Landscape Pattern Detection in Archaeological Remote Sensing

Automated detection of landscape patterns on Remote Sensing imagery has seen virtually no development or application in the archaeological domain, notwithstanding the fact that large portion of cultural landscapes worldwide are characterised by land engineering applications. The current extraordinary availability of remotely sensed data makes it now urgent to envision and develop automatic methods that can simplify the inspection of RS data and the extraction of relevant information from them, as the quantity of data is no longer manageable by traditional ‘human’ visual interpretation. This paper expands on the development of automatic methods for the detection of target landscape features –intended as field system patterns– in very high spatial resolution images, within the framework of VEiL, a landscape archaeology project based in Italy and focused on the engineered landscape of the Roman city of Aquileia. The targets of interest consist of a variety of similarly oriented objects (such as roads, drainage channels etc.) that concur to demark the current landscape organisation, which reflects the one imposed by Romans from the 2nd cent. BC onward. The proposed workflow exploits the textural and shape properties of real-world elements forming the field patterns using multiscale analysis of dominant oriented response filters. Experiments using remote sensing imagery show that the proposed approach provides accurate localisation of target linear objects and alignments signalled by a wide range of physical entities with very different characteristics.