[FFmpeg-devel] [PATCH V6 4/6] lavu: add side data AV_FRAME_DATA_BOUNDING_BOXES

[Anton Khirnov]

Quoting Guo, Yejun (2021-03-26 09:09:29)
> Signed-off-by: Guo, Yejun <yejun.guo at intel.com>
> ---
>  doc/APIchanges          |  2 ++
>  libavutil/Makefile      |  1 +
>  libavutil/boundingbox.h | 79 +++++++++++++++++++++++++++++++++++++++++
>  libavutil/frame.c       |  1 +
>  libavutil/frame.h       |  7 ++++
>  5 files changed, 90 insertions(+)
>  create mode 100644 libavutil/boundingbox.h
> 
> diff --git a/doc/APIchanges b/doc/APIchanges
> index b41dadee8d..160b020d9d 100644
> --- a/doc/APIchanges
> +++ b/doc/APIchanges
> @@ -14,6 +14,8 @@ libavutil:     2017-10-21
>  
>  
>  API changes, most recent first:
> +2021-03-xx - xxxxxxxxxx - lavu 56.xx.100 - frame.h boundingbox.h
> +  Add AV_FRAME_DATA_BOUNDING_BOXES
>  
>  2021-03-21 - xxxxxxxxxx - lavu 56.72.100 - frame.h
>    Deprecated av_get_colorspace_name().
> diff --git a/libavutil/Makefile b/libavutil/Makefile
> index 27bafe9e12..7e1dc713ac 100644
> --- a/libavutil/Makefile
> +++ b/libavutil/Makefile
> @@ -11,6 +11,7 @@ HEADERS = adler32.h                                                     \
>            avutil.h                                                      \
>            base64.h                                                      \
>            blowfish.h                                                    \
> +          boundingbox.h                                                 \
>            bprint.h                                                      \
>            bswap.h                                                       \
>            buffer.h                                                      \
> diff --git a/libavutil/boundingbox.h b/libavutil/boundingbox.h
> new file mode 100644
> index 0000000000..5e2fdd55e9
> --- /dev/null
> +++ b/libavutil/boundingbox.h
> @@ -0,0 +1,79 @@
> +/*
> + * This file is part of FFmpeg.
> + *
> + * FFmpeg is free software; you can redistribute it and/or
> + * modify it under the terms of the GNU Lesser General Public
> + * License as published by the Free Software Foundation; either
> + * version 2.1 of the License, or (at your option) any later version.
> + *
> + * FFmpeg is distributed in the hope that it will be useful,
> + * but WITHOUT ANY WARRANTY; without even the implied warranty of
> + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
> + * Lesser General Public License for more details.
> + *
> + * You should have received a copy of the GNU Lesser General Public
> + * License along with FFmpeg; if not, write to the Free Software
> + * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
> + */
> +
> +#ifndef AVUTIL_BOUNDINGBOX_H
> +#define AVUTIL_BOUNDINGBOX_H
> +
> +#include "libavutil/rational.h"
> +
> +typedef struct AVBoundingBox {
> +    /**
> +     * Distance in pixels from the top edge of the frame to top
> +     * and bottom, and from the left edge of the frame to left and
> +     * right, defining the bounding box.
> +     */
> +    int top;
> +    int left;
> +    int bottom;
> +    int right;

Is this allowed to be negative? Can/should this be size_t?

> +
> +#define AV_BBOX_LABEL_NAME_MAX_SIZE 32
> +
> +    /**
> +     * Detect result with confidence
> +     */
> +    char detect_label[AV_BBOX_LABEL_NAME_MAX_SIZE];
> +    AVRational detect_confidence;
> +
> +    /**
> +     * At most 4 classifications based on the detected bounding box.
> +     * For example, we can get max 4 different attributes with 4 different
> +     * DNN models on one bounding box.
> +     * classify_count is zero if no classification.
> +     */
> +#define AV_NUM_BBOX_CLASSIFY 4
> +    uint32_t classify_count;

size_t?

> +    char classify_labels[AV_NUM_BBOX_CLASSIFY][AV_BBOX_LABEL_NAME_MAX_SIZE];
> +    AVRational classify_confidences[AV_NUM_BBOX_CLASSIFY];
> +} AVBoundingBox;
> +
> +typedef struct AVBoundingBoxHeader {

This structure is not extensible in an ABI-compatible way.

> +    /**
> +     * Information about how the bounding box is generated.
> +     * for example, the DNN model name.
> +     */
> +    char source[128];
> +
> +    /**
> +     * The size of frame when it is detected.
> +     */
> +    int frame_width;
> +    int frame_height;

Why?

> +
> +    /**
> +     * Number of bounding boxes.
> +     */
> +    uint32_t nb_bbox;

size_t?

-- 
Anton Khirnov