Research topics at ISE Lab are based on the work developed by Prof. Hans-Hellmut Nagel and cover different cognitive skills for the semantic understanding of human behaviors in image sequences. These behaviors captured from camera sensors are explained by means of natural-language texts and virtual environments.

The ISE Lab is headed by Dr. F. Xavier Roca and is located at the Computer Vision Center (CVC) in Barcelona, Spain.

The analysis of image sequences involving human agents allows multiple applications, and implies lots of difficulties. This challenging domain is referred as Video-Hermeneutics (VH). A generic VH system transforms image data into conceptual descriptions, and vice versa. This abstraction process is addressed by describing the VH framework as a modular scheme, each module concerned to a specific task.

This analysis of video sequences incorporates high-level processes to determine the meaning of human motion. As a result, the goal is set motion naming, i.e. the automatic generation of semantic descriptions about when (ASL), where (ISL), what (PDL), who (SDL), how (CIL) and why (BIL) is motion being detected in complex scenes.

As a result, high-level interpretations provide a challenging domain of research on Cognitive Science, which encompasses topics on Computer Vision, Artificial Intelligence, Computational Linguistics and Computer Animation.