Abstract
The conventional surveillance and control system of Closed-Circuit Television (CCTV) cameras require human resource supervision. Almost all the criminal activities take place using weapons mostly handheld gun, revolver, or pistol. Automatic gun detection is a vital requirement now-a-days. The use of real-time object detection system for the improvement of surveillance is a promising application of Convolutional Neural Networks (CNN). We are concerned about the real-time detection of weapons for the surveillance cameras, so we focused on the implementation and comparison of faster approaches such as Region (R-CNN) and Region Fully Convolutional Networks (R-FCN) with feature extractor Visual Geometry Group (VGG) and ResNet respectively. Training and testing are done on database that consists of local environment images. These images are taken with different type and high- resolution cameras that minimize the idealism. Some metrics also defined to reduce the false positives which are specific to the solution of problem. This research also contributes to the constitution of a hybrid CNN model of both faster-based R-CNN and R-FCN. Both hybrid and existing models experimented to reduce false positive in weapon detection. Result represented in graph with calculation during and after training with confusion matrix and hybrid model results better than other models.
Highlights
The population of the world is increasing exponentially, so it becomes impossible to keep conventional security methods in practice any further
We are concerned about the real-time detection of weapons for the surveillance cameras, so we focused on the implementation and comparison of faster approaches such as Region (R-Convolutional Neural Networks (CNN)) and Region Fully Convolutional Networks (R-FCN) with feature extractor Visual Geometry Group (VGG) and ResNet respectively
The proposed system to reduce false positives in the weapon detection system is evaluated
Summary
The population of the world is increasing exponentially, so it becomes impossible to keep conventional security methods in practice any further. There might be negligence, misconception so the most suitable solution of this particular domain is to the deployment of surveillance cameras along with automatic hand-held weapon detection with the alert trigging system These observations forced the researchers on a need for an active surveillance system that works on automated weapon detection algorithms. These algorithms help the operator in detecting and recognizing the presence of guns in real-time. The R-CNN model works by combining region proposals using different CNNs. The R-CNN uses a small amount of detection data to localize and train the objects using a deep network. These pre-trained models are being used and modified to get significant results in this research
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have