In this paper we present a novel way to analyze LADAR images and model its data. Having an aerial LADAR image as data source, our aim is to extract a parametric description of the ground of our scenario in order to discern between the data samples that belong to the ground and those that belong to vehicles, objects or clutter. Once the samples are divided, we process each of the objects to perform an early classification refering to the object type (vehicle, building or clutter). The final step of our method is to estimate the pose of the interesting objects by building its corresponding oriented 3D bounding box.
Our method uses robust statistics in order to extract proper descriptions of both the ground and the oriented bounding boxes of the objects. Specifically, we use two robust parameter estimators : The Least Median Squares and the Variable Bandwith Quick Maximum Density Power Estimator, depending on the percentage of outliers that may be present in the different steps of our approach. Our method is open and can also be used along with other approaches that focus on extracting 3D invariant features or enhanced by applying a recognition step with the aid of model databases and 3D registration algorithms, such as the ICP.
The vast amount of video sequences available in digital format presents considerable challenges for descriptor extraction and information retrieval. The dominant motion in a video scene proves to be very important to characterize video sequences, but the cost to compute it is high when working in image domain because the retrieval of the optical flow of two consecutive frames is very demanding in terms of time, as well as the following estimation of parameters. In this paper we present a method to extract an affine description of the global motion of a video sequence using a robust estimator based on compressed domain data, where the motion vector field is already calculated. We perform further analysis, isolating and describing parametrically the local motions using the mean shift analysis as non parametric clustering method. Applying our approach to real sequences, we take advantage of the parametric description extracted to perform video summarization of the sequences using image mosaics.