computer world may be reduced to numerical matrices and other information describing the matrix itself. OpenCV is a computer vision library whose main focus is to process and manipulate this information.

Detecting objects from the extracted frame

Objects are detected using YOLO

Video Fingerprinting

0.000000: truck, car, person, 0.100100: truck, car, person, 0.200200: truck, car, person, 0.300300: truck, car, person, 0.400400: truck, car, person, 0.500500: truck, car, person

Conlusion

  • Identification of objects, extraction of the license plate, and detection of violence in a given video sequence are achieved.

  • Accuracy depends upon the techniques of object recognition, feature extraction, and classification along with the dataset used.

References

1. Ala Mhalla, Thierry Chateau, Sami Gazzah, and Najoua Essoukri Ben Amara, “An Embedded Computer-Vision System for Multi-Object Detection in Traffic Surveillance”, IEEE Transactions of intelligent transportation systems, 2017.


2. Muhammad Ramzan, Adnan Abid, Hikmat Ullah Khan, Shahid Mahmood Awan, Amina Ismail, Mahwish Ilyas, Ahsan Mahmood, “A Review on state-on-the-art Violence Detection Techniques” , IEEE Journal, 2019.


3. Guruh Fajar Shidik, Edi Noersasongko, Adhitya Nugraha, Pulung Nurtantio Ndono, Jumanto Jumanto, Edi Jaya Kusuma, “A Systematic Review of Intelligence Video Surveillance: Trends, Techniques, Frameworks, and Datasets” , IEEE , Dec 2019.


4. Shan Du, Member, Mahmoud Ibrahim, Mohamed Shehata, and Wael Badawy, ”Automatic License Plate Recognition (ALPR): A State of the Art Review ” In IEEE, 2014.

5. Shaoqing Ren, Kaiming He, Ross Girshick, and Jian Sun, "Faster R-CNN: Towards real- time object detection with region proposal networks" in Advances in Neural Information Processing Systems (NIPS), 2015.


6. Waqas Sultani , Chen Chen, Mubarak Shah, “Real-world Anomaly Detection in Surveillance Videos”,IEEE,2019.

Smart Suveillance System

BE CSE Project

2019

Designing a telemedicine solution to address the lack of accessible eye care in rural areas.

Team

Sriram Hemanth Kumar

Srinidhi Naraynan

Sridevi Shanmugam

Duration

2 Months

Programming Language

Abstract

Smart surveillance systems for road surveillance have become a topic of great interest. The proposed framework utilizes deep learning frameworks to monitor a specific scenario without upgrading the current hardware setup for faster identification of vehicles and capture a violent scene and report the same to the authority. It mainly focuses on physical assault or violence by way of bodily contact. By using the information captured from the stream, chances of identifying a vehicle can be improved drastically.

Problem Statement

  • Generally, the existing road surveillance systems require human intervention to verify the actions of the scene, which is time-consuming and inefficient.

  • The current proposal provides a solution by using efficient computer vision techniques to improve productivity and find lost motor vehicles and prevent physical abuse in a public place.

Concepts

Object detection

  • 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 (such as humans, buildings, or cars) in digital images and videos.

  • Well-researched domains of object detection include face detection and pedestrian detection. Object detection has applications in many areas of computer vision, including image retrieval and video surveillance.

  • It is widely used in computer vision tasks such as image annotation, activity recognition, face detection, face recognition, video object co-segmentation. It is also used in tracking objects, for example tracking a ball during a football match, tracking movement of a cricket bat, or tracking a person in a video.

License Plate Detection

• Vehicle Number Plate Detection aims at the detection of the License Plate present on a vehicle and then extracting the contents of that License Plate.

Optical character recognition or optical character read er(OCR) is the electronic or mechanical conversion of images of typed, handwritten, or printed text into machine-encoded text like, from a scene-photo.

  • Using OCR in the detection of license plates gives accuracy in the values.

Violence Detection

  • In public places, violent behaviors pose a serious threat to personal security and social stability.

  • At present, millions of equipment are applied in public places, leading to a huge pressure on the security attendants.

  • Therefore, it is of great significance to automatically detect violence events from the vast amounts of surveillance video data.

  • This task involves many related computer vision techniques, for instance, object detection, action recognition and classification.

  • The goal of violence detection is to automatically and effectively determine whether the violence occurs or not within a short video sequence.

Issues & Challenges

  • Longer training time is expected for higher accuracy.

  • Limited computational resources might affect the performance of the detectors.

  • Expensive components must be used for real-time calculation.

  • Training datasets depend on the power of the GPU used.

Proposed Work

The proposed work focuses on detecting and recognizing various objects and scenes, so it becomes feasible to recognize the type of the vehicle type, license plate and alert the authority (or) the concerned person when the incident takes place. By providing an application, users easily can get notified when violence is detected in a public place or even in a home and analyze the stream for investigating the scene.

Architecture

Module Implementation

How It Works

Input VIdeo

Reading input stream from user

FFMPEG is a leading multimedia framework able to decode, encode, transcode, mux, demux, stream, filter and play pretty anything that humans and machines have created

Extracting Frames

Reading input stream from user

Converting frames into workable format

For example in the above image you can see that the mirror of the car is nothing more than a matrix containing all the intensity values of the pixel points. How we get and store the pixels values may vary according to our needs, but in the end all images inside a computer world may be reduced to numerical matrices and other information describing the matrix itself. OpenCV is a computer vision library whose main focus is to process and manipulate this information.

Detecting objects from the extracted frame

Objects are detected using YOLO

Video Fingerprinting

0.000000: truck, car, person, 0.100100: truck, car, person, 0.200200: truck, car, person, 0.300300: truck, car, person, 0.400400: truck, car, person, 0.500500: truck, car, person

Conlusion

  • Identification of objects, extraction of the license plate, and detection of violence in a given video sequence are achieved.

  • Accuracy depends upon the techniques of object recognition, feature extraction, and classification along with the dataset used.

References

1. Ala Mhalla, Thierry Chateau, Sami Gazzah, and Najoua Essoukri Ben Amara, “An Embedded Computer-Vision System for Multi-Object Detection in Traffic Surveillance”, IEEE Transactions of intelligent transportation systems, 2017.


2. Muhammad Ramzan, Adnan Abid, Hikmat Ullah Khan, Shahid Mahmood Awan, Amina Ismail, Mahwish Ilyas, Ahsan Mahmood, “A Review on state-on-the-art Violence Detection Techniques” , IEEE Journal, 2019.


3. Guruh Fajar Shidik, Edi Noersasongko, Adhitya Nugraha, Pulung Nurtantio Ndono, Jumanto Jumanto, Edi Jaya Kusuma, “A Systematic Review of Intelligence Video Surveillance: Trends, Techniques, Frameworks, and Datasets” , IEEE , Dec 2019.


4. Shan Du, Member, Mahmoud Ibrahim, Mohamed Shehata, and Wael Badawy, ”Automatic License Plate Recognition (ALPR): A State of the Art Review ” In IEEE, 2014.

5. Shaoqing Ren, Kaiming He, Ross Girshick, and Jian Sun, "Faster R-CNN: Towards real- time object detection with region proposal networks" in Advances in Neural Information Processing Systems (NIPS), 2015.


6. Waqas Sultani , Chen Chen, Mubarak Shah, “Real-world Anomaly Detection in Surveillance Videos”,IEEE,2019.

sriramph