This paper proposes detection method of ships using navigationahmage sequence analyzed by HSV transform . The reg 重 on constructed with same color can be detected for specifying a Hue range . But it is difficult to decide a color of a target ship . So we proposed detection methods of ships by distribut 圭 on of Hue variance . W 合 verified the advantages of the proposed methods by processing images captured at the Tbkyo port and Tokyo Bay. As a result , the operator method was judged to be the most excellent 。 The operator method divides the image into a sma11 rectangular area , and to calculate the variance of Hue in the area . The areas 出 at include ships have many colors , so the variance will be high. We scanned the image with operator and check the variance , because the area wiIh high variance includes ships.It tumed out that it was not possible to detect wemn the Rain and Fog conditions . As for these conditions , we can solve by taking a picture by the infrared camera simukaneously and using value parameteL Keywords : lmage processing , Informat 加 system , HSV , Variance , Image sequence , 1>α V ' gatien system
This paper proposes a method for detecting ships on rea1 − time using navigational image sequence . As pointed out in the previous reports , our proposed method has problem in processing speed performance, although it is preclse p 「 eclslon ・ First , this paper analyzes this problem , and proposes a new method for solving them .
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.