Firearm Detection Using Deep Learning

Kambhatla, Akhila; Ahmed, Khaled R.

doi:10.1007/978-3-031-16075-2_13

Cited by 5 publications

(2 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Their approach achieved 96.26% accuracy and 70% of mAP in detecting weapons. In our previous research in the Big Data Software Engineer (BASE) research lab at Southern Illinois University [17], we implemented the sliding window approach and region proposal approach by two deep neural models SSD [50]and Faster R-CNN [51].…”

Section: Machine Learning Methodsmentioning

confidence: 99%

“…Weapon detection is mainly categorized into traditional & [4,5,6,7,8], image processing techniques [9,10,11,12,13], Machine Learning (ML) algorithms [14,15,16] and deep learning algorithms [17,18,19,20,21,22,23]. Traditional weapon detection techniques mainly focus on thermal/infrared and X-Ray techniques for detection are expensive and excess usage leads to radiation which cause deadly diseases like cancer and malignant tumours [24].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Real Time Deep Learning Weapon Detection Techniques for Mitigating Lone Wolf Attacks

Kambhatla¹,

Khaled²

2023

IJAIA

View full text Add to dashboard Cite

Firearm Shootings and stabbings attacks are intense and result in severe trauma and threat to public safety. Technology is needed to prevent lone-wolf attacks without human supervision. Hence designing an automatic weapon detection using deep learning, is an optimized solution to localize and detect the presence of weapon objects using Neural Networks. This research focuses on both unified and II-stage object detectors whose resultant model not only detects the presence of weapons but also classifies with respective to its weapon classes, including handgun, knife, revolver, and rifle, along with person detection. This research focuses on YOLOv5 (You Look Only Once) family and Faster RCNN family for model validation and training. Pruning and Ensembling techniques were applied to YOLOv5 to enhance their speed and performance. YOLOv5 models achieve the highest score of 78% with an inference speed of 8.1ms. However, Faster R-CNN models achieve the highest AP 89%.

show abstract

Section: Machine Learning Methodsmentioning

confidence: 99%