Update vibe-background-sequential.cpp

[vc-zju]

solve the logical error between initialization and segmentation in vibe
Describe the bug
When we init the historybuffer[], the elements in it are like BBBBBBBBBBBBBBBBBBGGG…RRR…(suppose that the image imported by cv is a RGB image not a BGR). But when we use historybuffer[], we see it as RGBRGBRGB…… which confuses me much.

To Reproduce
Just see the code : ), I will offer it.
when we init it

for (int index = (3 * width) * height - 1; index >= 0; --index) {
          uint8_t value = image_data[index];
          for (int x = 0; x < model->numberOfSamples - NUMBER_OF_HISTORY_IMAGES; ++x) {
            int value_plus_noise = value + rand() % 20 - 10;
            if (value_plus_noise < 0) { value_plus_noise = 0; }
            if (value_plus_noise > 255) { value_plus_noise = 255; }
            model->historyBuffer[index * (model->numberOfSamples - NUMBER_OF_HISTORY_IMAGES) + x] = value_plus_noise;
          }
}

when we use it

for (int i = numberOfTests; i > 0; --i, indexHistoryBuffer += 3) {
              if (
                distance_is_close_8u_C3R(
                  image_data[(3 * index)], image_data[(3 * index) + 1], image_data[(3 * index) + 2],
                  historyBuffer[indexHistoryBuffer], historyBuffer[indexHistoryBuffer + 1], historyBuffer[indexHistoryBuffer + 2],
                  matchingThreshold
                )
                )
                --segmentation_map[index];

Expected behavior
Consistency should be maintained in logic.
Init it just like this(may have some errors)

    auto plus_noise = [](uint8_t value) -> int {int value_plus_noise = value + rand() % 20 - 10;
            if (value_plus_noise < 0) { value_plus_noise = 0; }
            if (value_plus_noise > 255) { value_plus_noise = 255; }
            return value_plus_noise;};
    for (int index = (3 * width) * height - 1; index >= 0; index -= 3) {
          uint8_t value_1 = image_data[index];
          uint8_t value_2 = image_data[index - 1];
          uint8_t value_3 = image_data[index - 2];
          for (int x = 0; x < model->numberOfSamples - NUMBER_OF_HISTORY_IMAGES; ++x) {
            int value_plus_noise1 = plus_noise(value_1);
            int value_plus_noise2 = plus_noise(value_2);
            int value_plus_noise3 = plus_noise(value_3);
            model->historyBuffer[(index - 2) * (model->numberOfSamples - NUMBER_OF_HISTORY_IMAGES) + x * 3 + 2] = value_plus_noise1;
            model->historyBuffer[(index - 2) * (model->numberOfSamples - NUMBER_OF_HISTORY_IMAGES) + x * 3 + 1] = value_plus_noise2;
            model->historyBuffer[(index - 2) * (model->numberOfSamples - NUMBER_OF_HISTORY_IMAGES) + x * 3] = value_plus_noise3;
          }
     }

Additional context
However, it nearly doesn't cause any mistake when we just see the result, which confuses me more.

[andrewssobral]

Thank you very much @vc-zju for this fix! Let's merge it