The invention relates to a feature point matching method, system and device in binocular distance measurement of a hazardous chemical substance stack. The method comprises the steps of adopting a binocular camera to obtain a first image and a second image of the hazardous chemical substance stack; extracting matched feature point pairs from the first image and the second image based on an SURF algorithm, and obtaining coordinates of the matched feature point pairs; determining a neighborhood range of the first feature point according to the coordinates of the feature point pair, wherein the first feature point is any feature point extracted from the first image; judging whether the second feature point is in a neighborhood range of the first feature point or not according to the coordinates of the second feature point, wherein the second feature point is a feature point matched with the first feature point in the second image; and if the second feature point is in the neighborhood range of the first feature point, taking the first feature point and the second feature point as screened feature point pairs which are matched with each other, otherwise, removing the first feature pointand the second feature point. According to the invention, the matching rate and the matching accuracy of the feature points are greatly improved.