Modeling and Robot teleoperation

The problem of multi-sensor phenomenology includes several fundamental theoretical, experimental and validation issues.

Multi-sensor modeling: The objective in our study is to predict image appearance (or pixel values) based on (a) previous knowledge about viewed scene and objects, (b) existing data (saved measurements), and (c) developed prediction models. The goal of a validation component in the process multi-sensor modeling is to assess the goodness of image predictions based on modeling or application criteria.

Robot teleoperation: The problem of interest here is about multi-sensor data fusion in order to reliably navigate a vehicle in an unknown environment. Multiple human controls are used for navigating a robot in a hazardous environment (see also Towards Hazard Aware Environments) or in a complex environment (presence of both Unmanned and Manned Aerial Vehicles on an aircraft deck).

Unsupervised and supervised band selection

Recent development of advanced hyperspectral sensors has enabled better class discrimination of objects due to a higher spectral resolution than one could achieve with standard electro-optical (EO) and infrared (IR) sensors.

Hyperspectral image analysis has been applied in several Geospatial information systems (GIS), systems for capturing, storing, analyzing and managing data referenced to the Earth. Hyperspectral sensors generate imagery that captures surface and sub-surface properties of objects, e.g., fine textured soils and provide non-invasive and nonintrusive reflectance measurements.

Application areas include environmental monitoring, sensor design, agriculture, forestry, security, cartography and military.

Common problems in the area of hyperspectral analysis involving data relevancy include optimal selections of wavelength, number of bands, and spatial and spectral resolution.
Additional issues include the modeling issues of scene, sensor and processor contributions to the measured hyperspectral values, finding appropriate classification methods, and identifying underlying mathematical models. Every problem formulation is usually also associated with multiple application constraints. For example, communication bandwidth, data storage, discrimination or classification accuracy, minimum signal-to-noise ratio, sensor and data acquisition cost must be addressed.

In our project we propose methods for unsupervised and supervised band selection and their application to hyperspectral data collected for precision farming.