Scribd
Upload
10 views1 page

Problem Statement: Computer Science & Engg, Dept

Parallel programming with CUDA provides an architecture for developing a graphical user interface using CUDA to track multiple faces in video frames in real-time. Face tracking utilizes temporal correlation across frames to locate faces more efficiently than repeated detection in each frame. The goal is to reduce tracking time and produce real-time output by tracking multiple faces simultaneously with maximum stability.

Uploaded by

Amruta Ekbote
Copyright
© Attribution Non-Commercial (BY-NC)
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
10 views1 page

Problem Statement: Computer Science & Engg, Dept

Parallel programming with CUDA provides an architecture for developing a graphical user interface using CUDA to track multiple faces in video frames in real-time. Face tracking utilizes temporal correlation across frames to locate faces more efficiently than repeated detection in each frame. The goal is to reduce tracking time and produce real-time output by tracking multiple faces simultaneously with maximum stability.

Uploaded by

Amruta Ekbote
Copyright
© Attribution Non-Commercial (BY-NC)
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 1

Parallel programming with CUDA

PROBLEM STATEMENT

Develop architecture for CUDA using Graphical User Interface


for fast and robust tracking of multiple faces in receiving increased attention from computer
vision researchers as it finds potential applications in many fields like video surveillance and
computer mediated video conferencing.

CONCLUSION

A number of face detection and recognition algorithms can be found in a literature survey.
Instead of detecting human faces in each frame independently, face tracking utilizes temporal
correlation to locate them. The idea of introducing face tracking instead of doing repeated
detection is to reduce the tracking time and produce real time output. Real-time face tracker
tracks multiple faces simultaneously on subsequent video frames with maximum stability.

REFERENCES
[1]. David Kirk and Wen-mei. (2009). Many core-Processors for Science and Engineering
Applications.

[2]. NVIDIA, CUDA programming guide 1.1

[3]. Viola, P. Jones, M. (2004) Robust Real-Time Face Detection. International Journal of
Computer Vision.

Computer science & Engg, Dept. Page 1

You might also like