Ground truth to fake geographies: machine vision and learning in visual practices
- PDF / 655,977 Bytes
- 10 Pages / 595.276 x 790.866 pts Page_size
- 38 Downloads / 150 Views
ORIGINAL ARTICLE
Ground truth to fake geographies: machine vision and learning in visual practices Abelardo Gil‑Fournier1 · Jussi Parikka1,2 Received: 13 September 2019 / Accepted: 18 August 2020 © The Author(s) 2020
Abstract This article investigates the concept of the ground truth as both an epistemic and technical figure of knowledge that is central to discussions of machine vision and media techniques of visuality. While ground truth refers to a set of remote sensing practices, it has a longer history in operational photography, such as aerial reconnaissance. Building on a discussion of this history, this article argues that ground truth has shifted from a reference to the physical, geographical ground to the surface of the images echoing earlier points raised by philosopher Jean-Luc Nancy that there is a ground of the image that is central to the task of analysis beyond representational practices. Furthermore, building on the practices of pattern recognition, composite imaging, and different interpretational techniques, we discuss contemporary practices of machine learning that mobilizes geographical earth observation datasets for experimental purposes, including tests such as “fake geography” as well as artistic practices, to show how ground truth is operationalized in such contexts of AI and visual arts. Keywords Remote sensing · Machine vision · Machine learning · Visual culture · Operational image
1 Introduction “Knowing how to discern a groundless image from an image that is nothing but a blow is an entire art in itself”—JeanLuc Nancy (2005: 25). Geographical knowledge starts with how we see, or even more accurately, with the production of images through which we see, observe, analyze, and identify. Images are the supportive instrument for understanding territorial formations, and their mediating role is crucial in establishing the seeing that defines geographical entities of knowledge. This can include the most (seemingly) inconspicuous practices, such as coloring maps or populating them with place and site names. It can include the observation of how everyday life is filled with a variety of forms of geographical knowledge embedded in digital platforms for navigation and other purposes. Geographic information systems are the mainstay * Abelardo Gil‑Fournier [email protected] Jussi Parikka [email protected] 1
FAMU, Prague, Czechia
University of Southampton, Southampton, UK
2
of such practices that emerge through the mobilization of data and electronic communication technologies where the physical and the virtual sign entangle (see Pickles 1994). What has been established by decades of critical research is that the relationship between geography and images is heavily overdetermined: the visual and epistemic systems giving a sense of landscape formations are embedded in multiple social, colonial, gendered, and other forms of representational biases (see Rose 1993; Rogoff 2000; Thrift 2008). What’s more, this complex role of images in geographical knowledge has also g
Data Loading...
