How to get the real life size of an object from an image, when not knowing the distance between object and the camera?

by

The simple answer is you can’t.

Incidentally, this is why humans have two eyes. If you want to judge size without a known distance, you’ll need at least two reference points. This allows you to triangulate the position of the object, get a distance to it, and use your known focal distance to calculate the size.

The more complex answer is there are ways around this for example:

  1. Cheat by using a known reference:

    For example, if you have an object of known size, you can infer the distance. This is similar to what NASA does to calibrate its cameras, for example.

    You can make safe assumptions if you’re dealing with common objects, such as the height of one storey when analysing the image of a building.

  2. Move your camera around:

    This allows you to get more than one reference point with the same camera.

    I suppose you could use the accelerometer to accurately measure the positional relation between the image captured at point T1 in time and point T2. This would give you two images of the same subject with a known distance between them. This then allows you to triangulate as if you had two eyes.

    Whether normal hand-held camera jitters will be sufficient for triangulation, or whether the accelerometer will be accurate enough to inertially position the phone, I don’t know.

  3. Assume a distance:

    If your app is designed to compare something on the scale of a human hand (or other bit of human anatomy), you can probably safely assume a distance based on what people will naturally do. The focus limits of the camera itself will also give an upper and lower range on how far an object can be and still be in focus. This will probably be within a tolerable margin of error.

As you mention in your question, there is an entire subfield dedicated to this question, and it is an active research area.

More Related Contents:

  1. Converting RGB to grayscale/intensity
  2. Simple and fast method to compare images for similarity
  3. A guide to convert_imageset.cpp
  4. Face recognition Library [closed]
  5. OpenCV template matching and transparency
  6. What is “semantic segmentation” compared to “segmentation” and “scene labeling”?
  7. Pixel access in OpenCV 2.2
  8. proportions of a perspective-deformed rectangle
  9. Sobel filter kernel of large size
  10. Where do I start learning about image processing and object recognition? [closed]
  11. Is there a way to detect if an image is blurry? [closed]
  12. How can I sharpen an image in OpenCV?
  13. How to make the blackboard text appear clearer using MATLAB?
  14. Image segmentation based on edge pixel map [closed]
  15. Horizontal Line detection with OpenCV
  16. Detect and visualize differences between two images with OpenCV Python
  17. Window width and center calculation of DICOM image
  18. Algorithm to detect presence of text on image
  19. Filling holes inside a binary object
  20. Detect text area in an image using python and opencv
  21. Matching image to images collection
  22. Crop black edges with OpenCV
  23. Is Laplacian of Gaussian for blob detection or for edge detection?
  24. module’ object has no attribute ‘drawMatches’ opencv python
  25. numpy with python: convert 3d array to 2d
  26. Pytorch RuntimeError: The size of tensor a (4) must match the size of tensor b (3) at non-singleton dimension 0
  27. Is it possible to tell the quality level of a JPEG?
  28. Add padding to images to get them into the same shape
  29. How to read a frame from YUV file in OpenCV?
  30. How do I load and edit a bitmap file at the pixel level in Swift for iOS?

Leave a Comment