Carmona, Enrique J.Martínez Campos, JavierMira Mira, JoséRincón Zamorano, MarianoBachiller Mayoral, MargaritaMartínez Tomás, Rafael2024-06-112024-06-112009-011872-8286http://dx.doi.org/10.1016/j.neucom.2008.06.013https://hdl.handle.net/20.500.14468/22407In this work we propose a general top–down feedback scheme between adjacent description levels to interpret video sequences. This scheme distinguishes two types of feedback: repair-oriented feedback and focus-oriented feedback. With the first it is possible to improve the system's performance and produce more reliable and consistent information, and with the second it is possible to adjust the computational load to match the aims. Finally, the general feedback scheme is used in different examples for a visual surveillance application which improved the final result of each description level by using the information in the higher adjacent level.eninfo:eu-repo/semantics/openAccessjournal articleVisual Surveillance SystemsVideo Sequence InterpretationHigh Level VisionPredictive Diagnosis TaskFeedback between Description Levels