First 1-M Resolution Land Cover Map Labeling the Overlap in the 3rd Dimension: The 2018 Map for Wallonia

Land cover maps contribute to a large diversity of geospatial applications, including but not limited to land management, hydrology, land use planning, climate modeling and biodiversity monitoring. In densely populated and highly fragmented landscapes as observed in the Walloon region (Belgium), very high spatial resolution is required to depict all the infrastructures, buildings and most of the structural elements of the semi-natural landscapes (like hedges and small water bodies). Because of the resolution, the vertical dimension needs explicit handling to avoid discontinuities incompatible with many applications. For example, how to map a river flowing under a bridge? The particularity of our data is to provide a two-digit land cover code to label all the overlapping items. The identification of all the overlaps resulted from the combination of remote sensing image analysis and decision rules involving ancillary data. The final product is therefore semantically precise and accurate in terms of land cover description thanks to the addition of 24 classes on top of the 11 pure land cover classes. The quality of the map has been assessed using a state-of-the-art validation scheme. Its overall accuracy is as high as 91.5%, with an average producer’s accuracy of 86% and an average user’s accuracy of 91%.

A Unified Model and Algorithms for Temporal Map Labeling

We consider map labeling for the case that a map undergoes a sequence of operations such as rotation, zoom and translation over a specified time span. We unify and generalize several previous models for dynamic map labeling into one versatile and flexible model. In contrast to previous research, we completely abstract from the particular operations and express the labeling problem as a set of time intervals representing the labels’ presences, activities and conflicts. One of the model’s strength is manifested in its simplicity and broad range of applications. In particular, it supports label selection both for map features with fixed position as well as for moving entities (e.g., for tracking vehicles in logistics or air traffic control). We study the active range maximization problem in this model. We prove that the problem is -complete and [1]-hard, and present constant-factor approximation algorithms. In the restricted, yet practically relevant case that no more than k labels can be active at any time, we give polynomial-time algorithms as well as constant-factor approximation algorithms.

Improving Local Search for Minimum Weight Vertex Cover by Dynamic Strategies

The minimum weight vertex cover (MWVC) problem is an important combinatorial optimization problem with various real-world applications. Due to its NP hardness, most works on solving MWVC focus on heuristic algorithms that can return a good quality solution in reasonable time. In this work, we propose two dynamic strategies that adjust the behavior of the algorithm during search, which are used to improve a state of the art local search for MWVC named FastWVC, resulting in two local search algorithms called DynWVC1 and DynWVC2. Previous MWVC algorithms are evaluated on graphs with random or hand crafted weights. In this work, we evaluate the algorithms on the vertex weighted graphs that obtained from an important real world problem, the map labeling problem. Experiments show that our algorithm obtains better results than previous algorithms for MWVC and maximum weight independent set (MWIS) on these real world instances. We also test our algorithms on massive graphs studied in previous works, and show significant improvements there.

Folk perception of variation in Cavite Chabacano

Cavite Chabacano, an endangered creole language spoken in Cavite City, Philippines, has dialectal variation that can be traced to the settlement patterns established by the Spanish during the colonial era. This study focuses on Cavite Chabacano speakers’ metalinguistic awareness of dialectal variation, what their attitudes are toward it, and how they believe the different dialects are influenced by the superstrate Spanish or the substrate Tagalog. Participants’ comments during a map-labeling task show where Chabacano is still believed to be spoken and reveal that they have high metalinguistic awareness of variation in the vowel system and in second person pronoun usage. The Chabacano spoken in the San Roque district is perceived to have the closest relationship to Spanish, despite having more substrate influence in the vowel system. This study demonstrates the usefulness of perceptual dialectology for endangered language documentation and for studying variation and language attitudes in small communities and creole or other multilingual settings.

Coarse-to-Fine Lifted MAP Inference in Computer Vision

There is a vast body of theoretical research on lifted inference in probabilistic graphical models (PGMs). However, few demonstrations exist where lifting is applied in conjunction with top of the line applied algorithms. We pursue the applicability of lifted inference for computer vision (CV), with the insight that a globally optimal (MAP) labeling will likely have the same label for two symmetric pixels. The success of our approach lies in efficiently handling a distinct unary potential on every node (pixel), typical of CV applications. This allows us to lift the large class of algorithms that model a CV problem via PGM inference. We propose a generic template for coarse-to-fine (C2F) inference in CV, which progressively refines an initial coarsely lifted PGM for varying quality-time trade-offs. We demonstrate the performance of C2F inference by developing lifted versions of two near state-of-the-art CV algorithms for stereo vision and interactive image segmentation. We find that, against flat algorithms, the lifted versions have a much superior anytime performance, without any loss in final solution quality.