Activity and Motion Detection Based on Measuring Texture Change

We estimate the speed of texture change by measuring the spread of texture vectors in their feature space. This method allows us to robustly detect even very slow moving objects. By learning a normal amount of texture change over time, we are also able to detect increased activities in videos. We illustrate the performance of the proposed techniques on videos from PETS repository and the Temple University Police department.

• Type: Conference
• Year: 2005
• Where: MLDM
• Authors: Longin Jan Latecki, Roland Miezianko, Dragoljub Pokrajac
• Keywords: Machine Learning, MLDM 2005, Slow Moving Objects, Texture Change, Texture Vectors