Merge branch 'openvinotoolkit:master' into master

Author: ieliz

README.md

@@ -1,5 +1,5 @@
 # [OpenVINO™ Toolkit](https://docs.openvino.ai/latest/index.html) - Open Model Zoo repository
-[![Stable release](https://img.shields.io/badge/version-2022.1-green.svg)](https://github.com/openvinotoolkit/open_model_zoo/releases/tag/2022.1)
+[![Stable release](https://img.shields.io/badge/version-2022.2.0-green.svg)](https://github.com/openvinotoolkit/open_model_zoo/releases/tag/2022.2.0)
 [![Gitter chat](https://badges.gitter.im/gitterHQ/gitter.png)](https://gitter.im/open_model_zoo/community)
 [![Apache License Version 2.0](https://img.shields.io/badge/license-Apache_2.0-green.svg)](LICENSE)
 

ci/dependencies.yml

@@ -1,6 +1,6 @@
-opencv_linux: '20220228_0602-4.5.5_079'
-opencv_windows: '20220228_0602-4.5.5_079'
-openvino_linux: '2022.1.0.612'
-openvino_windows: '2022.1.0.612'
-wheel_linux: '2022.1.0.dev20220228-6910'
-wheel_windows: '2022.1.0.dev20220228-6910'
+opencv_linux: '20220311_0602-4.5.5_090'
+opencv_windows: '20220311_0602-4.5.5_090'
+openvino_linux: '2022.1.0.643'
+openvino_windows: '2022.1.0.643'
+wheel_linux: '2022.1.0-7019'
+wheel_windows: '2022.1.0-7019'

data/dataset_definitions.yml

@@ -1493,3 +1493,14 @@ datasets:
       annotation_file: object_detection/streams_1/high/annotations/instances_glb2bcls3.json
     annotation: mscoco_detection_high_3cls.pickle
     dataset_meta: mscoco_detection_high_3cls.json
+
+  - name: HumanMattingDataset
+    data_source:  human_matting_dataset/clip_img/1803151818/clip_00000000
+    additional_data_source: human_matting_dataset/matting/1803151818/matting_00000000
+    annotation_conversion:
+      converter: background_matting
+      images_dir: human_matting_dataset/clip_img/1803151818/clip_00000000
+      masks_dir: human_matting_dataset/matting/1803151818/matting_00000000
+      image_postfix: '.jpg'
+    annotation: human_matting.pickle
+    dataset_meta: human_matting.json

demos/3d_segmentation_demo/python/README.md

@@ -6,7 +6,7 @@ This topic demonstrates how to run the 3D Segmentation Demo, which segments 3D i
 
 On startup, the demo reads command-line parameters and loads a model and images to OpenVINO™ Runtime plugin.
 
-> **NOTE**: By default, Open Model Zoo demos expect input with BGR channels order. If you trained your model to work with RGB order, you need to manually rearrange the default channels order in the demo application or reconvert your model using the Model Optimizer tool with the `--reverse_input_channels` argument specified. For more information about the argument, refer to **When to Reverse Input Channels** section of [Converting a Model Using General Conversion Parameters](https://docs.openvino.ai/latest/openvino_docs_MO_DG_prepare_model_convert_model_Converting_Model.html#general-conversion-parameters).
+> **NOTE**: By default, Open Model Zoo demos expect input with BGR channels order. If you trained your model to work with RGB order, you need to manually rearrange the default channels order in the demo application or reconvert your model using the Model Optimizer tool with the `--reverse_input_channels` argument specified. For more information about the argument, refer to **When to Reverse Input Channels** section of [Embedding Preprocessing Computation](@ref openvino_docs_MO_DG_Additional_Optimization_Use_Cases).
 
 ## Preparing to Run
 
@@ -110,5 +110,5 @@ The demo reports
 ## See Also
 
 * [Open Model Zoo Demos](../../README.md)
-* [Model Optimizer](https://docs.openvino.ai/latest/_docs_MO_DG_Deep_Learning_Model_Optimizer_DevGuide.html)
+* [Model Optimizer](https://docs.openvino.ai/latest/openvino_docs_MO_DG_Deep_Learning_Model_Optimizer_DevGuide.html)
 * [Model Downloader](../../../tools/model_tools/README.md)

demos/README.md

@@ -167,7 +167,7 @@ You can download the [Intel pre-trained models](../models/intel/index.md) or [pu
 ## Build the Demo Applications
 
 To build the demos, you need to source OpenVINO™ and OpenCV environment. You can install the OpenVINO™ toolkit using the installation package for [Intel® Distribution of OpenVINO™ toolkit](https://www.intel.com/content/www/us/en/developer/tools/openvino-toolkit-download.html) or build the open-source version available in the [OpenVINO GitHub repository](https://github.com/openvinotoolkit/openvino) using the [build instructions](https://github.com/openvinotoolkit/openvino/wiki/BuildingCode).
-For the Intel® Distribution of OpenVINO™ toolkit installed to the `<INSTALL_DIR>` directory on your machine, run the following commands to download OpenCV and set environment variables before building the demos:
+For the Intel® Distribution of OpenVINO™ toolkit installed to the `<INSTALL_DIR>` directory on your machine, run the following commands to download prebuilt OpenCV and set environment variables before building the demos:
 
 ```sh
 <INSTALL_DIR>/extras/scripts/download_opencv.sh
@@ -180,9 +180,7 @@ source <INSTALL_DIR>/setupvars.sh
 > ```
 
 For the open-source version of OpenVINO, set the following variables:
-* `InferenceEngine_DIR` pointing to a folder containing `InferenceEngineConfig.cmake`
 * `OpenVINO_DIR` pointing to a folder containing `OpenVINOConfig.cmake`
-* `ngraph_DIR` pointing to a folder containing `ngraphConfig.cmake`.
 * `OpenCV_DIR` pointing to OpenCV. The same OpenCV version should be used both for OpenVINO and demos build.
 
 Alternatively, these values can be provided via command line while running `cmake`. See [CMake search procedure](https://cmake.org/cmake/help/latest/command/find_package.html#search-procedure).
@@ -192,8 +190,8 @@ Also add paths to the built OpenVINO™ Runtime libraries to the `LD_LIBRARY_PAT
 
 The officially supported Linux* build environment is the following:
 
-- Ubuntu* 18.04 LTS 64-bit or CentOS* 7.6 64-bit
-- GCC* 7.5.0 (for Ubuntu* 18.04) or GCC* 4.8.5 (for CentOS* 7.6)
+- Ubuntu* 18.04 LTS 64-bit or Ubuntu* 20.04 LTS 64-bit
+- GCC* 7.5.0 (for Ubuntu* 18.04) or GCC* 9.3.0 (for Ubuntu* 20.04)
 - CMake* version 3.10 or higher.
 
 To build the demo applications for Linux, go to the directory with the `build_demos.sh` script and
@@ -236,10 +234,8 @@ for the debug configuration — in `<path_to_build_directory>/intel64/Debug/`.
 The recommended Windows* build environment is the following:
 
 - Microsoft Windows* 10
-- Microsoft Visual Studio* 2017, or 2019
-- CMake* version 3.10 or higher
-
-> **NOTE**: If you want to use Microsoft Visual Studio 2019, you are required to install CMake 3.14.
+- Microsoft Visual Studio* 2019
+- CMake* version 3.14 or higher
 
 To build the demo applications for Windows, go to the directory with the `build_demos_msvc.bat`
 batch file and run it:
@@ -250,13 +246,19 @@ build_demos_msvc.bat
 
 By default, the script automatically detects the highest Microsoft Visual Studio version installed on the machine and uses it to create and build
 a solution for a demo code. Optionally, you can also specify the preferred Microsoft Visual Studio version to be used by the script. Supported
-versions are: `VS2017`, `VS2019`. For example, to build the demos using the Microsoft Visual Studio 2017, use the following command:
+version is: `VS2019`. For example, to build the demos using the Microsoft Visual Studio 2019, use the following command:
+
+```bat
+build_demos_msvc.bat VS2019
+```
+
+By default, the demo applications binaries are build into the `C:\Users\<username>\Documents\Intel\OpenVINO\omz_demos_build\intel64\Release` directory.
+The default build folder can be changed with `-b` option. For example, following command will buid Open Model Zoo demos into `c:\temp\omz-demos-build` folder:
 
 ```bat
-build_demos_msvc.bat VS2017
+build_demos_msvc.bat -b c:\temp\omz-demos-build
 ```
 
-The demo applications binaries are in the `C:\Users\<username>\Documents\Intel\OpenVINO\omz_demos_build\intel64\Release` directory.
 
 You can also build a generated solution by yourself, for example, if you want to
 build binaries in Debug configuration. Run the appropriate version of the
@@ -415,7 +417,7 @@ For example, for the **Debug** configuration, go to the project's
 variable in the **Environment** field to the following:
 
 ```
-PATH=<INSTALL_DIR>\deployment_tools\inference_engine\bin\intel64\Debug;<INSTALL_DIR>\opencv\bin;%PATH%
+PATH=<INSTALL_DIR>\runtime\bin\intel64\Debug;<INSTALL_DIR>\extras\opencv\bin;%PATH%
 ```
 
 where `<INSTALL_DIR>` is the directory in which the OpenVINO toolkit is installed.

demos/action_recognition_demo/python/README.md

@@ -32,7 +32,7 @@ that uses Asynchronous Inference Request API by scheduling infer requests in cyc
 You can change the value of `num_requests` in `action_recognition_demo.py` to find an optimal number of parallel working infer requests for your inference accelerators
 (Intel(R) Neural Compute Stick devices and GPUs benefit from higher number of infer requests).
 
-> **NOTE**: By default, Open Model Zoo demos expect input with BGR channels order. If you trained your model to work with RGB order, you need to manually rearrange the default channels order in the demo application or reconvert your model using the Model Optimizer tool with the `--reverse_input_channels` argument specified. For more information about the argument, refer to **When to Reverse Input Channels** section of [Converting a Model Using General Conversion Parameters](https://docs.openvino.ai/latest/openvino_docs_MO_DG_prepare_model_convert_model_Converting_Model.html#general-conversion-parameters).
+> **NOTE**: By default, Open Model Zoo demos expect input with BGR channels order. If you trained your model to work with RGB order, you need to manually rearrange the default channels order in the demo application or reconvert your model using the Model Optimizer tool with the `--reverse_input_channels` argument specified. For more information about the argument, refer to **When to Reverse Input Channels** section of [Embedding Preprocessing Computation](@ref openvino_docs_MO_DG_Additional_Optimization_Use_Cases).
 
 ## Preparing to Run
 
@@ -147,5 +147,5 @@ The application uses OpenCV to display the real-time action recognition results
 ## See Also
 
 * [Open Model Zoo Demos](../../README.md)
-* [Model Optimizer](https://docs.openvino.ai/latest/_docs_MO_DG_Deep_Learning_Model_Optimizer_DevGuide.html)
+* [Model Optimizer](https://docs.openvino.ai/latest/openvino_docs_MO_DG_Deep_Learning_Model_Optimizer_DevGuide.html)
 * [Model Downloader](../../../tools/model_tools/README.md)

demos/background_subtraction_demo/cpp_gapi/README.md

@@ -28,7 +28,7 @@ The demo workflow is the following:
     * If you specify `--target_bgr`, background will be replaced by a chosen image or video. By default background replaced by green field.
     * If you specify `--blur_bgr`, background will be blurred according to a set value. By default equal to zero and is not applied.
 
-> **NOTE**: By default, Open Model Zoo demos expect input with BGR channels order. If you trained your model to work with RGB order, you need to manually rearrange the default channels order in the demo application or reconvert your model using the Model Optimizer tool with the `--reverse_input_channels` argument specified. For more information about the argument, refer to **When to Reverse Input Channels** section of [Converting a Model Using General Conversion Parameters](https://docs.openvino.ai/latest/openvino_docs_MO_DG_prepare_model_convert_model_Converting_Model.html#general-conversion-parameters).
+> **NOTE**: By default, Open Model Zoo demos expect input with BGR channels order. If you trained your model to work with RGB order, you need to manually rearrange the default channels order in the demo application or reconvert your model using the Model Optimizer tool with the `--reverse_input_channels` argument specified. For more information about the argument, refer to **When to Reverse Input Channels** section of [Embedding Preprocessing Computation](@ref openvino_docs_MO_DG_Additional_Optimization_Use_Cases).
 
 ## Preparing to Run
 
@@ -114,5 +114,5 @@ The demo reports
 ## See Also
 
 * [Open Model Zoo Demos](../../README.md)
-* [Model Optimizer](https://docs.openvinotoolkit.org/latest/_docs_MO_DG_Deep_Learning_Model_Optimizer_DevGuide.html)
+* [Model Optimizer](https://docs.openvino.ai/latest/openvino_docs_MO_DG_Deep_Learning_Model_Optimizer_DevGuide.html)
 * [Model Downloader](../../../tools/model_tools/README.md)

demos/background_subtraction_demo/cpp_gapi/include/custom_kernels.hpp

@@ -33,6 +33,8 @@ G_API_OP(GCalculateMaskRCNNBGMask,
 
 class NNBGReplacer {
 public:
+    NNBGReplacer() = default;
+    virtual ~NNBGReplacer() = default;
     NNBGReplacer(const std::string& model_path);
     virtual cv::GMat replace(cv::GMat, const cv::Size&, cv::GMat) = 0;
     const std::string& getName() { return m_tag; }

demos/background_subtraction_demo/python/README.md

@@ -29,7 +29,10 @@ The demo application expects an instance segmentation or background matting mode
     * At least two outputs including:
         * `fgr` with normalized in [0, 1] range foreground
         * `pha` with normalized in [0, 1] range alpha
-4. for video background matting models based on RNN architecture:
+4. for image background matting models without trimap (background segmentation):
+    * Single input for input image.
+    * Single output with normalized in [0, 1] range alpha
+5. for video background matting models based on RNN architecture:
     * Five inputs:
         * `src` for input image
         * recurrent inputs: `r1`, `r2`, `r3`, `r4`
@@ -53,7 +56,13 @@ The demo workflow is the following:
     * If you specify `--blur_bgr`, background will be blurred according to a set value. By default equal to zero and is not applied.
     * If you specify `--show_with_original_frame`, the result image will be merged with an input one.
 
-> **NOTE**: By default, Open Model Zoo demos expect input with BGR channels order. If you trained your model to work with RGB order, you need to manually rearrange the default channels order in the demo application or reconvert your model using the Model Optimizer tool with the `--reverse_input_channels` argument specified. For more information about the argument, refer to **When to Reverse Input Channels** section of [Converting a Model Using General Conversion Parameters](https://docs.openvino.ai/latest/openvino_docs_MO_DG_prepare_model_convert_model_Converting_Model.html#general-conversion-parameters).
+> **NOTE**: By default, Open Model Zoo demos expect input with BGR channels order. If you trained your model to work with RGB order, you need to manually rearrange the default channels order in the demo application or reconvert your model using the Model Optimizer tool with the `--reverse_input_channels` argument specified. For more information about the argument, refer to **When to Reverse Input Channels** section of [Embedding Preprocessing Computation](@ref openvino_docs_MO_DG_Additional_Optimization_Use_Cases).
+
+## Model API
+
+The demo utilizes model wrappers, adapters and pipelines from [Python* Model API](../../common/python/openvino/model_zoo/model_api/README.md).
+
+The generalized interface of wrappers with its unified results representation provides the support of multiple different background subtraction model topologies in one demo.
 
 ## Preparing to Run
 
@@ -75,10 +84,12 @@ omz_converter --list models.lst
 
 ### Supported Models
 
-* instance-segmentation-person-????
-* yolact-resnet50-fpn-pytorch
 * background-matting-mobilenetv2
+* instance-segmentation-person-????
+* modnet-photographic-portrait-matting
+* modnet-webcam-portrait-matting
 * robust-video-matting-mobilenetv3
+* yolact-resnet50-fpn-pytorch
 
 > **NOTE**: Refer to the tables [Intel's Pre-Trained Models Device Support](../../../models/intel/device_support.md) and [Public Pre-Trained Models Device Support](../../../models/public/device_support.md) for the details on models inference support at different devices.
 
@@ -227,5 +238,5 @@ You can use these metrics to measure application-level performance.
 ## See Also
 
 * [Open Model Zoo Demos](../../README.md)
-* [Model Optimizer](https://docs.openvinotoolkit.org/latest/_docs_MO_DG_Deep_Learning_Model_Optimizer_DevGuide.html)
+* [Model Optimizer](https://docs.openvino.ai/latest/openvino_docs_MO_DG_Deep_Learning_Model_Optimizer_DevGuide.html)
 * [Model Downloader](../../../tools/model_tools/README.md)

demos/background_subtraction_demo/python/background_subtraction_demo.py

@@ -26,7 +26,10 @@
 
 sys.path.append(str(Path(__file__).resolve().parents[2] / 'common/python'))
 
-from openvino.model_zoo.model_api.models import MaskRCNNModel, OutputTransform, RESIZE_TYPES, YolactModel, ImageMattingWithBackground, VideoBackgroundMatting
+from openvino.model_zoo.model_api.models import (
+    MaskRCNNModel, OutputTransform, RESIZE_TYPES, YolactModel,
+    ImageMattingWithBackground, VideoBackgroundMatting, PortraitBackgroundMatting
+)
 from openvino.model_zoo.model_api.models.utils import load_labels
 from openvino.model_zoo.model_api.performance_metrics import PerformanceMetrics
 from openvino.model_zoo.model_api.pipelines import get_user_config, AsyncPipeline
@@ -123,6 +126,9 @@ def get_model(model_adapter, configuration, args):
         model = ImageMattingWithBackground(model_adapter, configuration)
         need_bgr_input = True
         is_matting_model = True
+    elif len(inputs) == 1 and len(outputs) == 1:
+        model = PortraitBackgroundMatting(model_adapter, configuration)
+        is_matting_model = True
     else:
         model = MaskRCNNModel(model_adapter, configuration)
     if not need_bgr_input and args.background is not None: