Binary Robust Independent Elementary Features(BRIEF) is a feature descriptor. It samples 128 pairs of random points around a feature, and fills up a vector. Each dimension's value is calculated as either 1 or 0, depending on some condition for each pair.
Example
If the first point in the pair is greater than the second in terms of intensity, we choose 1, else 0. This will be done for all of the 128 pairs.