Being able to promptly analyse mass video data with regards to content is increasingly important for complex investigative procedures, especially for those dealing with crime scenes. Video data is used to solve crimes, to create investigation approaches and to spot connections between crimes. Currently, this data is analysed manually. This often requires hundreds or thousands of hours of investigative work. This effort multiplies even further in the case that additional evidence is offered multiple times by civilian witnesses. The prompt analysis of video data, however, is fundamental – especially in the event of terrorist attacks – to prevent immediate, subsequent attacks.
The overarching goal of the joint project FLORIDA is to implement legally compliant tools for law enforcement agencies that will increase their effectiveness in analysing mass video data and speed up investigative work. A range of new methods for the analysis of video data will be developed in close cooperation with end users. These include geo-spatial crime scene reconstruction, interactive exploration of extracted information (Visual Analytics), prioritisation of video data, generic object search and audio analysis. Combining these methods will greatly reduce the amount of data to be analysed by investigators, thus increasing focus on relevant events and supporting decision making.