A key point in ORB feature detection is:

ORB (Oriented FAST and Rotated BRIEF) feature detection is a fast robust local feature detector, first presented by Ethan Rublee et al. in 2011. A key point in ORB feature detection is its ability to provide a fast and efficient alternative to SIFT and SURF in computation cost, matching performance and mainly the patents.

Here are the steps involved in ORB feature detection:

1. Scale-Space Extrema Detection: The first step in ORB is to detect the keypoints in the image. ORB uses FAST (Features from Accelerated Segment Test) to find keypoints, then applies Harris corner measure to find top N points among them.

2. Orientation Assignment: The keypoints detected from the previous step are assigned an orientation based on the intensity weighted centroid of the patch with the selected corner at the center. The result is rotation invariant features.

3. Descriptor Extraction: The next step is to provide a unique identifier for each keypoint, which is done by using BRIEF (Binary Robust Independent Elementary Features) descriptors. However, BRIEF does not perform well under rotation. Hence, ORB modifies it by adding a rotation component to it, making it rotation invariant.

4. Keypoint Matching: The final step is to match these keypoints with the keypoints in another image, which is done using Hamming distance.

So, the key point in ORB feature detection is its ability to efficiently detect and describe keypoints in an image, and its robustness to rotation, scale, and lighting variations.