A Vision-based Virtual Assistant. Case Study: Human Detection and Tracking on Surveillance Cameras

Please enable javascript in your browser.

Morsali, Mohammad Mehrdad | 2024

3 Viewed

Type of Document: M.Sc. Thesis
Language: Farsi
Document No: 56990 (05)
University: Sharif University of Technology
Department: Electrical Engineering
Advisor(s): Bagheri Shouraki, Saeed; Mohammadzadeh, Hoda
Abstract:
This thesis suggests a practical system designed for the implementation of vision-based virtual assistants, aligning with the identified needs in the research background. Distinguishing itself from current literature, this study thoroughly explores and delineates the computing hierarchy while also suggesting the appropriate software architecture customized for the effective utilization of virtual assistants. Focusing on the most common application in vision-based virtual assistants—object detection and tracking—the research introduces an efficient multi-object tracking method using the tracking-by-detection paradigm. Notably, the proposed tracker stands out for its minimal computational load, achieving the fastest reported tracking speed to date. Benchmark results on the MOT17 dataset's test data demonstrate the effectiveness of the proposed method, with the system reaching an impressive speed of 1471 Hz and achieving an HOTA of 61.7\%
Keywords:
Multiobjective Tracking ; Object Detection ; Virtual Assistant ; Edge-Cloud Computing ; Surveillance Cameras ; Human Tracking