[v6,2/3] libcamera: Add face detection controls
diff mbox series

Message ID 20240923144921.1729183-3-chenghaoyang@google.com
State Superseded
Headers show
Series
  • Add Face Detection Controls
Related show

Commit Message

Harvey Yang Sept. 23, 2024, 2:45 p.m. UTC
From: Yudhistira Erlandinata <yerlandinata@chromium.org>

Add FaceDetectMode, FaceDetectFaceRectangles, FaceDetectFaceScores,
and FaceDetectFaceLandmark. Also add ControlTypePoint for supporting
FaceDetectFaceLandmark.

Signed-off-by: Yudhistira Erlandinata <yerlandinata@chromium.org>
Co-developed-by: becker hsieh <beckerh@chromium.org>
Co-developed-by: Harvey Yang <chenghaoyang@chromium.org>
---
 include/libcamera/controls.h           |  6 ++
 include/libcamera/meson.build          |  3 +-
 src/libcamera/control_ids_android.yaml | 98 ++++++++++++++++++++++++++
 src/libcamera/control_ranges.yaml      |  1 +
 src/libcamera/controls.cpp             |  6 ++
 5 files changed, 113 insertions(+), 1 deletion(-)
 create mode 100644 src/libcamera/control_ids_android.yaml

Comments

Cheng-Hao Yang Sept. 23, 2024, 2:51 p.m. UTC | #1
On Mon, Sep 23, 2024 at 10:49 PM Harvey Yang <chenghaoyang@chromium.org>
wrote:

> From: Yudhistira Erlandinata <yerlandinata@chromium.org>
>
> Add FaceDetectMode, FaceDetectFaceRectangles, FaceDetectFaceScores,
> and FaceDetectFaceLandmark. Also add ControlTypePoint for supporting
> FaceDetectFaceLandmark.
>
> Signed-off-by: Yudhistira Erlandinata <yerlandinata@chromium.org>
> Co-developed-by: becker hsieh <beckerh@chromium.org>
> Co-developed-by: Harvey Yang <chenghaoyang@chromium.org>
> ---
>  include/libcamera/controls.h           |  6 ++
>  include/libcamera/meson.build          |  3 +-
>  src/libcamera/control_ids_android.yaml | 98 ++++++++++++++++++++++++++
>  src/libcamera/control_ranges.yaml      |  1 +
>  src/libcamera/controls.cpp             |  6 ++
>  5 files changed, 113 insertions(+), 1 deletion(-)
>  create mode 100644 src/libcamera/control_ids_android.yaml
>
> diff --git a/include/libcamera/controls.h b/include/libcamera/controls.h
> index 7c2bb287..bf1b8609 100644
> --- a/include/libcamera/controls.h
> +++ b/include/libcamera/controls.h
> @@ -34,6 +34,7 @@ enum ControlType {
>         ControlTypeString,
>         ControlTypeRectangle,
>         ControlTypeSize,
> +       ControlTypePoint,
>  };
>
>  namespace details {
> @@ -87,6 +88,11 @@ struct control_type<Size> {
>         static constexpr ControlType value = ControlTypeSize;
>  };
>
> +template<>
> +struct control_type<Point> {
> +       static constexpr ControlType value = ControlTypePoint;
> +};
> +
>  template<typename T, std::size_t N>
>  struct control_type<Span<T, N>> : public
> control_type<std::remove_cv_t<T>> {
>  };
> diff --git a/include/libcamera/meson.build b/include/libcamera/meson.build
> index a969a95d..4fff14d2 100644
> --- a/include/libcamera/meson.build
> +++ b/include/libcamera/meson.build
> @@ -34,6 +34,7 @@ libcamera_headers_install_dir = get_option('includedir')
> / libcamera_include_dir
>
>  controls_map = {
>      'controls': {
> +        'android': 'control_ids_android.yaml',
>          'draft': 'control_ids_draft.yaml',
>          'core': 'control_ids_core.yaml',
>          'rpi/vc4': 'control_ids_rpi.yaml',
> @@ -55,7 +56,7 @@ foreach mode, entry : controls_map
>      files_list = []
>      input_files = []
>      foreach vendor, header : entry
> -        if vendor != 'core' and vendor != 'draft'
> +        if vendor != 'core' and vendor != 'draft' and vendor != 'android'
>              if vendor not in pipelines
>                  continue
>              endif
> diff --git a/src/libcamera/control_ids_android.yaml
> b/src/libcamera/control_ids_android.yaml
> new file mode 100644
> index 00000000..8b0d624f
> --- /dev/null
> +++ b/src/libcamera/control_ids_android.yaml
> @@ -0,0 +1,98 @@
> +# SPDX-License-Identifier: LGPL-2.1-or-later
> +#
> +# Copyright (C) 2024, Google Inc.
> +#
> +%YAML 1.1
> +---
> +# Unless otherwise stated, all controls are bi-directional, i.e. they can
> be
> +# set through Request::controls() and returned out through
> Request::metadata().
> +vendor: android
> +controls:
> +  - FaceDetectMode:
> +      type: uint8_t
> +      description: |
> +        Reporting mode of face detection.
> +
> +        Currently identical to ANDROID_STATISTICS_FACE_DETECT_MODE.
> +
> +        \sa FaceDetectFaceRectangles
> +        \sa FaceDetectFaceScores
> +        \sa FaceDetectFaceLandmarks
> +        \sa FaceDetectFaceIds
> +
> +      enum:
> +        - name: FaceDetectModeOff
> +          value: 0
> +          description: |
> +            Pipeline should not report face detection result.
> +        - name: FaceDetectModeSimple
> +          value: 1
> +          description: |
> +            Pipeline should at least report FaceDetectFaceRectangles and
> +            FaceDetectFaceScores for each detected faces.
> +            FaceDetectFaceLandmarks and FaceDetectFaceIds is optional.
> +
> +        - name: FaceDetectModeFull
> +          value: 2
> +          description: |
> +            Pipeline should report all face controls, including
> +            FaceDetectFaceRectangles, FaceDetectFaceScores,
> +            FaceDetectFaceLandmarks, and FaceDeteceFaceIds.
> +
> +  - FaceDetectFaceRectangles:
> +      type: Rectangle
> +      description: |
> +        Boundary rectangles of the detected faces.
> +        The number of values should be the number of faces reported in
> +        FaceDetectFaceRectangles.
> +
> +        The FaceDetectFaceRectangles control can only be returned in
> metadata.
> +
> +        Currently identical to ANDROID_STATISTICS_FACE_RECTANGLES.
> +
> +      size: [n]
> +
> +  - FaceDetectFaceScores:
> +      type: uint8_t
> +      description: |
> +        Confidence score of each of the detected faces by face detector.
> +        The range of score is [0, 100].
> +        The FaceDetectFaceScores control can only be returned in metadata.
> +        The number of values should be the number of faces reported in
> +        FaceDetectFaceRectangles.
> +
> +        Currently identical to ANDROID_STATISTICS_FACE_SCORES.
> +
> +      size: [n]
> +
> +  - FaceDetectFaceLandmarks:
> +      type: Point
> +      description: |
> +        Array of human face landmark coordinates in format:
> +        [..., left_eye_i, right_eye_i, mouth_i, left_eye_i+1, ...],
> +        with i = index of face.
> +        The number of values should be 3 * the number of faces reported in
> +        FaceDetectFaceRectangles.
> +
> +        The FaceDetectFaceLandmarks control can only be returned in
> metadata.
> +
> +        Currently identical to ANDROID_STATISTICS_FACE_LANDMARKS.
> +
> +      size: [n]
> +
> +  - FaceDetectFaceIds:
> +      type: int32_t
> +      description: |
> +        Each detected face is given a unique ID that is valid for as long
> as
> +        the face is visible to the camera device. A face that leaves the
> field
> +        of view and later returns may be assigned a new ID.
> +        The number of values should be the number of faces reported in
> +        FaceDetectFaceRectangles.
> +
> +        The FaceDetectFaceIds control can only be returned in metadata.
> +
> +        Currently identical to ANDROID_STATISTICS_FACE_IDS.
> +
> +      size: [n]
> +
> +...
> diff --git a/src/libcamera/control_ranges.yaml
> b/src/libcamera/control_ranges.yaml
> index d42447d0..5c6ca414 100644
> --- a/src/libcamera/control_ranges.yaml
> +++ b/src/libcamera/control_ranges.yaml
> @@ -14,5 +14,6 @@ ranges:
>    # Raspberry Pi vendor controls
>    rpi: 20000
>    # Next range starts at 30000
> +  android: 30000
>

Sorry, I should've updated the comments as well.
Will update in the next version with other changes to prevent
spamming.


>
>  ...
> diff --git a/src/libcamera/controls.cpp b/src/libcamera/controls.cpp
> index dba74404..c452e607 100644
> --- a/src/libcamera/controls.cpp
> +++ b/src/libcamera/controls.cpp
> @@ -60,6 +60,7 @@ static constexpr size_t ControlValueSize[] = {
>         [ControlTypeString]             = sizeof(char),
>         [ControlTypeRectangle]          = sizeof(Rectangle),
>         [ControlTypeSize]               = sizeof(Size),
> +       [ControlTypePoint]              = sizeof(Point),
>  };
>
>  } /* namespace */
> @@ -254,6 +255,11 @@ std::string ControlValue::toString() const
>                         str += value->toString();
>                         break;
>                 }
> +               case ControlTypePoint: {
> +                       const Point *value = reinterpret_cast<const Point
> *>(data);
> +                       str += value->toString();
> +                       break;
> +               }
>                 case ControlTypeNone:
>                 case ControlTypeString:
>                         break;
> --
> 2.46.0.792.g87dc391469-goog
>
>

Patch
diff mbox series

diff --git a/include/libcamera/controls.h b/include/libcamera/controls.h
index 7c2bb287..bf1b8609 100644
--- a/include/libcamera/controls.h
+++ b/include/libcamera/controls.h
@@ -34,6 +34,7 @@  enum ControlType {
 	ControlTypeString,
 	ControlTypeRectangle,
 	ControlTypeSize,
+	ControlTypePoint,
 };
 
 namespace details {
@@ -87,6 +88,11 @@  struct control_type<Size> {
 	static constexpr ControlType value = ControlTypeSize;
 };
 
+template<>
+struct control_type<Point> {
+	static constexpr ControlType value = ControlTypePoint;
+};
+
 template<typename T, std::size_t N>
 struct control_type<Span<T, N>> : public control_type<std::remove_cv_t<T>> {
 };
diff --git a/include/libcamera/meson.build b/include/libcamera/meson.build
index a969a95d..4fff14d2 100644
--- a/include/libcamera/meson.build
+++ b/include/libcamera/meson.build
@@ -34,6 +34,7 @@  libcamera_headers_install_dir = get_option('includedir') / libcamera_include_dir
 
 controls_map = {
     'controls': {
+        'android': 'control_ids_android.yaml',
         'draft': 'control_ids_draft.yaml',
         'core': 'control_ids_core.yaml',
         'rpi/vc4': 'control_ids_rpi.yaml',
@@ -55,7 +56,7 @@  foreach mode, entry : controls_map
     files_list = []
     input_files = []
     foreach vendor, header : entry
-        if vendor != 'core' and vendor != 'draft'
+        if vendor != 'core' and vendor != 'draft' and vendor != 'android'
             if vendor not in pipelines
                 continue
             endif
diff --git a/src/libcamera/control_ids_android.yaml b/src/libcamera/control_ids_android.yaml
new file mode 100644
index 00000000..8b0d624f
--- /dev/null
+++ b/src/libcamera/control_ids_android.yaml
@@ -0,0 +1,98 @@ 
+# SPDX-License-Identifier: LGPL-2.1-or-later
+#
+# Copyright (C) 2024, Google Inc.
+#
+%YAML 1.1
+---
+# Unless otherwise stated, all controls are bi-directional, i.e. they can be
+# set through Request::controls() and returned out through Request::metadata().
+vendor: android
+controls:
+  - FaceDetectMode:
+      type: uint8_t
+      description: |
+        Reporting mode of face detection.
+
+        Currently identical to ANDROID_STATISTICS_FACE_DETECT_MODE.
+
+        \sa FaceDetectFaceRectangles
+        \sa FaceDetectFaceScores
+        \sa FaceDetectFaceLandmarks
+        \sa FaceDetectFaceIds
+
+      enum:
+        - name: FaceDetectModeOff
+          value: 0
+          description: |
+            Pipeline should not report face detection result.
+        - name: FaceDetectModeSimple
+          value: 1
+          description: |
+            Pipeline should at least report FaceDetectFaceRectangles and
+            FaceDetectFaceScores for each detected faces.
+            FaceDetectFaceLandmarks and FaceDetectFaceIds is optional.
+
+        - name: FaceDetectModeFull
+          value: 2
+          description: |
+            Pipeline should report all face controls, including
+            FaceDetectFaceRectangles, FaceDetectFaceScores,
+            FaceDetectFaceLandmarks, and FaceDeteceFaceIds.
+
+  - FaceDetectFaceRectangles:
+      type: Rectangle
+      description: |
+        Boundary rectangles of the detected faces.
+        The number of values should be the number of faces reported in
+        FaceDetectFaceRectangles.
+
+        The FaceDetectFaceRectangles control can only be returned in metadata.
+
+        Currently identical to ANDROID_STATISTICS_FACE_RECTANGLES.
+
+      size: [n]
+
+  - FaceDetectFaceScores:
+      type: uint8_t
+      description: |
+        Confidence score of each of the detected faces by face detector.
+        The range of score is [0, 100].
+        The FaceDetectFaceScores control can only be returned in metadata.
+        The number of values should be the number of faces reported in
+        FaceDetectFaceRectangles.
+
+        Currently identical to ANDROID_STATISTICS_FACE_SCORES.
+
+      size: [n]
+
+  - FaceDetectFaceLandmarks:
+      type: Point
+      description: |
+        Array of human face landmark coordinates in format:
+        [..., left_eye_i, right_eye_i, mouth_i, left_eye_i+1, ...],
+        with i = index of face.
+        The number of values should be 3 * the number of faces reported in
+        FaceDetectFaceRectangles.
+
+        The FaceDetectFaceLandmarks control can only be returned in metadata.
+
+        Currently identical to ANDROID_STATISTICS_FACE_LANDMARKS.
+
+      size: [n]
+
+  - FaceDetectFaceIds:
+      type: int32_t
+      description: |
+        Each detected face is given a unique ID that is valid for as long as
+        the face is visible to the camera device. A face that leaves the field
+        of view and later returns may be assigned a new ID.
+        The number of values should be the number of faces reported in
+        FaceDetectFaceRectangles.
+
+        The FaceDetectFaceIds control can only be returned in metadata.
+
+        Currently identical to ANDROID_STATISTICS_FACE_IDS.
+
+      size: [n]
+
+...
diff --git a/src/libcamera/control_ranges.yaml b/src/libcamera/control_ranges.yaml
index d42447d0..5c6ca414 100644
--- a/src/libcamera/control_ranges.yaml
+++ b/src/libcamera/control_ranges.yaml
@@ -14,5 +14,6 @@  ranges:
   # Raspberry Pi vendor controls
   rpi: 20000
   # Next range starts at 30000
+  android: 30000
 
 ...
diff --git a/src/libcamera/controls.cpp b/src/libcamera/controls.cpp
index dba74404..c452e607 100644
--- a/src/libcamera/controls.cpp
+++ b/src/libcamera/controls.cpp
@@ -60,6 +60,7 @@  static constexpr size_t ControlValueSize[] = {
 	[ControlTypeString]		= sizeof(char),
 	[ControlTypeRectangle]		= sizeof(Rectangle),
 	[ControlTypeSize]		= sizeof(Size),
+	[ControlTypePoint]		= sizeof(Point),
 };
 
 } /* namespace */
@@ -254,6 +255,11 @@  std::string ControlValue::toString() const
 			str += value->toString();
 			break;
 		}
+		case ControlTypePoint: {
+			const Point *value = reinterpret_cast<const Point *>(data);
+			str += value->toString();
+			break;
+		}
 		case ControlTypeNone:
 		case ControlTypeString:
 			break;