During the past four decades, important research efforts in computer vision have been focused on developing theories, methods and systems applied to the description of human movements in image sequences. Broadly speaking, in the past the main goal was the estimation of quantitative parameters describing where was motion. Nowadays, the focus is on the analysis of image sequences by incorporating cognitive processes which provides interpretation and understanding for detected human motion. That is, the true challenge is the generation of qualitative descriptions about the meaning of motion, therefore understanding not only where, but also why motion is being observed. This goal called Human Sequence Evaluation (HSE) has become a key task in many promising computer-vision applications, such as smart video surveillance or advanced human-computer interfaces.

Towards this end, the advancement of novel cognitive capabilities does increase the relation between multiple research areas, using computer vision as the main tool: it is then of particular interest to organize a workshop which encourages links between Computer Vision research and other fields, such as Artificial Intelligence, Computational Linguistics, Computer Animation and Multimedia Semantics, which share common goals to understand and describe the human behaviour observed in image sequences. The aim is then to have representatives from all these research areas, and to promote discussion between the different research groups on topics of mutual interest.

Thus, the First International Workshop on Tracking Humans for the Evaluation of their Motion in Image Sequences (THEMIS’08) will take a step forward towards the interpretation of human behaviour in image sequences. The goal is to provide cross-disciplinary approach to addressing the aforementioned problems on the topic of computational models of human behaviour understanding using cognitive systems, with the purpose to advance understanding of the state-of-the-art on evaluation in the frame of cognitive processing. This will imply to discuss about possible research synergies and collaborations, and also about semantic enhancements which can be applied based on the numeric data obtained from tracking processes.

As a result, THEMIS2008 will aim at promoting interaction and collaboration among researchers specialising in these related fields:

• Cognitive visual surveillance;
• Ambient intelligence;
• High-level behaviour recognition and scene understanding;
• Identification of semantic regions in human-populated scenarios;
• Ontologies and semantic mapping on human motion;
• Human behaviour analysis: articulated models and animation;
• Content-based browsing, indexing and retrieval of behaviours in video;
• Natural-language description of human behaviours from image sequences;
• Learning human models for behaviour synthesis (body/face);
• Learning human motion semantics from multimedia content.