MediaPipeTasksVision Framework Reference

MPPObjectDetector


@interface MPPObjectDetector : NSObject

@brief Class that performs object detection on images.

The API expects a TFLite model with mandatory TFLite Model Metadata.

The API supports models with one image input tensor and one or more output tensors. To be more specific, here are the requirements:

Input tensor (kTfLiteUInt8/kTfLiteFloat32)

  • image input of size [batch x height x width x channels].
  • batch inference is not supported (batch is required to be 1).
  • only RGB inputs are supported (channels is required to be 3).
  • if type is kTfLiteFloat32, NormalizationOptions are required to be attached to the metadata for input normalization.

Output tensors must be the 4 outputs of a DetectionPostProcess op, i.e:(kTfLiteFloat32) (kTfLiteUInt8/kTfLiteFloat32)

  • locations tensor of size [num_results x 4], the inner array representing bounding boxes in the form [top, left, right, bottom].
  • BoundingBoxProperties are required to be attached to the metadata and must specify type=BOUNDARIES and coordinate_type=RATIO. (kTfLiteFloat32)
  • classes tensor of size [num_results], each value representing the integer index of a class.
  • optional (but recommended) label map(s) can be attached as AssociatedFiles with type TENSOR_VALUE_LABELS, containing one label per line. The first such AssociatedFile (if any) is used to fill the class_name field of the results. The display_name field is filled from the AssociatedFile (if any) whose locale matches the display_names_locale field of the ObjectDetectorOptions used at creation time (“en” by default, i.e. English). If none of these are available, only the index field of the results will be filled. (kTfLiteFloat32)
  • scores tensor of size [num_results], each value representing the score of the detected object.
  • optional score calibration can be attached using ScoreCalibrationOptions and an AssociatedFile with type TENSOR_AXIS_SCORE_CALIBRATION. See metadata_schema.fbs [1] for more details. (kTfLiteFloat32)
  • integer num_results as a tensor of size [1]
  • Creates a new instance of ObjectDetector from an absolute path to a TensorFlow Lite model file stored locally on the device and the default ObjectDetector.

    Declaration

    Objective-C

    - (nullable instancetype)initWithModelPath:(nonnull NSString *)modelPath
                                         error:(NSError *_Nullable *_Nullable)error;

    Parameters

    modelPath

    An absolute path to a TensorFlow Lite model file stored locally on the device.

    error

    An optional error parameter populated when there is an error in initializing the object detector.

    Return Value

    A new instance of ObjectDetector with the given model path. nil if there is an error in initializing the object detector.

  • Creates a new instance of ObjectDetector from the given ObjectDetectorOptions.

    Declaration

    Objective-C

    - (nullable instancetype)initWithOptions:
                                 (nonnull MPPObjectDetectorOptions *)options
                                       error:(NSError *_Nullable *_Nullable)error;

    Parameters

    options

    The options of type ObjectDetectorOptions to use for configuring the ObjectDetector.

    error

    An optional error parameter populated when there is an error in initializing the object detector.

    Return Value

    A new instance of ObjectDetector with the given options. nil if there is an error in initializing the object detector.

  • Performs object detection on the provided MPImage using the whole image as region of interest. Rotation will be applied according to the orientation property of the provided MPImage. Only use this method when the ObjectDetector is created with .image.

    This method supports detecting objects in RGBA images. If your MPImage has a source type of .pixelBuffer or .sampleBuffer, the underlying pixel buffer must use kCVPixelFormatType_32BGRA as its pixel format.

    If your MPImage has a source type of .image ensure that the color space is RGB with an Alpha channel.

    Declaration

    Objective-C

    - (nullable MPPObjectDetectorResult *)
        detectImage:(nonnull MPPImage *)image
              error:(NSError *_Nullable *_Nullable)error;

    Parameters

    image

    The .image on which object detection is to be performed.