Loading...
| Friend's email | |
| Your name | |
| Your email | |
| enter code | |
This page was sent successfuly
- Type of Document: M.Sc. Thesis
- Language: Farsi
- Document No: 56492 (05)
- University: Sharif University of Technology
- Department: Electrical Engineering
- Advisor(s): Gholampour, Iman
- Abstract:
- The multi people tracking is considered a fundamental problem in computer vision, which has received considerable attention from academic and commercial fields. This issue deals with a set of proposed methods that track the movement path of several humans in a video-like sequence. The problem of multi people tracking is the foundation of other computer vision problems, including human gesture estimation, motion recognition, and behavioral analysis, and is mainly used in emerging fields such as automatic car driving, smart security, service robots, etc. Although many methods have been proposed and investigated to solve the above problem; But there are still serious challenges, such as severe occlusion of humans, sudden changes in people's appearance (especially in low frame rate sequences), that need to be solved. The purpose of this research is to investigate, design and implement a real-time detection and tracking system based on deep learning models and focusing on the movement and appearance features of humans. In general, in the investigation of human detection and tracking systems, in addition to the accuracy of the model in detection and tracking, the number of frames that the model can process in one second is also taken into consideration, which is called FPS for short. In many researches, only the time needed for the tracking part is measured, and the time needed to detect humans is ignored; Therefore, many of them cannot be included in the collection of so-called real time methods. In this research, a model has been proposed and implemented that has increased the accuracy of the model compared to the basic models by maintaining the FPS for the system to be real time. Also, in addition to detecting and tracking humans, the system is capable of detecting human faces and extracting and storing the highest quality faces that have been detected from humans
- Keywords:
- Deep Learning ; Face Detection ; Privacy Preserving ; People Tracking ; People Detection ; Human Pose Estimation
Digital Object List
-
محتواي کتاب
- view
Bookmark