A General Gray Code Quantized Method of Binary Feature Descriptors for Fast and Efficient Keypoint Matching

In this paper, a general Gray code quantized method of binary feature descriptors is proposed for fast and efficient keypoint matching on 3D point clouds. In our method, it includes 2 variable L and N. L is rule variable which can be used to set the encoding group length according to the feature of the real-valued descriptor, and N is bits variable which can be used to set the number of Gray code bits according to the actual system requirements. Be different from the exist method, such as B-SHOT, our proposed method has the advantages of reasonable and flexible. As an example, our method is applied on the feature descriptor SHOT and tested in a standard benchmark dataset, different variable combinations of L and N are tested in the Gray code quantized processes, the best combination of L and N is dubbed as GRAY-SHOT through performance comparison. At last, GRAY-SHOT is compared with the state-of-the-art binary 3D feature descriptor B-SHOT, experimental evaluation result shows that GRAY-SHOT offers better keypoint matching performances to B-SHOT on a standard benchmark dataset with a slight more memory footprint and time consumption.