Non-maximum suppression method for simplifying time complexity

The invention relates to a non-maximum suppression method for simplifying time complexity, belongs to the field of image processing, and is used for simplifying the time complexity, shortening the calculation time and improving the real-time performance of an algorithm in a non-maximum suppression process after image recognition. Different from a traditional non-maximum suppression method in which IOU calculation is carried out on the recognition result and all other results, all the recognition results are subjected to region division according to the recognition result center point, the corresponding possible association interval is solved according to the IOU threshold value, and IOU calculation is only carried out on other recognition results in the possible association interval, so that the recognition result is more accurate. The time complexity of the algorithm is reduced, and the speed of the non-maximum suppression process is finally improved. 本发明涉及一种简化时间复杂度的非极大值抑制方法，属于图像处理领域，用于在图像识别后非极大值抑制过程中简化其时间复杂