Modelling vague places with knowledge from the Web

Jones, Chris; Purves, Ross S.; Clough, Paul; Joho, Hideo

doi:10.1080/13658810701850547

Cited by 315 publications

(132 citation statements)

References 32 publications

Supporting

Mentioning

117

Contrasting

Unclassified

Order By: Relevance

“…Montello et al [34] investigated this problem by asking residents of Santa Barbara to sketch the boundaries of downtown on a map. More recently, Jones et al [35] searched for place names co-occurring with vernacular regions, and used density surfaces to estimate the borders of the fiat regions. Both of these sets of techniques used human perception of the boundaries, or locations found inside a region, to delineate a spatial extent for vernacular regions.…”

Section: Determining Region Boundariesmentioning

confidence: 99%

Delineation of Valleys and Valley Floors

Straumann

Purves

2008

Geographic Information Science

View full text Add to dashboard Cite

Methods to automatically derive landforms have typically focused on pixel-based, bottom-up approaches and most commonly on the derivation of topographic eminences. In this paper we describe an object-based, top-down algorithm to identify valley floors. The algorithm is based on a region growing approach, seeded by thalwegs with pixels added to the region according to a threshold gradient value. Since such landforms are fiat we compare the results of our algorithm for a particular valley with a numberof textual sources describing that valley. In a further comparison, we computed a pixel-based six-fold morphometric classification for regions we classified as either being, or not being, valley floor. The regions classified as valley floor are dominated by pla nar slopes and channels,though the algorithm is robust enough to allow local convexities to be classified as within the valley floor. Future work will explore the delineation of valley sides, and thus complete valleys. Abstract. Methods to automatically derive landforms have typically focused on pixel-based, bottom-up approaches and most commonly on the derivation of topographic eminences. In this paper we describe an object-based, top-down algorithm to identify valley floors. The algorithm is based on a region growing approach, seeded by thalwegs with pixels added to the region according to a threshold gradient value. Since such landforms are fiat we compare the results of our algorithm for a particular valley with a number of textual sources describing that valley. In a further comparison, we computed a pixel-based sixfold morphometric classification for regions we classified as either being, or not being, valley floor. The regions classified as valley floor are dominated by planar slopes and channels, though the algorithm is robust enough to allow local convexities to be classified as within the valley floor. Future work will explore the delineation of valley sides, and thus complete valleys. Delineation of Valleys and Valley Floors

show abstract

Section: Determining Region Boundariesmentioning

confidence: 99%

Delineation of Valleys and Valley Floors

Straumann

Purves

2008

Geographic Information Science

View full text Add to dashboard Cite

show abstract

“…This problem has been recognized by those working on administrative gazetteers as a pressing issue [14]. Recent research has used datamining techniques to identify toponyms with entries in gazetteers which co-occur with known vernacular names and to define potential spatial extents related to vernacular names [16]. However, most work has so far addressed relatively large regions (such as Mid-Wales or the South of France), though work is currently ongoing on the automated identification and definition of vernacular names with finer granularities [22].…”

Section: Methods To Describe "Where/ Specific Of"mentioning

confidence: 99%

Describing the Where – Improving Image Annotation and Search through Geography

Purves¹,

Edwardes²,

Sanderson³

2008

Metadata Mining for Image Understanding

View full text Add to dashboard Cite

Abstract. Image retrieval, using either content or text-based techniques, does not match up to the current quality of standard text retrieval. One possible reason for this mismatch is the semantic gap -the terms by which images are indexed do not accord with those imagined by users querying image databases. In this paper we set out to describe how geography might help to index the where facet of the Pansofsky-Shatford matrix, which has previously been shown to accord well with the types of queries users make. We illustrate these ideas with existing (e.g. identifying place names associated with a set of coordinates) and novel (e.g. describing images using land cover data) techniques to describe images and contend that such methods will become central as increasing numbers of images become georeferenced.

show abstract

“…For example, taking a vernacular geography approach, Jones et al (2008) explored the modelling of vague places and Hollenstein and Purves (2010) reported on the extent of places (e.g. city cores).…”

Section: Flickr and Tourism Studiesmentioning

confidence: 99%

Towards (Re)Constructing Narratives from Georeferenced Photographs through Visual Analytics

Straumann

Çöltekin

Andrienko

2014

The Cartographic Journal

View full text Add to dashboard Cite

We present a study that explores methodological steps towards (re)constructing collective narratives from the phototaking behaviour of two groups (foreign tourists and inhabitants of Switzerland) by analysing spatial and temporal patterns in user-contributed, georeferenced photographs of Zurich, Switzerland. We reason that the photographers typically capture a scene or a moment because they want to remember or share it, thus these scenes or moments are meaningful to them. Various scholars suggest that the human experience (i.e. this meaningfulness) is what separates a place from the mathematical descriptions of space. While this notion is well known in larger geographic literature, it is under-explored in cartographic research. We respond to this research gap and reconstruct static and dynamic patterns of photo-taking and -sharing behaviour to assist in capturing the implicit meaning in the studied locations. These locations may be meaningful to only a certain group of people in certain moments; therefore, studying group differences in spatial and temporal photo-taking patterns will help building a collective and comparative story about the studied place. In our study, we focus on experiences of foreign versus domestic visitors, and in the process, we examine the potential (and feasibility) of georeferenced photographs for extracting such collective narratives using qualitative and quantitative visual analytical methods.

show abstract

Modelling vague places with knowledge from the Web

Cited by 315 publications

References 32 publications

Delineation of Valleys and Valley Floors

Delineation of Valleys and Valley Floors

Describing the Where – Improving Image Annotation and Search through Geography

Towards (Re)Constructing Narratives from Georeferenced Photographs through Visual Analytics

Contact Info

Product

Resources

About