Skip to content

Commit 42d9f27

Browse files
authored
Merge branch 'main' into update_depth_visualziation
2 parents b0fa0fe + f5117cc commit 42d9f27

File tree

11 files changed

+99
-31
lines changed

11 files changed

+99
-31
lines changed

docs/requirements_mkdoc.txt

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -1 +1 @@
1-
git+https://github.com/luxonis/pybind11_mkdoc.git@47a353ae22a3ca2fe1ca47f47b38613dcfb1043b
1+
git+https://github.com/luxonis/pybind11_mkdoc.git@59746f8d1645c9f00ebfb534186334d0154b5bd6
35.4 KB
Loading
Binary file not shown.
254 KB
Loading

docs/source/components/nodes/stereo_depth.rst

Lines changed: 2 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -1,7 +1,8 @@
11
StereoDepth
22
###########
33

4-
StereoDepth node calculates the disparity/depth from the stereo camera pair (2x :ref:`MonoCamera <MonoCamera>`/:ref:`ColorCamera`).
4+
StereoDepth node calculates the disparity and/or depth from the stereo camera pair (2x :ref:`MonoCamera <MonoCamera>`/:ref:`ColorCamera`).
5+
We suggest following :ref:`Configuring Stereo Depth` tutorial to achieve the best depth results.
56

67
How to place it
78
===============

docs/source/includes/footer-short.rst

Lines changed: 2 additions & 25 deletions
Original file line numberDiff line numberDiff line change
@@ -1,28 +1,5 @@
11
.. raw:: html
22

3-
<h2>Got questions?</h2>
3+
<h2>Got questions?</h2>
44

5-
We're always happy to help with code or other questions you might have.
6-
7-
.. raw:: html
8-
9-
<div class="cta-row cta-row-short">
10-
<div class="cta-box">
11-
<a href="https://discord.gg/luxonis">
12-
<img src="https://docs.luxonis.com/en/latest/_images/discord.png" alt="Discord"/>
13-
<h5 class="cta-title">Community Discord</h5>
14-
</a>
15-
</div>
16-
<div class="cta-box">
17-
<a href="https://discuss.luxonis.com/">
18-
<img src="https://docs.luxonis.com/en/latest/_images/forum.png" alt="forum"/>
19-
<h5 class="cta-title">Discussion Forum</h5>
20-
</a>
21-
</div>
22-
<div class="cta-box">
23-
<a href="mailto:[email protected]">
24-
<img src="https://docs.luxonis.com/en/latest/_images/email.png" alt="forum"/>
25-
<h5 class="cta-title">Email Support</h5>
26-
</a>
27-
</div>
28-
</div>
5+
Head over to <a href="https://discuss.luxonis.com/"><strong>Discussion Forum</strong></a> for technical support or any other questions you might have.
Lines changed: 49 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,49 @@
1+
Script UART communication
2+
=========================
3+
4+
This example uses :ref:`Script` node for `UART communication <https://en.wikipedia.org/wiki/Universal_asynchronous_receiver-transmitter>`__. Note that OAK
5+
cameras don't have UART pins easily disposed, and we soldered wires on `OAK-FFC-4P <https://docs.luxonis.com/projects/hardware/en/latest/pages/DD2090.html>`__
6+
to expose UART pins.
7+
8+
.. note::
9+
10+
This should only be run on OAK-FFC-4P, as other OAK cameras might have different GPIO configuration.
11+
12+
Demo
13+
####
14+
15+
.. raw:: html
16+
17+
<div style="position: relative; padding-bottom: 56.25%; height: 0; overflow: hidden; max-width: 100%; height: auto;">
18+
<iframe src="https://www.youtube.com/embed/nbS1BczO5sE" frameborder="0" allowfullscreen style="position: absolute; top: 0; left: 0; width: 100%; height: 100%;"></iframe>
19+
</div>
20+
21+
22+
.. figure:: https://user-images.githubusercontent.com/18037362/232458809-a36dc418-6bb5-411f-9172-5130a926191d.jpg
23+
24+
Oscilloscope connected to the OAK-FFC-4P UART pins
25+
26+
Setup
27+
#####
28+
29+
.. include:: /includes/install_from_pypi.rst
30+
31+
Source code
32+
###########
33+
34+
.. tabs::
35+
36+
.. tab:: Python
37+
38+
Also `available on GitHub <https://github.com/luxonis/depthai-python/blob/main/examples/Script/script_uart.py>`__
39+
40+
.. literalinclude:: ../../../../examples/Script/script_uart.py
41+
:language: python
42+
:linenos:
43+
44+
.. tab:: C++
45+
46+
Not yet available
47+
48+
49+
.. include:: /includes/footer-short.rst

docs/source/tutorials/code_samples.rst

Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -122,6 +122,7 @@ are presented with code.
122122
- :ref:`Script HTTP server` - Serve still image over HTTP response (only OAK-POE devices)
123123
- :ref:`Script MJPEG server` - Serve MJPEG video stream over HTTP response (only OAK-POE devices)
124124
- :ref:`Script NNData example` - Constructs :ref:`NNData` in Script node and sends it to the host
125+
- :ref:`Script UART communication` - UART communication with Script node
125126

126127
.. rubric:: SpatialDetection
127128

docs/source/tutorials/configuring-stereo-depth.rst

Lines changed: 3 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -277,7 +277,7 @@ just note it's a very large output (eg. 1280*800*96 => 98MB for each frame).
277277

278278
Stereo Subpixel mode will calculate subpixel disparity by looking at the confidence values of the 2 neighboring disparity pixels in each direction.
279279
In the above example graph, in normal mode, StereoDepth would just get the max disparity = 34 pixels, but in Subpixel
280-
mode, it will return a bit more, eg. 37.375 pixels, as confidences for pixels 35 and 36 are quite high as well.
280+
mode, it will return a bit more, eg. 34.375 pixels, as confidences for pixels 35 and 36 are quite high as well.
281281

282282
**TL;DR:** Stereo Subpixel mode should always provide more accurate depth, but will consume additional HW resources (see :ref:`Stereo depth FPS` for impact).
283283

@@ -287,7 +287,7 @@ Stereo subpixel effect on layering
287287
Default stereo depth output has 0..95 disparity pixels, which would produce 96 unique depth values. This can especially be seen when using pointcloud representation
288288
and seeing how there are discrete "layers" of points, instead of a smooth transition:
289289

290-
.. image:: /_static/images/components/layered-pointcloud.png
290+
.. image:: /_static/images/components/pointcloud_layering.jpg
291291

292292
This layering can especially be seen at longer distances, where these layers are exponentially further apart.
293293

@@ -375,7 +375,7 @@ as the other 2 methods above do.
375375
Disparity shift will shift the starting point of the disparity search, which will significantly decrease MaxZ, but
376376
it will also decrease the MinZ. Disparity shift can be combined with extended/subpixel/LR-check modes.
377377

378-
.. image:: https://user-images.githubusercontent.com/18037362/189375017-2fa137d2-ad6b-46de-8899-6304bbc6c9d7.png
378+
.. image:: /_static/images/components/disparity_shift.png
379379

380380
The **Left graph** shows min and max disparity and depth for OAK-D (7.5cm baseline, 800P resolution, ~70° HFOV) by default (disparity shift=0). See :ref:`Depth from disparity`.
381381
Since hardware (stereo block) has a fixed 95 pixel disparity search, DepthAI will search from 0 pixels (depth=INF) to 95 pixels (depth=71cm).

docs/source/tutorials/low-latency.rst

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -133,7 +133,7 @@ Bandwidth
133133

134134
With large, unencoded frames, one can quickly saturate the bandwidth even at 30FPS, especially on PoE devices (1gbps link):
135135

136-
.. code-block::bash
136+
.. code-block::
137137
138138
4K NV12/YUV420 frames: 3840 * 2160 * 1.5 * 30fps * 8bits = 3 gbps
139139
1080P NV12/YUV420 frames: 1920 * 1080 * 1.5 * 30fps * 8bits = 747 mbps

0 commit comments

Comments
 (0)