depthai
depthai copied to clipboard
luxonis
DepthAI Python API utilities, examples, and tutorials.
### Start with the `why`: NN performance (both latency and throughput) can vary largely depending on allocated resources to the NN ([some docs here](https://docs.luxonis.com/projects/api/en/latest/tutorials/low-latency/#increasing-nn-resources)). As mentioned in docs, NN models...
**Check if issue already exists** reference docs for Latency: https://docs.luxonis.com/projects/api/tutorials/low-latency.html#low-latency **Describe the bug** very high latency when using OAK-D-W different scenes: 1. one mono on, latency is as low as...
**Describe the bug** When setting manual ISO with very small or very big values, a fatal error is thrown. **Minimal Reproducible Example** ```python import cv2 import depthai as dai pipeline...
Followed the instruction to install depthai-sdk by running: python3 -m pip install depthai-sdk on my RPi 4 with 4GB ram 32GB SD card. OS Details: PRETTY_NAME="Raspbian GNU/Linux 10 (buster)" NAME="Raspbian...
### Start with the `why`: Many customers have already shown interest in robust multi-device object (people, vehicle..) tracking. ### Move to the `what`: Develop a demo that showcases how customers...
Start with the `why`: As it stands now, DepthAI returns the XYZ location of the detected object using a distance (z) averaged over the `padding_factor` specified [here](https://github.com/luxonis/depthai/blob/ac00dbd71e3d13c9eeab2316a07e8b4d40707642/depthai.py#L267) (i.e. some subset...
While designing Pipeline Builder and thinking how to go about sending blobs and other big files to the device, the following idea came to mind. DepthAI hardware features various types...
### Start with the `why`: The pixel-motion of https://github.com/luxonis/depthai/issues/132 , although plenty useful in indoor applications/etc. may not give the intended behavior (detecting things that are physically moving in the...
### Start with the `why`: In many applications that involve obstacle avoidance, it doesn’t matter what the obstacle is, i.e. the obstacles encountered are not conveniently in a PASCAL-VOC-2007 20-class...
### Start with the `why`: When doing object detection, often the object (once found) is of most interest. So having the ROI of the object detector (e.g. the highest-confidence object...