Proceedings
Authors
| Filter results4 paper(s) found. |
|---|
1. Application of Information Technologies in Precision ApicultureApiculture, widely known as beekeeping, is one of the agriculture’s sub directions, where Precision Agriculture (PA) methods can be successfully applied. Adaptation of PA methods and technics into Apiculture, as well as integrating information technologies into beekeeping process can change and improve the beekeepers understanding of bee... E. Stalidzans, A. Zacepins, J. Meitalovs |
2. Estimating Crop Leaf Area Index from Remotely Sensed Data: Scale Effects and Scaling MethodsLeaf area index (LAI) of crop canopies is significant for growth condition monitoring and crop yield estimation, and estimating LAI based on remote sensing observations is the normal way to assess regional crop growth. However, the scale effects of LAI make multi-scale observations harder to be fully and effectively utilized for LAI estimation. A systematical statistical strategy... Y. Dong , J. Wang , C. Li , G. Yang, X. Song, W. Huang |
3. High Resolution Vegetation Mapping with a Novel Compact Hyperspectral Camera SystemThe COSI-system is a novel compact hyperspectral imaging solution designed for small remotely piloted aircraft systems (RPAS). It is designed to supply accurate action and information maps related to the crop status and health for precision agricultural applications. The COSI-Cam makes use of a thin film hyperspectral filter technology which is deposited onto an image sensor chip resulting in a compact and lightweight instrument design. This paper reports on the agricultural monitoring... B. Delauré, P. Baeck, J. Blommaert, S. Delalieux, S. Livens, A. Sima, M. Boonen, J. Goffart, G. Jacquemin, D. Nuyttens |
4. Supervised Feature Selection and Clustering for Equine Activity RecognitionIn this paper we introduce a novel supervised algorithm for equine activity recognition based on accelerometer data. By combining an approach of calculating a wide variety of time-series features with a supervised feature significance test we can obtain the best suited features using just 5 labeled samples per class and without requiring any expert domain knowledge. By using a simple cluster assignment algorithm with these obtained features, we get a classification algorithm that achieves a mean... T. De waele, D. Peralta, A. Shahid, E. De poorter |