// Copyright 2020 The MediaPipe Authors.
//
// Licensed under the Apache License, Version 2.0 (the "License");
// you may not use this file except in compliance with the License.
// You may obtain a copy of the License at
//
//      http://www.apache.org/licenses/LICENSE-2.0
//
// Unless required by applicable law or agreed to in writing, software
// distributed under the License is distributed on an "AS IS" BASIS,
// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
// See the License for the specific language governing permissions and
// limitations under the License.

syntax = "proto3";

package mediapipe;

import "mediapipe/modules/objectron/calculators/a_r_capture_metadata.proto";
import "mediapipe/modules/objectron/calculators/object.proto";

// Projection of a 3D point on an image, and its metric depth.
message NormalizedPoint2D {
  // x-y position of the 2d keypoint in the image coordinate system.
  // u,v \in [0, 1], where top left corner is (0, 0) and the bottom-right corner
  // is (1, 1).
  float x = 1;
  float y = 2;

  // The depth of the point in the camera coordinate system (in meters).
  float depth = 3;
}

// The 3D point in the camera coordinate system, the scales are in meters.
message Point3D {
  float x = 1;
  float y = 2;
  float z = 3;
}

message AnnotatedKeyPoint {
  int32 id = 1;
  Point3D point_3d = 2;
  NormalizedPoint2D point_2d = 3;
  // Indicates whether this keypoint is hidden or not. The hidden attribute is
  // determined from the object's skeleton. For box model, none of the keypoints
  // are hidden.
  bool hidden = 4;
}

message ObjectAnnotation {
  // Reference to the object identifier in ObjectInstance.
  int32 object_id = 1;

  // For each objects, list all the annotated keypoints here.
  // E.g. for bounding-boxes, we have 8 keypoints, hands = 21 keypoints, etc.
  // These normalized points are the projection of the Object's 3D keypoint
  // on the current frame's camera poses.
  repeated AnnotatedKeyPoint keypoints = 2;

  // Visibiity of this annotation in a frame.
  float visibility = 3;

  // 3x3 row-major rotation matrix describing the orientation of the rigid
  // object's frame of reference in the camera-coordinate system.
  repeated float rotation = 4;

  // 3x1 vector describing the translation of the rigid object's frame of
  // reference in the camera-coordinate system in meters.
  repeated float translation = 5;

  // 3x1 vector describing the scale of the rigid object's frame of reference in
  // the camera-coordinate system.
  repeated float scale = 6;
}

message FrameAnnotation {
  // Unique frame id, corresponds to images.
  int32 frame_id = 1;

  // List of the annotated objects in this frame. Depending on how many object
  // are observable in this frame, we might have non or as much as
  // sequence.objects_size() annotations.
  repeated ObjectAnnotation annotations = 2;

  // Information about the camera transformation (in the world coordinate) and
  // imaging characteristics for a captured video frame.
  ARCamera camera = 3;

  // The timestamp for the frame.
  double timestamp = 4;

  // Plane center and normal in camera frame.
  repeated float plane_center = 5;
  repeated float plane_normal = 6;
}

// The sequence protocol contains the annotation data for the entire video clip.
message Sequence {
  // List of all the annotated 3D objects in this sequence in the world
  // Coordinate system. Given the camera poses of each frame (also in the
  // world-coordinate) these objects bounding boxes can be projected to each
  // frame to get the per-frame annotation (i.e. image_annotation below).
  repeated Object objects = 1;

  // List of annotated data per each frame in sequence + frame information.
  repeated FrameAnnotation frame_annotations = 2;
}