Human activities Computer Vision Project
Updated 3 months ago
0
0
Metrics
Project Description:
This project aims to develop an intelligent surveillance system for a call center's work area and break area, using annotated image data to detect and analyze workers' activities. The goal is to identify unwanted activities, monitor the duration of these activities, and track the time spent by workers in the break area.
The system is designed to analyze live camera feeds from the work area, detecting various activities such as "working," "not working," "talking," "using a cell phone," and "eating." By annotating the image data with these classes, the system can accurately identify and monitor when workers engage in activities that deviate from their expected tasks. Additionally, the system will detect how long each worker remains engaged in any unwanted activity.
Moreover, the project extends to the break area, where the system will track the time each worker spends during their break. Annotated images from the break area will be used to train the model, enabling the system to differentiate between work-related activities and break times accurately.
This system will help enhance productivity by providing real-time monitoring and ensuring workers adhere to their designated roles and break times.
Use This Trained Model
Try it in your browser, or deploy via our Hosted Inference API and other deployment methods.
Build Computer Vision Applications Faster with Supervision
Visualize and process your model results with our reusable computer vision tools.
Cite This Project
If you use this dataset in a research paper, please cite it using the following BibTeX:
@misc{
human-activities-0yexl_dataset,
title = { Human activities Dataset },
type = { Open Source Dataset },
author = { call center },
howpublished = { \url{ https://universe.roboflow.com/call-center/human-activities-0yexl } },
url = { https://universe.roboflow.com/call-center/human-activities-0yexl },
journal = { Roboflow Universe },
publisher = { Roboflow },
year = { 2024 },
month = { aug },
note = { visited on 2024-11-23 },
}