Search NASA⌕ Search

DOE OSTI · 965862

Non-Negative Matrix Factorization of Partial Track Data for Motion

Abstract

This paper addresses the problem of segmenting low level partial feature point tracks belonging to multiple motions. We show that the local velocity vectors at each instant of the trajectory are an effective basis for motion segmentation. We decompose the velocity profiles of point tracks into different motion components and corresponding nonnegative weights using non-negative matrix factorization (NNMF). We then segment the different motions using spectral clustering on the derived weights. We test our algorithm on the Hopkins 155 benchmarking database and several new sequences, demonstrating that the proposed algorithm can accurately segment multiple motions at a speed of a few seconds per frame. We show that our algorithm is particularly successful on low-level tracks from real-world video that are fragmented, noisy and inaccurate

Explore related subjects

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Cheriyadat, Anil M. 2009-01-01. Non-Negative Matrix Factorization of Partial Track Data for Motion. https://doi.org/10.1109/iccv.2009.5459311. https://searchnasa.com/record/osti%3A965862/non-negative-matrix-factorization-of-partial-track-data-for-motion

Citations retain the original authors and DOI and include this site’s record URL. If this discovery service contributed to your research, you can also cite Search NASA by Indiciae: BibTeX · RIS.

KEEP EXPLORING

Related reports

Identifying Genomic Islands with Deep Neural Networks

Background Horizontal gene transfer is the main source of adaptability for bacteria, through which genes are obtained from different sources including bacteria, archaea, viruses, and eukaryotes. This process promotes the rapid spread of genetic information across lineages, typically in the form of clusters of genes referred to as genomic islands (GIs). Different types of GIs exist, and are often classified by the content of their cargo genes or their means of integration and mobility. While various computational methods have been devised to detect different types of GIs, no single method is capable of detecting all types. Results We propose a method, which we call Shutter Island, that uses a deep learning model (Inception V3, widely used in computer vision) to detect genomic islands. The intrinsic value of deep learning methods lies in their ability to generalize. Via a technique called transfer learning, the model is pre-trained on a large generic dataset and then re-trained on images that we generate to represent genomic fragments. We demonstrate that this image-based approach generalizes better than the existing tools. Conclusions We used a deep neural network and an image-based approach to detect the most out of the correct GI predictions made by other tools, in addition to making novel GI predictions. The fact that the deep neural network was re-trained on only a limited number of GI datasets and then successfully generalized indicates that this approach could be applied to other problems in the field where data is still lacking or hard to curate.

Computer Vision↗

Aerial Scene Recognition using Efficient Sparse Representation

Advanced scene recognition systems for processing large volumes of high-resolution aerial image data are in great demand today. However, automated scene recognition remains a challenging problem. Efficient encoding and representation of spatial and structural patterns in the imagery are key in developing automated scene recognition algorithms. We describe an image representation approach that uses simple and computationally efficient sparse code computation to generate accurate features capable of producing excellent classification performance using linear SVM kernels. Our method exploits unlabeled low-level image feature measurements to learn a set of basis vectors. We project the low-level features onto the basis vectors and use simple soft threshold activation function to derive the sparse features. The proposed technique generates sparse features at a significantly lower computational cost than other methods~\cite{Yang10, newsam11}, yet it produces comparable or better classification accuracy. We apply our technique to high-resolution aerial image datasets to quantify the aerial scene classification performance. We demonstrate that the dense feature extraction and representation methods are highly effective for automatic large-facility detection on wide area high-resolution aerial imagery.

Computer Vision↗