A Lightweight Deep Learning-based Weapon Detection Model for Mobile Robots

Rajeshwar Yadav, Raju Halder, Atul Thakur, Gourinath Banda*

*Kontaktforfatter

Publikation: Kapitel i bog/rapport/konference-proceedingKonferencebidrag i proceedingsForskningpeer review

Abstract

As mobile robotics continues to advance, the need for adequate surveillance in robotic environments is becoming increasingly important. Detecting suspicious objects in sensitive areas using mobile robots is challenging due to the limited computational resources available on these devices. This paper describes a new system for automatically detecting weapons in real-time video footage designed for low-computing devices in mobile robots. We present a novel weapon detection model that aims to balance the trade-off between inference time and detection accuracy, making it a lightweight model compared to existing models. The proposed model is trained and tested on existing benchmark datasets. The model is compared to existing lightweight weapon detection models to determine its suitability for low-computing devices. We obtain the mAP of 90.3%, 85.13% and 92.38% for the IITP_W, Handgun and Sohas datasets, respectively. The results outperforming the well-known PicoDet model. We envisage that the proposed model could be a useful tool for surveillance using mobile robots during events such as riots and anti-terrorist operations.

OriginalsprogEngelsk
TitelProceedings of 2023 6th International Conference on Advances in Robotics, AIR 2023
Antal sider6
ForlagAssociation for Computing Machinery / Special Interest Group on Programming Languages
Publikationsdato2. nov. 2023
Artikelnummer70
ISBN (Elektronisk)9781450399807
DOI
StatusUdgivet - 2. nov. 2023
Begivenhed6th International Conference on Advances in Robotics, AIR 2023 - Ropar, Indien
Varighed: 5. jul. 20238. jul. 2023

Konference

Konference6th International Conference on Advances in Robotics, AIR 2023
Land/OmrådeIndien
ByRopar
Periode05/07/202308/07/2023
SponsorADDVERB, et al., MathWorks, Miyuki Technologies PUT Ltd, Pukhya, QUALISYS
NavnACM International Conference Proceeding Series

Bibliografisk note

Publisher Copyright:
© 2023 ACM.

Fingeraftryk

Dyk ned i forskningsemnerne om 'A Lightweight Deep Learning-based Weapon Detection Model for Mobile Robots'. Sammen danner de et unikt fingeraftryk.

Citationsformater