Region Based Moving Shadow Detection using Watershed Algorithm


Moving shadow location is an essential undertaking in PC vision, with applications a few fields, for example, reconnaissance, video gathering, visual following and question acknowledgment. In this project, we present a Spatio-Temporal based Moving Shadow Detection (STMSD) strategy, The primary thought is: as per the slope change of flow picture, we use the watershed calculation to accomplish versatile division forefront sub-locales, Then, the adjustments in surface of nearby video casings and ebb and flow video casing and foundation are removed, and each sub-district is characterized regarding surface element to acquire the last moving shadow and target zone. Broad tests exhibit that STMSD is better than some outstanding strategies particularly pixel-based techniques. Particularly, our strategy shows much better execution contrasted and settled square technique, which can keep up the surface consistency in one district sufficiently.


Please enter your comment!
Please enter your name here