No abstract

ABSTRACT:With the rapid development of Precision Agriculture (PA) promoted by high-resolution remote sensing, it makes significant sense in management and estimation of agriculture through crop classification of high-resolution remote sensing image. Due to the complex and fragmentation of the features and the surroundings in the circumstance of high-resolution, the accuracy of the traditional classification methods has not been able to meet the standard of agricultural problems. In this case, this paper proposed a classification method for high-resolution agricultural remote sensing images based on convolution neural networks(CNN). For training, a large number of training samples were produced by panchromatic images of GF-1 high-resolution satellite of China. In the experiment, through training and testing on the CNN under the toolbox of deep learning by MATLAB, the crop classification finally got the correct rate of 99.66% after the gradual optimization of adjusting parameter during training. Through improving the accuracy of image classification and image recognition, the applications of CNN provide a reference value for the field of remote sensing in PA.

Occupant classifcation is essential to a smart airbag system that can either turn off or deploy in a less harmful way according to the p p e of the occupants in the front seat. This paper presents U monocular vision-based occupant classification approach to d a s s i h the occupants into five categories including empty seats, adiilts in normal position, adults out of position, front-facing chila7infant seats, and rear-facing infant seats. The proposed approach consists oj image representation and pattern classification. The image representation step computes Haar wavelers and edge features from the monochrome video frames. A support vector machine (SVM) classifier next determines the occupant category based on the representative features. We have tested our approach on a large variew of indoor and outdoor images acquired under various illumination cotadifions for occupants with different appearances, sizes and shapes. With a strict occupant exclusive training/testing split, our approach has achieved an average correct classification rate of 97.18% among the five occupant categories.

Integrating multiple data sources is a very important strategy to obtain relevant solutions in geo-scientific analysis. This paper mainly deals with the integration of Geographical Information System (GIS) data, stereo aerial imagery and a Digital Surface Model (DSM) to extract wind erosion obstacles (namely tree rows and hedges) in open landscapes. Different approaches, such as image segmentation, edge extraction, linking, grouping and 3-dimensional verification with the DSM, are combined to extract the objects of interest. Experiments show that most wind erosion obstacles can be successfully extracted by the developed system.

ABSTRACT:GIS is now faced with the challenge how to represent and understand the fast-paced, constantly changing world, given increasingly real-time data including readings from large-scale distributed sensors and large quantities of simulation data generated by computation models. Traditional static GIS pays more attention to representing historic data and Temporal GIS(TGIS) only treats time as a occasional but not critical factor and can't support the explicit change representation. In this context, Real-time GIS(RGIS) is put forward and its data model becomes a key problem how to make an appropriate abstraction over the rapid changes implied in real-time data stream and establish the general interaction relationship between them. The paper proposes a spatiotemporal changeoriented three-domain model with the emphasis on the semantic interaction relationship of object, event and process. Based on this model, a semantic enrichment method for multi-scale spatiotemporal change is put forward. Finally, as a RGIS application, indoor fire disaster simulation is illustrated and proves the validity of the proposed model.