Human Dataset v2 Computer Vision Dataset
About Human Dataset v2 Dataset
This project provides an extensive computer vision resource for the detection and tracking of people in varied environments. Containing approximately 14,000 images and utilizing a pre-trained object detection model, this dataset is designed to recognize multiple categories of human presence, including pedestrians, children, and individuals in various poses, making it a highly versatile foundation for security, retail, and urban planning applications.
Ways to Use Human Dataset v2 Model
- Smart City Pedestrian Analytics: Integrate the model into urban camera networks to monitor foot traffic patterns and pedestrian density, helping city planners optimize crosswalk timings and sidewalk widths.
- Retail Store Optimization: Use the "Person" and "Human" detection classes to analyze customer movement and dwell times within a retail space, providing insights for better aisle layouts and product placement.
- Advanced Security and Surveillance: Enhance automated security systems by accurately identifying human presence in restricted areas while distinguishing between adults and children for more contextual alert protocols.
- Autonomous Robot Navigation: Empower delivery robots or service machines with the ability to safely navigate crowded environments by detecting and predicting the movement of pedestrians and individuals using wheels or strollers.
- Workplace Safety Monitoring: Deploy the model in industrial or construction settings to ensure that personnel remain in designated safe zones and to trigger immediate alerts if a person enters a high-risk machinery area.
Use Free Human Detection API
Powered by general detection model
Code
pip install inference-sdk# 1. Import the library
from inference_sdk import InferenceHTTPClient
# 2. Connect to your workspace
client = InferenceHTTPClient(
api_url="https://serverless.roboflow.com",
api_key="API_KEY"
)
# 3. Run your workflow on an image
result = client.run_workflow(
workspace_name="<YOUR_WORKSPACE>",
workflow_id="<YOUR_WORKFLOW_ID>",
images={
"image": "YOUR_IMAGE.jpg" # Path to your image file
},
parameters={
"classes": "Human"
},
use_cache=True # cache workflow definition for 15 minutes
)
# 4. Get your results
print(result)Run on custom image
Drop an image here or click to upload
Detecting classes:
Or try a test image
Roboflow Agent
Tell the agent what you want to build.
Cite This Project
LicenseCC BY 4.0If you use this dataset in a research paper, please cite it using the following BibTeX:
@misc{ human-dataset-v2-brnah_dataset,
title = { Human Dataset v2 Dataset },
type = { Open Source Dataset },
author = { Thesis },
howpublished = { \url{ https://universe.roboflow.com/thesis-xxfpt/human-dataset-v2-brnah } },
url = { https://universe.roboflow.com/thesis-xxfpt/human-dataset-v2-brnah },
journal = { Roboflow Universe },
publisher = { Roboflow },
year = { 2026 },
month = { feb },
note = { visited on 2026-07-29 },
}