Disclosed is a corner detection method based on a dynamic vision sensor. The method comprises the following steps: 1) constructing a corner detection template for each newly incoming event in dynamic vision sensor data by taking same as the center of a circle; 2) counting the number of corresponding events in the template according to the polarity and timestamp of the event at the center of the circle; 3) determining, according to the counted number of corresponding events, whether the center of the circle is an initial corner; and 4) carrying out non-maximum suppression on the determined initial corner to obtain a final corner. Compared with the prior art, the method has the advantages of being quick, accurate, etc.
展开▼