Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Update camera example to support face detection and recognition #6603

Merged
merged 2 commits into from
Apr 21, 2022

Conversation

me-no-dev
Copy link
Member

@me-no-dev me-no-dev commented Apr 21, 2022

Fixes: #6508

@github-actions
Copy link
Contributor

github-actions bot commented Apr 21, 2022

Unit Test Results

0 files  0 suites   0s ⏱️
0 tests 0 ✔️ 0 💤 0

Results for commit 25333db.

♻️ This comment has been updated with latest results.

@VojtechBartoska VojtechBartoska linked an issue Apr 21, 2022 that may be closed by this pull request
1 task
@me-no-dev me-no-dev merged commit 12045d3 into master Apr 21, 2022
@me-no-dev me-no-dev deleted the feature/camera_face branch April 21, 2022 14:48
Jason2866 added a commit to tasmota/arduino-esp32 that referenced this pull request Apr 21, 2022
* Delete stale.yml

* IDF release/v4.4 b8050b365e (espressif#6594)

* Update camera example to support face detection and recognition (espressif#6603)

Fixes: espressif#6508

* Change pinMode OUTPUT to INPUT_OUTPUT (espressif#6602)

* Change OUTPUT to INPUT_OUTPUT

To match the official Arduino API.

* Changed type of LEDC frequency from double to uint32_t (espressif#6570)

* BUGFIX: FS read + speed improvements for SD (espressif#6569)

* Revert "Edited VFSFileImpl::read to use both read/fread (espressif#6456)"

This reverts commit 7b89b39.

* Added default file buffer size + function to change it by user

* workflows/publish.yml: Run the workflow on success and failure only. (espressif#6531)

* workflows/publish.yml: Run the workflow on success and failure only.
This prevents trying to run when the trigger was cancelled or skipped.
In these cases there will be no event file to upload.

Signed-off-by: Abdelatif Guettouche <[email protected]>

* scripts/sketch_utils.sh: Move the logic that gets the build dir after
the part that retrieves the arguments.

Signed-off-by: Abdelatif Guettouche <[email protected]>

* workflows/hil.yml: Update the HIL runners tags.

Signed-off-by: Abdelatif Guettouche <[email protected]>

* workflows/hil.yml: Remove the Check Artifacts step.  That was only
useful for debugging.

Signed-off-by: Abdelatif Guettouche <[email protected]>

* Pull request/Issue Templates and Readme update (espressif#6577)

* Templates and readme

* Templates_and_readme

* Delete libraries/RainMaker directory

* Delete tools/sdk/esp32/include/esp_rainmaker directory

* Delete tools/sdk/esp32s2/include/esp_rainmaker directory

* Delete tools/sdk/esp32s3/include/esp_rainmaker directory

* Delete tools/sdk/esp32c3/include/esp_rainmaker directory

Co-authored-by: Me No Dev <[email protected]>
Co-authored-by: Jan Procházka <[email protected]>
Co-authored-by: Abdelatif Guettouche <[email protected]>
Co-authored-by: Vojtěch Bartoška <[email protected]>
@HaydenHu
Copy link

The enroll face button cannot register faces

@me-no-dev
Copy link
Member Author

recognition does not work at all on chips other than ESP32-S3. Is that what you are running?

@HaydenHu
Copy link

HaydenHu commented Apr 22, 2022

image
I'm using this development board, which uses esp32, not esp32s3。
Isn't esp32 supported yet?

@me-no-dev
Copy link
Member Author

The updated AI library for image recognition does work on ESP32, but it would take 20 seconds to run a single 320x240 frame (compared to a few hundred milliseconds on ESP32-S3), so I have disabled it on ESP32 and ESP32-S2 to save flash space and memory. If you really want face recognition, maybe go back to 1.0.6.

Jason2866 added a commit to tasmota/arduino-esp32 that referenced this pull request Apr 24, 2022
* Delete stale.yml

* IDF release/v4.4 b8050b365e (espressif#6594)

* Update camera example to support face detection and recognition (espressif#6603)

Fixes: espressif#6508

* Change pinMode OUTPUT to INPUT_OUTPUT (espressif#6602)

* Change OUTPUT to INPUT_OUTPUT

To match the official Arduino API.

* Changed type of LEDC frequency from double to uint32_t (espressif#6570)

* BUGFIX: FS read + speed improvements for SD (espressif#6569)

* Revert "Edited VFSFileImpl::read to use both read/fread (espressif#6456)"

This reverts commit 7b89b39.

* Added default file buffer size + function to change it by user

* workflows/publish.yml: Run the workflow on success and failure only. (espressif#6531)

* workflows/publish.yml: Run the workflow on success and failure only.
This prevents trying to run when the trigger was cancelled or skipped.
In these cases there will be no event file to upload.

Signed-off-by: Abdelatif Guettouche <[email protected]>

* scripts/sketch_utils.sh: Move the logic that gets the build dir after
the part that retrieves the arguments.

Signed-off-by: Abdelatif Guettouche <[email protected]>

* workflows/hil.yml: Update the HIL runners tags.

Signed-off-by: Abdelatif Guettouche <[email protected]>

* workflows/hil.yml: Remove the Check Artifacts step.  That was only
useful for debugging.

Signed-off-by: Abdelatif Guettouche <[email protected]>

* Pull request/Issue Templates and Readme update (espressif#6577)

Co-authored-by: Me No Dev <[email protected]>
Co-authored-by: Jan Procházka <[email protected]>
Co-authored-by: Abdelatif Guettouche <[email protected]>
Co-authored-by: Vojtěch Bartoška <[email protected]>
nvs, data, nvs, 0x9000, 0x5000,
otadata, data, ota, 0xe000, 0x2000,
app0, app, ota_0, 0x10000, 0x3d0000,
fr, data, , 0x3e0000, 0x20000,

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

coredump, data, coredump,0x3F0000,0x10000,

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

Face Detection in CameraWebServer Example Not Working in 2.0.3
3 participants