[JAVA API][ARM CPU] Add COCO Android ARM demo (update old version) (#924

) * init copy android demo * init copy android demo * update docs * remove redudant files * update docs 2 * remove dirs * update docs 3 * remove docs * update docs * update build.gradle * update AndroidManifest * update * add new files * final fixes * radd spaces * Delete modules/android_demos/coco_detection_android_demo/gradle directory * update docs * fix property * fix docs 3 * finish * finish * Update README.md * Update README.md * Update modules/android_demos/coco_detection_android_demo/README.md Co-authored-by: Anna Likholat <aniali201398@gmail.com> --------- Co-authored-by: Anna Likholat <aniali201398@gmail.com>
openvinotoolkit · Jun 13, 2024 · e6eb43a · e6eb43a
1 parent a508f97
commit e6eb43a
Show file tree

Hide file tree

Showing 15 changed files with 709 additions and 0 deletions.
diff --git a/modules/android_demos/coco_detection_android_demo/README.md b/modules/android_demos/coco_detection_android_demo/README.md
@@ -0,0 +1,79 @@
+# Coco Detection Android Demo
+
+![Running result](https://user-images.githubusercontent.com/47499836/189129594-2634e176-5a5b-4051-b713-ae9574a8c3da.png)
+
+This demo showcases inference of Object Detection network on Android ARM devices using [OpenVINO Java API](https://github.com/openvinotoolkit/openvino_contrib/tree/7239f8201bf18d953298966afd9161cff50b2d38/modules/java_api).
+For inference is used `ssd_mobilenet_v2_coco` object detection model.
+
+## How to run it
+
+### Build the OpenVINO libraries for Android
+
+To build the OpenVINO library for an Android system, please follow these step-by-step [instruction](https://github.com/openvinotoolkit/openvino/blob/master/docs/dev/build_android.md) in full. 
+After successful completion, you can move on to the next step.
+
+### Re-build the OpenVINO libraries for Java API
+_Please save the state of the environment variables_ 
+
+For more information, please refer to [these instructions](../../java_api/README.md)
+  ```sh
+  # Clone OpenVINO™ contrib repository 
+  git clone --recursive https://github.com/openvinotoolkit/openvino_contrib $OPV_HOME_DIR/openvino_contrib
+  # Re-configure, created in the previous step, the OpenVINO™ CMake project for Java API
+  cmake -S $OPV_HOME_DIR/openvino \
+        -B $OPV_HOME_DIR/openvino-build \
+        -DCMAKE_INSTALL_PREFIX=$OPV_HOME_DIR/openvino-install \
+        -DBUILD_java_api=ON \
+        -DOPENVINO_EXTRA_MODULES=$OPV_HOME_DIR/openvino_contrib/modules/java_api
+  # Re-build OpenVINO™ project 
+  cmake --build $OPV_HOME_DIR/openvino-build --parallel
+  # Re-install OpenVINO™ project 
+  cmake --install $OPV_HOME_DIR/openvino-build
+  ```
+
+### Build the OpenVINO JAVA library for Android
+For more information, please refer to [these instructions](../../java_api/README.md)
+  ```sh
+  gradle build --project-dir $OPV_HOME_DIR/openvino_contrib/modules/java_api
+  ```
+
+### Preparing a demo to run it
+  ```sh
+  export ANDROID_DEMO_PATH=$OPV_HOME_DIR/openvino_contrib/modules/android_demos/coco_detection_android_demo
+  mkdir -p $ANDROID_DEMO_PATH/app/libs
+  cp $OPV_HOME_DIR/openvino_contrib/modules/java_api/build/libs/* $ANDROID_DEMO_PATH/app/libs/
+  
+  mkdir -p $ANDROID_DEMO_PATH/app/src/main/jniLibs/arm64-v8a
+  cp -r $OPV_HOME_DIR/openvino-install/runtime/lib/aarch64/* $ANDROID_DEMO_PATH/app/src/main/jniLibs/arm64-v8a/
+  cp -r $OPV_HOME_DIR/one-tbb-install/lib/* $ANDROID_DEMO_PATH/app/src/main/jniLibs/arm64-v8a/
+  cp -r $ANDROID_NDK_PATH/toolchains/llvm/prebuilt/linux-x86_64/sysroot/usr/lib/aarch64-linux-android/libc++_shared.so $ANDROID_DEMO_PATH/app/src/main/jniLibs/arm64-v8a/
+
+  wget https://github.com/opencv/opencv/releases/download/4.10.0/opencv-4.10.0-android-sdk.zip --directory-prefix $OPV_HOME_DIR
+  unzip $OPV_HOME_DIR/opencv-4.10.0-android-sdk.zip -d $OPV_HOME_DIR
+  cp -r $OPV_HOME_DIR/OpenCV-android-sdk/sdk $ANDROID_DEMO_PATH/OpenCV
+  ```
+
+Please rename jar library that project works correct , e.g.
+  ```sh
+  # Release version can be changed
+  mv $ANDROID_DEMO_PATH/app/libs/openvino-2024.2-linux-x86_64.jar $ANDROID_DEMO_PATH/app/libs/openvino-java-api.jar
+  ```
+
+### Download and convert model
+To get a `ssd_mobilenet_v2_coco` model for this demo you should use the Open Model Zoo tools in [these instructions](https://docs.openvino.ai/2024/omz_tools_downloader.html).
+
+### Import demo project on Android Studio
+
+- Choose and download [Android Studio](https://developer.android.com/studio) on your PC.
+
+- Select "File -> Open", and import demo project in `$OPV_HOME_DIR/openvino_contrib/modules/android_demos/coco_detection_android_demo`.
+
+- Build and run demo
+
+> The first time when you run the demo application on your device, your need to grant camera permission. Then run it again.
+
+> To build the project correctly, you should write in OpenCV `build.gradle` file `kotlinOptions` parameter same as current project's `build.gradle` file
+
+### Application Output
+
+The demonstration is expected to include real-time inferencing from the camera stream. This means that the system will continuously analyze and process video data from the camera in real-time, providing immediate insights and responses based on the live feed. 
diff --git a/modules/android_demos/coco_detection_android_demo/app/build.gradle b/modules/android_demos/coco_detection_android_demo/app/build.gradle
@@ -0,0 +1,71 @@
+plugins {
+    alias(libs.plugins.android.application)
+    alias(libs.plugins.jetbrains.kotlin.android)
+}
+
+android {
+    namespace 'org.intel.openvino'
+    compileSdk 34
+
+    defaultConfig {
+        applicationId "org.intel.openvino"
+        minSdk 30
+        targetSdk 34
+        versionCode 1
+        versionName "1.0"
+
+        testInstrumentationRunner "androidx.test.runner.AndroidJUnitRunner"
+        vectorDrawables {
+            useSupportLibrary true
+        }
+        ndk { abiFilters "arm64-v8a" }
+    }
+
+    buildTypes {
+        release {
+            minifyEnabled false
+            proguardFiles getDefaultProguardFile('proguard-android-optimize.txt'), 'proguard-rules.pro'
+        }
+    }
+    compileOptions {
+        sourceCompatibility JavaVersion.VERSION_1_8
+        targetCompatibility JavaVersion.VERSION_1_8
+    }
+    kotlinOptions {
+        jvmTarget = '1.8'
+    }
+    buildFeatures {
+        compose true
+    }
+    composeOptions {
+        kotlinCompilerExtensionVersion '1.5.1'
+    }
+    packaging {
+        resources {
+            excludes += '/META-INF/{AL2.0,LGPL2.1}'
+        }
+    }
+}
+
+dependencies {
+
+    implementation libs.androidx.core.ktx
+    implementation libs.androidx.lifecycle.runtime.ktx
+    implementation libs.androidx.activity.compose
+    implementation platform(libs.androidx.compose.bom)
+    implementation libs.androidx.ui
+    implementation libs.androidx.ui.graphics
+    implementation libs.androidx.ui.tooling.preview
+    implementation libs.androidx.material3
+    implementation libs.androidx.constraintlayout
+    implementation 'com.google.android.material:material:1.5.0'
+    testImplementation libs.junit
+    androidTestImplementation libs.androidx.junit
+    androidTestImplementation libs.androidx.espresso.core
+    androidTestImplementation platform(libs.androidx.compose.bom)
+    androidTestImplementation libs.androidx.ui.test.junit4
+    debugImplementation libs.androidx.ui.tooling
+    debugImplementation libs.androidx.ui.test.manifest
+    implementation project(':OpenCV')
+    implementation files('libs/openvino-java-api.jar')
+}
diff --git a/modules/android_demos/coco_detection_android_demo/app/src/main/AndroidManifest.xml b/modules/android_demos/coco_detection_android_demo/app/src/main/AndroidManifest.xml
@@ -0,0 +1,27 @@
+<?xml version="1.0" encoding="utf-8"?>
+<manifest xmlns:android="http://schemas.android.com/apk/res/android"
+    package="org.intel.openvino">
+    <uses-feature
+        android:name="android.hardware.camera"
+        android:required="false" />
+    <uses-permission android:name="android.permission.CAMERA"/>
+    <!-- Grant the permission to external libraries -->
+    <application
+        android:allowBackup="true"
+        android:label="@string/app_name"
+        android:supportsRtl="true"
+        android:extractNativeLibs="true"
+        android:theme="@style/Theme.CocoDetectionAndroidDemo">
+        <activity
+            android:name=".MainActivity"
+            android:exported="true"
+            android:screenOrientation="landscape">
+            <intent-filter>
+                <action android:name="android.intent.action.MAIN" />
+
+                <category android:name="android.intent.category.LAUNCHER" />
+            </intent-filter>
+        </activity>
+    </application>
+
+</manifest>
diff --git a/modules/android_demos/coco_detection_android_demo/app/src/main/assets/labels.txt b/modules/android_demos/coco_detection_android_demo/app/src/main/assets/labels.txt
@@ -0,0 +1,92 @@
+background
+person
+bicycle
+car
+motorcycle
+airplane
+bus
+train
+truck
+boat
+traffic light
+fire hydrant
+street sign
+stop sign
+parking meter
+bench
+bird
+cat
+dog
+horse
+sheep
+cow
+elephant
+bear
+zebra
+giraffe
+hat
+backpack
+umbrella
+shoe
+eye glasses
+handbag
+tie
+suitcase
+frisbee
+skis
+snowboard
+sports ball
+kite
+baseball bat
+baseball glove
+skateboard
+surfboard
+tennis racket
+bottle
+plate
+wine glass
+cup
+fork
+knife
+spoon
+bowl
+banana
+apple
+sandwich
+orange
+broccoli
+carrot
+hot dog
+pizza
+donut
+cake
+chair
+couch
+potted plant
+bed
+mirror
+dining table
+window
+desk
+toilet
+door
+tv
+laptop
+mouse
+remote
+keyboard
+cell phone
+microwave
+oven
+toaster
+sink
+refrigerator
+blender
+book
+clock
+vase
+scissors
+teddy bear
+hair drier
+toothbrush
+hair brush