Plumerai Familiar Face Identification C++ API¶

#include <cstdint>
#include <vector>

#include "plumerai/face_identification.h"

int main() {
  // Settings, to be changed as needed
  constexpr int width = 1600;   // camera image width in pixels
  constexpr int height = 1200;  // camera image height in pixels
  constexpr auto image_format = plumerai::ImageFormat::PACKED_RGB888;

  // Initialize the `FaceIdentification` object
  auto ffid = plumerai::FaceIdentification(height, width);

  // ---------------------- Enrollment starting ------------------------------
  auto error_code = ffid.start_face_enrollment();
  if (error_code != plumerai::ErrorCodeFamiliarFaceID::ENROLLMENT_IN_PROGRESS) {
    printf("Error: %s\n", plumerai::error_code_string(error_code));
    return 1;
  }

  // Enroll for 10 frames (just an example, more frames is better)
  for (int t = 0; t < 10; ++t) {
    // Some example input here, normally this is where camera data is acquired
    auto image = std::vector<std::uint8_t>(height * width * 3);  // 3 for RGB

    // Process the frame
    std::vector<BoxPrediction> predictions(0);
    // If the enrollment frames come from a video source, then use
    // `process_frame` instead:
    // error_code =
    //     ffid.process_frame<image_format>(image.data(), predictions, delta_t);
    error_code = ffid.single_image<image_format>(image.data(), predictions);
    printf("Enrollment status: %d\n", error_code);
  }

  // Finish enrollment
  std::vector<std::int8_t> embedding;
  error_code = ffid.finish_face_enrollment(embedding);
  if (error_code != plumerai::ErrorCode::SUCCESS) {
    printf("Error: %s\n", plumerai::error_code_string(error_code));
    return 1;
  }

  // Add the embedding to the library with face id '1'.
  error_code = ffid.add_face_embedding(embedding, 1);
  if (error_code != plumerai::ErrorCode::SUCCESS) {
    printf("Error: %s\n", plumerai::error_code_string(error_code));
    return 1;
  }
  // ---------------------- Enrollment finished ------------------------------

  // Loop over frames in a video stream (example: 10 frames)
  for (int t = 0; t < 10; ++t) {
    // Some example input here, normally this is where camera data is acquired
    auto image = std::vector<std::uint8_t>(height * width * 3);  // 3 for RGB

    // The time between two video frames in seconds
    // In this example we assume a constant frame rate of 30 fps, but variable
    // rates are supported.
    const float delta_t = 1.f / 30.f;

    // Process the frame
    std::vector<BoxPrediction> predictions(0);
    error_code =
        ffid.process_frame<image_format>(image.data(), predictions, delta_t);
    if (error_code != plumerai::ErrorCode::SUCCESS) {
      printf("Error: %s\n", plumerai::error_code_string(error_code));
      return 1;
    }

    // Display the results to stdout
    for (auto &p : predictions) {
      if (p.confidence < 0.8f) { continue; }  // only high-confidence boxes
      if (p.class_id != CLASS_PERSON) { continue; }
      printf(
          "Box #%d of class %d and face id %d with confidence %.2f @ (x,y) -> "
          "(%.2f,%.2f) till (%.2f,%.2f)\n",
          p.id, p.class_id, ffid.get_face_id(p), p.confidence, p.x_min, p.y_min,
          p.x_max, p.y_max);
    }
    if (predictions.size() == 0) {
      printf("No bounding boxes found in this frame\n");
    }
  }
  return 0;
}