Related Experiment Video
Updated: Jul 18, 2026
10:56
Long-term Behavioral Tracking of Freely Swimming Weakly Electric Fish
Published on: March 6, 2014
Real-time gun detection in CCTV: An open problem
Jose L Salazar González1, Carlos Zaccaro1, Juan A Álvarez-García1
1Dpto. de Lenguajes y Sistemas Informáticos, Universidad de Sevilla, 41012, Sevilla, Spain.
Summary
This study introduces a new dataset and Faster R-CNN model for detecting weapons in real-time on CCTV footage. The approach significantly improves weapon detection accuracy, benefiting security and counter-terrorism efforts.
Area of Science:
- Computer Vision
- Artificial Intelligence
- Security Systems
Background:
- Small object detection remains a challenge for current object detectors.
- Autonomous weapons detection in Closed-circuit television (CCTV) is crucial for security and risk mitigation.
Purpose of the Study:
- To develop an effective weapon detection model for quasi real-time CCTV applications.
- To evaluate the impact of synthetic datasets on training weapon detection systems.
Main Methods:
- Applied Faster R-CNN with Feature Pyramid Network and ResNet-50 to real and synthetic CCTV data.
- Utilized a two-stage training approach for enhanced detection.
- Achieved an inference time of 90 ms on an NVIDIA GeForce GTX-1080Ti.
Main Results:
- Developed a weapon detection model with improved state-of-the-art performance.
- Demonstrated the effectiveness of synthetic datasets in augmenting real-world CCTV data.
- Identified current limitations in automated weapon detection systems.
Conclusions:
- The proposed method offers a viable solution for quasi real-time weapon detection in CCTV.
- Synthetic data generation is a valuable technique for improving the robustness of weapon detection models.
- Further research is needed to address the inherent limitations of current detection systems.
Related Concept Videos
01:10Detection of Black Holes
Although black holes were theoretically postulated in the 1920s, they remained outside the domain of observational astronomy until the 1970s.
Their closest cousins are neutron stars, which are composed almost entirely of neutrons packed against each other, making them extremely dense. A neutron star has the same mass as the Sun but its diameter is only a few kilometers. Therefore, the escape velocity from their surface is close to the speed of light.
Not until the 1960s, when the first neutron...
Their closest cousins are neutron stars, which are composed almost entirely of neutrons packed against each other, making them extremely dense. A neutron star has the same mass as the Sun but its diameter is only a few kilometers. Therefore, the escape velocity from their surface is close to the speed of light.
Not until the 1960s, when the first neutron...
01:05Difference from Background: Limit of Detection
The limit of detection (LOD) is the smallest amount of analyte that can be distinguished from the background noise. The LOD value corresponds to the concentration at which the analyte signal is three times larger than the standard deviation of the blank signal. Below this value, the analyte signal cannot be differentiated from the background noise. It is calculated by dividing the calibration slope by 3 times the standard deviation of the blank signals.
The LOD indicates the presence or absence...
The LOD indicates the presence or absence...
01:29Real-World Applications of Space Curves
Modern aerospace navigation depends on the accurate prediction of motion in three-dimensional space. In defense applications, radar systems continuously track both interceptors and moving aerial targets to find whether their flight paths will result in a collision. These motions are modeled mathematically as space curves, which represent paths that change continuously with time. Each object’s position is described by a vector function that specifies its location in terms of time-dependent...