Home

Awesome

GitHub license GitHub top language GitHub stars

Vision Counter: Object Counting Library using Deep Learning

VisionCounter is a powerful Python library that provides a collection of deep learning models for accurately counting objects in input images. Whether you need to count people in a crowded street, cars in a parking lot, or any other objects in a scene, VisionCounter has got you covered.

<div style="text-align: center;"> <img src="./images/logo.png" alt="logo" /> </div>

Key Features

Quick Start

Install the library using pip

pip install vision_counter

Usage

from sys import argv
from vision_counter import CounTR

counter = CounTR()
bboxes = [[[156, 112], [173, 129]]]  # x1, y1, x2, y2

image_path = argv[1]
object_count = counter.count(image_path, bboxes)
print("Estimated object count:", object_count)

Contributing

We welcome contributions from the community! Whether it's bug fixes, feature enhancements, or new models, feel free to submit pull requests.

Citation

@article{liu2022countr,
  author = {Chang, Liu and Yujie, Zhong and Andrew, Zisserman and Weidi, Xie},
  title = {CounTR: Transformer-based Generalised Visual Counting},
  journal = {arXiv:2208.13721},
  year = {2022}
}