Android CameraX

Introduction

Already had this working for my Food app but this is now broken so watching a tutorial and thought I better take notes

Setup Permissions

Make sure we give permissions in the Manifest

    <uses-feature
        android:name="android.hardware.camera"
        android:required="false" />

    <uses-permission android:name="android.permission.CAMERA" />
    <uses-permission android:name="android.permission.RECORD_AUDIO" />

Implement Permission Checking

This is the simplest way to get going

class MainActivity : ComponentActivity() {
    override fun onCreate(savedInstanceState: Bundle?) {
        super.onCreate(savedInstanceState)

        if (!hasRequiredPermissions()) {
            requestPermissions(CAMERAX_PERMISSIONS, 0)
        }
        enableEdgeToEdge()
    }

    private fun hasRequiredPermissions(): Boolean {
        return CAMERAX_PERMISSIONS.all {
            ContextCompat.checkSelfPermission(this, it) == PackageManager.PERMISSION_GRANTED
        }
    }

    companion object {
        private val CAMERAX_PERMISSIONS = arrayOf(
            android.Manifest.permission.CAMERA,
            android.Manifest.permission.RECORD_AUDIO
        )
    }

    @Composable
    fun Greeting(name: String, modifier: Modifier = Modifier) {
        Text(
            text = "Hello $name!",
            modifier = modifier
        )
    }
}

Compose

I am loving the new compose. It takes a lot of the tedium out of it all. This did not exist last time. Basically bye, bye XML. Lot of code here but you just make the bits and add the components inline. The CameraPreview is the implementation of the previewer in Xml. This

        setContent {
            CameraXTutTheme {
                Scaffold {
                    val scaffoldState = rememberBottomSheetScaffoldState()

                    val controller = remember {
                        LifecycleCameraController(applicationContext).apply {
                            setEnabledUseCases(
                                CameraController.IMAGE_CAPTURE or
                                        CameraController.VIDEO_CAPTURE
                            )
                        }
                    }

                    BottomSheetScaffold(
                        scaffoldState = scaffoldState,
                        sheetPeekHeight = 0.dp,
                        sheetContent = {
                        }
                    ) { padding ->
                        Box(
                            modifier = Modifier
                                .fillMaxSize()
                                .padding(padding)
                        ) {
                            CameraPreview(
                                controller,
                                Modifier.fillMaxSize()
                            )

                            IconButton(
                                onClick = {
                                    controller.cameraSelector =
                                        if (controller.cameraSelector == CameraSelector.DEFAULT_BACK_CAMERA) {
                                            CameraSelector.DEFAULT_FRONT_CAMERA
                                        } else {
                                            CameraSelector.DEFAULT_BACK_CAMERA
                                        }
                                },
                                modifier = Modifier.padding(16.dp)
                            ) {
                                Icon(
                                    imageVector = Icons.Default.Cameraswitch,
                                    contentDescription = "Switch Camera"
                                )
                            }

                            Row(
                                modifier = Modifier
                                    .fillMaxWidth()
                                    .align(Alignment.BottomCenter)
                                    .padding(16.dp),
                                horizontalArrangement = Arrangement.SpaceAround
                            ) {
                                IconButton(
                                    onClick = {
                                    }
                                ) {
                                    Icon(
                                        imageVector = Icons.Default.Photo,
                                        contentDescription = "Open Gallery"
                                    )
                                }

                                IconButton(
                                    onClick = {
                                    }
                                ) {
                                    Icon(
                                        imageVector = Icons.Default.PhotoCamera,
                                        contentDescription = "Take Photo"
                                    )
                                }
                            }
                        }
                    }
                }
            }
        }

Add A Panel (Sheet) to Display Taken Images

First we create a sheet to display the images take on, this really is an excuse to document something to remind me what to do

@Composable
fun PhotoBottomSheetContent(
    bitmaps: List<Bitmap>,
    modifier: Modifier
) {

    if(bitmaps.isEmpty()) {
        Box(
          modifier = modifier
              .padding(16.dp),
            contentAlignment = Alignment.Center
        )
        {
            Text ("No photos taken yet")
        }
    } else {
        LazyVerticalStaggeredGrid(
            columns = StaggeredGridCells.Fixed(2),
            horizontalArrangement = Arrangement.spacedBy(16.dp),
            verticalItemSpacing = 16.dp,
            contentPadding = PaddingValues(16.dp),
            modifier = modifier
        ) {
            items(bitmaps) { bitmap ->
                Image(
                    bitmap = bitmap.asImageBitmap(),
                    contentDescription = null,
                    modifier = Modifier
                        .clip(RoundedCornerShape(10.dp))
                )
            }
        }
    }
}

This is the code for the Panel is this photo

Taking A Photo

Glad I watched this course, the compose stuff looks like it will improve people speed a lot. Next take the photo and you can see this is now trivial.

Make A Model for the View

We create a model of type MutableStateFlow to store the collected images

class MainViewModel : ViewModel() {
    private val _bitmaps = MutableStateFlow<List<Bitmap>>(emptyList())

    val bitmaps = _bitmaps.asStateFlow()

    fun onTakePhoto(bitmap: Bitmap) {
        Log.i("CameraXTut", "Adding a photo")
        _bitmaps.value +=  bitmap
    }

Attach the onTakePhoto to the onPhotoTaken delegate

When we take a photo, it is added to the model

IconButton(
    onClick = {
        takePhoto(
           controller = controller,
           onPhotoTaken = viewModel::onTakePhoto
        )
   }
) {
    Icon(
       imageVector = Icons.Default.PhotoCamera,
       contentDescription = "Take Photo"
    )
}

Taking the Photo

And here is the function which takes the photo

    private fun takePhoto(
        controller: LifecycleCameraController,
        onPhotoTaken: (Bitmap) -> Unit
    ) {
        controller.takePicture(
            ContextCompat.getMainExecutor(applicationContext),
            object: OnImageCapturedCallback() {
                override fun onCaptureSuccess(image: ImageProxy) {
                    onPhotoTaken(image.toBitmap())
                    Log.i("CameraXTut", "Taken a picture")
                }

                override fun onError(exception: ImageCaptureException) {
                    super.onError(exception)
                    Log.e("CameraXTut", "Error capturing image", exception)
                }
            }
        )
    }

Rotating and Flipping the image

When you take the photo you need to handle to flipping of the image based on the camera which is used.

override fun onCaptureSuccess(image: ImageProxy) {
    // Flip the image if it's from the front camera
    val isFrontCamera = controller.cameraSelector == CameraSelector.DEFAULT_FRONT_CAMERA
    onPhotoTaken(rotateImage(image, isFrontCamera))
    Log.i("CameraXTut", "Taken a picture")
}

We create a matrix, getting the number of degrees to rotate, then create a bitmap based on this matrix

    private fun rotateImage(image: ImageProxy, flipImage: Boolean ): Bitmap {
        val matrix = Matrix().apply {
            postRotate(image.imageInfo.rotationDegrees.toFloat())
            if(flipImage) {
                postScale(-1f, 1f)
            }
        }

        return Bitmap.createBitmap(
            image.toBitmap(),
            0,
            0,
            image.width,
            image.height,
            matrix,
            true
        )
    }

Recording a Video

This could not be easier, its like they want you to use their product. Create a recording object.

    private var recording: Recording? = null

Create a button

IconButton(
  onClick = {
    recordVideo(controller = controller)
  }
) {
  Icon(
    imageVector = Icons.Default.Videocam,
    contentDescription = "Record Video"
  )
}

Write the function which, checks for permissions, either stops or starts video recording

    @SuppressLint("MissingPermission")
    private fun recordVideo(
        controller: LifecycleCameraController,
    ) {
        if(!hasRequiredPermissions()) {
            requestPermissions(CAMERAX_PERMISSIONS, 0)
            return
        }
        
        // Check if we're already recording, and stop if we are
        if (recording != null) {
            recording?.stop()
            recording = null
            return
        }

        val outputFile = File(filesDir, "video.mp4")
        recording = controller.startRecording(
            FileOutputOptions.Builder(outputFile).build(),
            AudioConfig.create(true),
            ContextCompat.getMainExecutor(applicationContext)
        ) { event ->
            when (event) {
                is VideoRecordEvent.Finalize -> {
                    if (event.hasError()) {
                        recording?.close()
                        recording = null
                        Toast.makeText(
                            applicationContext,
                            "Error recording video",
                            Toast.LENGTH_LONG
                        ).show()
                    } else {
                        Toast.makeText(applicationContext, "Video saved", Toast.LENGTH_LONG).show()
                    }
                }
            }
        }
    }

Dipped my Toe into AI on Android

So this is my first faray into AI on android. I am going to plug in an Analyzer to the camera to recognize landmarks using a model on TensorFlow. So to do this we need to

• Create a Preview Window
• Enable the Analyzer Use Case
• Get the Model

Create a Preview Window

This has been done already above

Enable the Analyzer Use Case

We do this by adding the IMAGE analysis to the enabled Use Cases

val controller = remember {
  LifecycleCameraController(applicationContext).apply {
    setEnabledUseCases(
      CameraController.IMAGE_CAPTURE or
        CameraController.VIDEO_CAPTURE or 
          CameraController.IMAGE_ANALYSIS
    )
  }
}

Get the Model

Download the model from [Kaggle]. This use to be known as tfhub but is now known as kaggle. The model format was shown in the video but since moving from tfhub this information seemed to be missing.

Make a data Class to Hold the Confidence

This will hold the result from the model

data class Classification(
    val label: String,
    val confidence: Float
)

Make an Interface for the Classifier

This is the interface to implement

interface LandmarkClassifier {
    fun classify(bitmap: Bitmap, rotation: Int): List<Classification>
}

Implement the Classifier

We need to make sure the image is orientated as the model expects. This held in the metadata on the original Tfhub but could not find it on kaggle.

class TfliteLandmarkClassifier(
    private val context: Context,
    private val threshold: Float = 0.5f,
    private val maxResults: Int = 1
) : LandmarkClassifier {

    private var classifier: ImageClassifier? = null

    private fun setupClassifier() {
        val baseOptions = BaseOptions.builder()
            .setNumThreads(2)
            .build()

        val options = ImageClassifier.ImageClassifierOptions.builder()
            .setBaseOptions(baseOptions)
            .setMaxResults(maxResults)
            .setScoreThreshold(threshold)
            .build()

        try {
            classifier = ImageClassifier.createFromFileAndOptions(
                context,
                "1.tflite",
                options
            )
        } catch (e: IllegalStateException) {
            e.printStackTrace()
        }
    }

    override fun classify(bitmap: Bitmap, rotation: Int): List<Classification> {
        if (classifier == null) {
            setupClassifier()
        }

        var imageProcessor = ImageProcessor.Builder().build()
        val tensorImage = imageProcessor.process(TensorImage.fromBitmap(bitmap))

        val imageProcessingOptions = ImageProcessingOptions.builder()
            .setOrientation(getOrientationFromRotation(rotation))
            .build()

        val results = classifier?.classify(tensorImage, imageProcessingOptions)

        val thisTime =  results?.flatMap { classifications ->
            classifications.categories.map { category ->
                Classification(
                    label = category.displayName,
                    confidence = category.score
                )
            }
            // Make a dummy entry if no results
        }?.distinctBy { it.label } ?: listOf(Classification("No results", 10f))
        Log.i("RESULTS", thisTime.first().label)
        return thisTime
    }

    private fun getOrientationFromRotation(rotation: Int): ImageProcessingOptions.Orientation {
        return when (rotation) {
            android.view.Surface.ROTATION_0 -> ImageProcessingOptions.Orientation.RIGHT_TOP
            android.view.Surface.ROTATION_90 -> ImageProcessingOptions.Orientation.TOP_LEFT
            android.view.Surface.ROTATION_180 -> ImageProcessingOptions.Orientation.RIGHT_BOTTOM
            else -> ImageProcessingOptions.Orientation.TOP_LEFT
        }
    }
}