Human identification

Project Title

Human identification

Project Area of Specialization Artificial IntelligenceProject Summary

Biometric technology based on human gait identifies humans at a far distance even if the individual’s face is covered, hidden, or not visible to cameras in dark environments. The studies conducted in low-illumination environments (dark environments) are based on side view images (horizontal walking) of subjects. However, there are cases in which people only show the front and back views of their bodies while they are walking in low-illumination corridors. In these views, it is difficult to identify humans by using conventional features such as cycle, cadence, stride length of walking, and distance between points (ankle, knee, and hip). Additionally, the cases of problems such as people carrying cellphones and/or small personal items (a purse, bag, clothes, etc.) have critical effects on the accuracy of human identification. To overcome these problems, we would propose a new human identification technique, which will based on the front and back view images of a human, captured by using a thermal camera r. Our technique would use movements of the human body for identification, particularly movement of the head, shoulders, and legs. We would use a convolutional neural network for feature extraction and classification in this study. Four datasets would be compiled by collecting data of 30 people including men and women in both bright and dark environments.

Project Objectives

Human identification is an important and challenging research topic in surveillance systems with various applications in criminal detection, crime prevention, access control, and finding lost children and people. Human identification is based on biometric identifiers, which are categorized as physiological and behavioral characteristics. Physiological characteristics represent the shape of human body parts such as  fingerprint, palm veins, deoxyribonucleic acid, and iris. Behavioral characteristics represent the pattern of behavior of a person such as gait, voice, motion, and movements. Such biometric signatures can be measured at different distances depending upon the measurement process.

Project Implementation Method

         Artificial Intelligence Markup Language, is an XML dialect for creating natural language software agents. AIML is an XML based markup language meant to create artificial intelligent applications. AIML makes it possible to create human interfaces while keeping the implementation simple to program, easy to understand and highly maintainable.

Motion detection:

        Motion detection is usually a software-based monitoring algorithm which, when it detects motions will signal the surveillance camera to begin capturing the event. Also called activity detection. An advanced motion detection surveillance system can analyze the type of motion to see if it warrants an alarm.

Benefits of the Project

1. Side view of a human provides clear view of legs and leg joints.
2. It is efficient and secure.
3. It recognize person in low light or in dark.
4. There is no shadow problem.
5. Clothes would not affect performance of the system.

First this system would capture the scene through a thermal sensor camera then it would pre-process the video and then it would track the human and detects its movements and recognize the person.

Technical Details of Final Deliverable

1. We will gather data through camera.
2. We would pre-process the data.
3. Extract features from the gathered data.
4. Match the patterns on the base of features extracted from gathered data
5. Recognize the person.

Final Deliverable of the Project HW/SW integrated systemType of Industry IT 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)	60000
thermal cam	Equipment	1	50000	50000
Masters walking	Equipment	1	10000	10000