Development of Surveillance Framework for Person Localization and Recognition in UAV Images

In recent years, use of UAV is increasing for aerial surveillance, border patrol and convoy protection, tracking a ground-moving target (GMT) autonomously. However, the Ariel images have an issue of cluttered background, low resolution quality and various environment and lighting conditions which in

Project Title

Development of Surveillance Framework for Person Localization and Recognition in UAV Images

Project Area of Specialization

Artificial Intelligence

Project Summary

In recent years, use of UAV is increasing for aerial surveillance, border patrol and convoy protection, tracking a ground-moving target (GMT) autonomously. However, the Ariel images have an issue of cluttered background, low resolution quality and various environment and lighting conditions which increase complexity levels of localization and recognition. In this project, we are focusing to implement human localization, recognition, and tracking in UAV real-time images and video with various constraints. The main components of the project will be: (1). UAV Platform for video and image acquisitioning, (2) Data link for transferring of image from UAV to processing system (3) Development and use of algorithms for image enhancement, features extraction for human detection and recognition, and performance comparison of algorithms. (4) Implementation on Raspberry-PI that can be used as onboard processing on UAV. (5) We will collect local environment large dataset for better accuracy.

The proposed system will be utilized for security surveillance, crowd management, and also for delivery services.

Project Objectives

There are following objectives of human localization and recoginition from aerial images:

• UAV Platform for Video and Image acquisitioning
• Human Detection in Aerial images and video
• Crowd counting and management through UAV aerial images
• Datalink for transmission of video from UAV to ground control system.
• Collection of 20k aerial images from different clutter backgrounds.                
• Performance Comparison of Acquired image (Still) and on move.
• Impementation on Raspberry PI.                                                                       Fig 1: Objectives of human localization and recognition in UAV Images

Project Implementation Method

There are following steps for project implementation:

• UAV directly communicate with drone and raspberry-pi
• Video obtain on both remote and raspberry pi
• Aerail Images sepration from video
• Pre-proceing and image enhancment
• Extraction of area of interst
• Human features extraction
• Human detection
• Human counting
• Display detected and counted aerial images/video on screen

                            

                               Fig 2: Implementation model of human localization and recognition in UAV Images

                                                                                          

                                                   Fig3: Flow Chart of human localization and recognition in UAV Images

Benefits of the Project

• In recent years, use of UAV is increasing for aerial surveillance, border patrol and convoy protection, tracking a ground-moving target (GMT) autonomously

• An Unmanned Aerial vehicle (UAV) is a robot used to augment human capability in both civil and military activities. • The Human detection and recognition are used in following aeras:

• Identify criminals
• Crowd managment
• safe city concept
• traffic control system
• flood disaster monitoring
• rescue operations
• surveillance and monitoring etc.

Technical Details of Final Deliverable

-UAV Video/Image Acquisitioning Platform

      Camera Resolution 1280x720

      Camera Resolusion 640x260

      ON-board and ground control system for UAV

-Software for image enhancement, features extraction, and human detection in images

      For Image enhancement using Gussian, sobal and canny edge detector.

      For features extraction and human detection using Haar-  Cascade, Tamplet matching, YOLO and CNN.  

-Raspberry-PI based processing platform that can be ultilized both at onboard and ground system

       Lunix based operating system

       Used for Image Processing, and real time person  detection and regonition.  

Final Deliverable of the Project

HW/SW integrated system

Core Industry

Security

Other Industries

Transportation

Core Technology

Artificial Intelligence(AI)

Other Technologies

Internet of Things (IoT)

Sustainable Development Goals

Sustainable Cities and Communities

Required Resources

If you need this project, please contact me on contact@adikhanofficial.com