Monocular Depth Estimation: is the task of estimating the depth value (distance relative to the camera) of each pixel given a single (monocular) RGB image. This challenging task is a key prerequisite for determining scene understanding for applications such as 3D scene reconstruction, autonomous driving, and AR.

Measuring the gap between two objects is known as distance calculation within a specified space. In the case of Ultralytics YOLOv8, the bounding box centroid is employed to calculate the distance for bounding boxes highlighted by the user.

• Localization Precision: Enhances accurate spatial positioning in computer vision tasks.
• Size Estimation: Allows estimation of physical sizes for better contextual understanding.
• Scene Understanding: Contributes to a 3D understanding of the environment for improved decision-making.

Download one of the provided four models of varying scales for robust relative depth estimation and keep in checkpoints directory:

git clone https://github.com/zubi9/depth_and_distance_measure.git
cd depth_and_distance_measure
pip install -r requirements.txt

To run the script for side-by-side YOLO v8 distance measurement and monocular depth estimation with a webcam:

python dnd_live_only.py

python run.py --encoder <vits | vitb | vitl | vitg> --img-path <path> --outdir <outdir> [--input-size <size>] [--pred-only] [--grayscale]

Options:

• --encoder: Choose from vits, vitb, vitl, vitg.
• --img-path: Path to an image directory, single image, or a text file with image paths.
• --input-size (optional): Default is 518. Increase for finer results.
• --pred-only (optional): Only save the predicted depth map.
• --grayscale (optional): Save the grayscale depth map without applying a color palette.

Example:

python run.py --encoder vitg --img-path assets/examples --outdir depth_vis

python run_video.py --encoder vitg --video-path assets/examples_video --outdir video_depth_vis

Note: The larger models provide better temporal consistency on videos.

To use the Gradio demo locally:

python app.py

If you find this project useful, please consider citing:

@article{depth_anything_v2,
  title={Depth Anything V2},
  author={Yang, Lihe and Kang, Bingyi and Huang, Zilong and Zhao, Zhen and Xu, Xiaogang and Feng, Jiashi and Zhao, Hengshuang},
  journal={arXiv preprint arXiv:},
  year={2024}
}

• Yolo v8: Ultralytics GitHub

• Apache License
• [GNU License]