The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
Many computer vision tasks such as large-scale image retrieval and nearest-neighbor classification perform similarity searches using Approximate Nearest Neighbor (ANN) indexes. These applications rely on the quality of ANN retrieval for success. Popular indexing methods for ANN queries include forests of kd-trees (KDT) and hierarchical k-means (HKM). The dominance of these two methods has led to implementations...
We present a novel structure, called a Subspace Forest, designed to provide an efficient approximate nearest neighbor query of subspaces represented as points on Grassmann manifolds. We apply this structure to action recognition by representing actions as subspaces spanning a sequence of thumbnail image tiles extracted from a tracked entity. The Subspace Forest lifts the concept of randomized decision...
This paper presents a method for unsupervised learning and recognition of human actions in video. Lacking any supervision, there is nothing except the inherent biases of a given representation to guide grouping of video clips along semantically meaningful partitions. Thus, in the first part of this paper, we compare two contemporary methods, Bag of Features (BOF) and Product Manifolds (PM), for clustering...
This paper presents a completely unsupervised mechanism for learning micro-actions in continuous video streams. Unlike other works, our method requires no prior knowledge of an expected number of labels (classes), requires no silhouette extraction, is tolerant to minor tracking errors and jitter, and can operate at near real time speed. We show how to construct a set of training “tracklets,” how to...
The use of computers and sensors to detect and classify targets, often called aided target recognition (ATR), is an important component of military and civilian surveillance. Carrying it outfrom unmanned aerial vehicles is expensive in terms of both manpower and hardware. In this paper, we discuss the creation of a distributed ATR (DATR) method which replaces a single monolithic approach to ATR with...
We propose an intelligent agent-based system for the automatic decluttering of a representative net-centric interface designed for controlling multiple unmanned aerial vehicles (UAVs) by a single operator. Our concept is called ARID, for Agent-based Reduction of Information Density. Intelligent agents can reduce the cognitive load imposed upon an operator by de-emphasizing those aspects of a display...
Unmanned vehicle control algorithms are continuously evolving, but may still overlook benefits of the intrinsic spatial separation offered in operations spanning multiple planes (aerial, ground/surface, underwater, etc.). We approach the problem of distributing a search space among heterogeneous vehicles over multiple planes from a distributed computing perspective. This yields a decomposition framework...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.