Employing the power of Semantic Grid services into pervasive problem domains such as video analysis would allow for more effective distributed processing. A vast amount of ecological data from the EcoGrid of varying qualities and features will need to be analysed efficiently. As manual processing by humans can be time and labour intensive, video and image processing tools can go some way to addressing such problems since they are computationally fast. However, most video analyses that utilise a combination of these tools are still done manually. We propose a semantic-based hybrid workflow composition method that strives to provide automation to speed up this process. The main components of this framework are presented, along with the illustration of a scenario where these components act as Semantic Grid services for EcoGrid video analysis.