https://github.com/nizarassad/weapon-detection

This project addresses the escalating challenge of gun violence through the development of an advanced gun detection system.
https://github.com/nizarassad/weapon-detection

cctv-detection data-science deep-learning jupyter-notebook machine-learning object-detection python real-time-object-detection real-time-object-detection-models real-time-object-tracker roboflow vgg16 yolov5 yolov7 yolov8

Last synced: about 22 hours ago
JSON representation

This project addresses the escalating challenge of gun violence through the development of an advanced gun detection system.

• Host: GitHub
• URL: https://github.com/nizarassad/weapon-detection
• Owner: Nizarassad
• Created: 2024-07-27T14:53:06.000Z (5 months ago)
• Default Branch: main
• Last Pushed: 2024-08-05T21:16:18.000Z (5 months ago)
• Last Synced: 2024-11-07T04:16:44.583Z (about 2 months ago)
• Topics: cctv-detection, data-science, deep-learning, jupyter-notebook, machine-learning, object-detection, python, real-time-object-detection, real-time-object-detection-models, real-time-object-tracker, roboflow, vgg16, yolov5, yolov7, yolov8
• Language: Jupyter Notebook
• Homepage:
• Size: 16.8 MB
• Stars: 6
• Watchers: 1
• Forks: 2
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        

# Weapon-Detection

 Ensuring effective gun detection is vital in contemporary times to address escalating concerns about public safety and combat the increasing occurrences of crimes.This project aims to enhance gun detection models by fine-tuning various deep learning architectures. 

 



  



## 🎯 Goals

- Achieve superior accuracy compared to existing gun detection models.

- Experiment with hyperparameter tuning to find optimal configurations.

- Focus on reducing false positive predictions while increasing precision.

- Develop a robust model that can adapt to different scenarios and perform well in various environments.

## Architectures Used

- VGG16

- YOLOv5

- YOLOv7

- YOLOv8

### ✨ Model Performance Comparison

In this section, we compare the performance of all four models on the test set

| Model   | Precision | Recall | F1 Score | mAP_0.5 | Test Time |

|---------|-----------|--------|----------|---------|-----------|

| Yolov5s | 0.89      | 0.77   | 0.83     | 0.84    | 10s       |

| Yolov7  | 0.81      | 0.73   | 0.80     | 0.80    | 13s       |

| Yolov8s | 0.91      | 0.75   | 0.83     | 0.83    | 9s        |

| VGG16   | 0.86      | 0.85   | 0.82     | 0.81    | 20s       |

## 📚 Dataset

- Download the dataset for custom training

- https://universe.roboflow.com/upc-tf3xi/guns-dataset-j8cz1

## Download Object Detection Models

- Download the object detection models manyally through this link:

- https://drive.google.com/drive/folders/1o37wWBGuH7HGw9sc2HK1VMCc3maSKQuM?usp=sharing

- Download the weight file and place it in "models" folder