Oskar Puschmann

Senior Adviser

(+47) 993 53 677
oskar.puschmann@nibio.no

Place
Ås R9

Visiting address
Raveien 9, 1430 Ås

Abstract

Repeat photography is an efficient method for documenting long-term landscape changes. So far, the usage of repeat photographs for quantitative analyses is limited to approaches based on manual classification. In this paper, we demonstrate the application of a convolutional neural network (CNN) for the automatic detection and classification of woody regrowth vegetation in repeat landscape photographs. We also tested if the classification results based on the automatic approach can be used for quantifying changes in woody vegetation cover between image pairs. The CNN was trained with 50 × 50 pixel tiles of woody vegetation and non-woody vegetation. We then tested the classifier on 17 pairs of repeat photographs to assess the model performance on unseen data. Results show that the CNN performed well in differentiating woody vegetation from non-woody vegetation (accuracy = 87.7%), but accuracy varied strongly between individual images. The very similar appearance of woody vegetation and herbaceous species in photographs made this a much more challenging task compared to the classification of vegetation as a single class (accuracy = 95.2%). In this regard, image quality was identified as one important factor influencing classification accuracy. Although the automatic classification provided good individual results on most of the 34 test photographs, change statistics based on the automatic approach deviated from actual changes. Nevertheless, the automatic approach was capable of identifying clear trends in increasing or decreasing woody vegetation in repeat photographs. Generally, the use of repeat photography in landscape monitoring represents a significant added value to other quantitative data retrieved from remote sensing and field measurements. Moreover, these photographs are able to raise awareness on landscape change among policy makers and public as well as they provide clear feedback on the effects of land management.

Abstract

Norway has a political goal to minimize the loss of cultural heritage due to removal, destruction or decay. On behalf of the national Directorate for Cultural Heritage, we have developed methods to monitor Cultural Heritage Environments. The complementary set of methods includes (1) landscape mapping through interpretation of aerial photographs, including field control of the map data, (2) qualitative and quantitative initial and repeat landscape photography, (3) field recording of cultural heritage objects including preparatory analysis of public statistical data, and (4) recording of stakeholder attitudes, perceptions and opinions. We applied these methods for the first time to the historical clustered farm settlement of Havrå in Hordaland County, West Norway. The methods are documented in a handbook and can be applied as a toolbox, where different monitoring methods or frequency of repeat recording may be selected, dependent on local situations, e.g., on the landscape character of the area in focus.

Abstract

When ground level photography is to be used in landscape monitoring, it is important to record when, where, how and possibly even why the photographs are taken. Standardisation enables better repeat photography in the future and maximises comparability of photos over time. We used a Cultural Environment protected by law on the peninsula of Bygdøy,Oslo municipality, as a study area to document advantages and disadvantages of different approaches to the first round of landscape photography for long-term monitoring.

To document

Abstract

The World Trade Organization (WTO) will initiate negotiations on the further liberalization of the global trade with agricultural commodities by the end of 1999. These negotiations are basedon Article 20 of the Uruguay Round’s Agreement on Agriculture, which states, inter alia, that the reform process is to be continued, with the long-term objective of substantial and progressive reductions in the support and protection of the agricultural sector. In this context, however, a number of issues are to be taken into consideration, including the so-called non-trade concerns. The Norwegian authorities have started preparations for the new round of WTO negotiations, and have placed substantial emphasis on the non-trade concerns. Norwegian agriculture is regarded as being a ”producer” of more than just food and fibres, for example, national food security, viable rural areas and environmental benefits. The term ”Multifunctional Agriculture” is being increasingly applied to describe these additional functions1. With regard to Norwegian agriculture, it will be of major importance for Norway that sufficient consideration is given to the non-trade and other concerns during the next round of the WTO negotiations. In the summer/fall of 1998, the Norwegian Ministry of Agriculture initialized an evaluation program in order to survey and analyse a number of issues in relation to ”multifunctional agriculture”. The present report is one of the contributions in this context.