An Efficient Pipeline for Distant Person Detection and Identification in 4K Video using GPUs

Mattela, Govardhan and Tripathi, Manmohan and Pal, Chandrajit and Dhiraj, Rampelli Sai and Acharyya, Amit (2020) An Efficient Pipeline for Distant Person Detection and Identification in 4K Video using GPUs. In: 2020 International Conference on COMmunication Systems and NETworkS, COMSNETS 2020, 7 January 2020 - 11 January 2020.

Full text not available from this repository. (Request a copy)

Abstract

The gradual advent of machine learning has been assisting to shift the field of computer vision from statistical methods to deep neural networks. These networks should be able to process high resolution video streams coming from the HD camera sources in real time. However, due to the fixed network size and to maintain the processing speed, high resolution frames need to be resized and down-sampled before feeding into the networks resulting in loss of feature information, hampering recognition accuracy. This motivated us to propose a methodology which focuses on creating and processing the active region of interests in the foreground image through an active region generator (ARG) module, eliminating the need to traverse the entire frame and down-sample the resolution before feeding it to the neural network. This resulted in saving 25x more image feature information, whilst maintaining a given person detection accuracy of 92 % mAP for longer distance up to 3035 metre executing in real time w.r.t it's classical counterpart based on singleshot detector model. Besides, our proposed pipeline architecture utilizing multi-core TESLA GPU increases the execution throughput by a factor of 3X verified in NVIDIA DGX system.

[error in script]
IITH Creators:
IITH CreatorsORCiD
Mattela, GovardhanUNSPECIFIED
Dhiraj, R.S.UNSPECIFIED
Acharyya, Amithttp://orcid.org/0000-0002-5636-0676
Item Type: Conference or Workshop Item (Paper)
Uncontrolled Keywords: Active region generator (ARG) module; CCTV; COTS (component of the shelf); GPU (Graphics processing unit); ReID (reidentification)
Subjects: Electrical Engineering
Electrical Engineering > Power System
Divisions: Department of Electrical Engineering
Depositing User: . LibTrainee 2021
Date Deposited: 23 Jun 2021 05:35
Last Modified: 23 Jun 2021 05:35
URI: http://raiith.iith.ac.in/id/eprint/7981
Publisher URL: http://doi.org/10.1109/COMSNETS48256.2020.9027465
Related URLs:

Actions (login required)

View Item View Item
Statistics for RAIITH ePrint 7981 Statistics for this ePrint Item