The LandingLens Python library contains the LandingLens development library and examples that show how to integrate your app with LandingLens in a variety of scenarios. The examples cover different model types, image acquisition sources, and post-procesing techniques.
First, install the LandingAI Python library:
pip install landingaiAfter installing the LandingAI Python library, you can start acquiring images from one of many image sources.
For example, from a single image file:
from landingai.pipeline.frameset import Frame
frame = Frame.from_image("/path/to/your/image.jpg")
frame.resize(width=512, height=512)
frame.save_image("/tmp/resized-image.png")You can also extract frames from your webcam. For example:
from landingai.pipeline.image_source import Webcam
with Webcam(fps=0.5) as webcam:
for frame in webcam:
frame.resize(width=512, height=512)
frame.save_image("/tmp/webcam-image.png")To learn how to acquire images from more sources, go to Image Acquisition.
If you have deployed a computer vision model in LandingLens, you can use this library to send images to that model for inference.
For example, let's say we've created and deployed a model in LandingLens that detects coffee mugs. Now, we'll use the code below to extract images (frames) from a webcam and run inference on those images.
Note
If you don't have a LandingLens account, create one here. You will need to get an "endpoint ID" and "API key" from LandingLens in order to run inferences. Check our Running Inferences / Getting Started.
Note
Learn how to use LandingLens from our Support Center and Video Tutorial Library. Need help with specific use cases? Post your questions in our Community.
from landingai.pipeline.image_source import Webcam
from landingai.predict import Predictor
predictor = Predictor(
endpoint_id="abcdef01-abcd-abcd-abcd-01234567890",
api_key="land_sk_xxxxxx",
)
with Webcam(fps=0.5) as webcam:
for frame in webcam:
frame.resize(width=512)
frame.run_predict(predictor=predictor)
frame.overlay_predictions()
if "coffee-mug" in frame.predictions:
frame.save_image("/tmp/latest-webcam-image.png", include_predictions=True)We've provided some examples in Jupyter Notebooks to focus on ease of use, and some examples in Python apps to provide a more robust and complete experience.
| Example | Description | Type |
|---|---|---|
| Poker Card Suit Identification | This notebook shows how to use an object detection model from LandingLens to detect suits on playing cards. A webcam is used to take photos of playing cards. | Jupyter Notebook  |
| Door Monitoring for Home Automation | This notebook shows how to use an object detection model from LandingLens to detect whether a door is open or closed. An RTSP camera is used to acquire images. | Jupyter Notebook |
| Satellite Images and Post-Processing | This notebook shows how to use a Visual Prompting model from LandingLens to identify different objects in satellite images. The notebook includes post-processing scripts that calculate the percentage of ground cover that each object takes up. | Jupyter Notebook |
| License Plate Detection and Recognition | This notebook shows how to extract frames from a video file and use a object detection model and OCR from LandingLens to identify and recognize different license plates. | Jupyter Notebook |
| Streaming Video | This application shows how to continuously run inference on images extracted from a streaming RTSP video camera feed. | Python application |
All the examples in this repo can be run locally.
To give you some guidance, here's how you can run the rtsp-capture example locally in a shell environment:
- Clone the repo to local:
git clone https://github.com/landing-ai/landingai-python.git - Install the library:
poetry install --with examples(See the poetry docs for how to installpoetry) - Activate the virtual environment:
poetry shell - Run:
python landingai-python/examples/capture-service/run.py