Efficient feature extraction and likelihood fusion for vehicle tracking in low frame rate airborne video

Palaniappan, Kannappan; Bunyak, Filiz; Kumar, Praveen; Ersoy, Ilker; Jaeger, Stefan; Ganguli, Koyeli; Haridas, Anoop; Fraser, Joshua; Rao, Raghuveer M.; Seetharaman, Guna

doi:10.1109/icif.2010.5711891

Cited by 98 publications

(46 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Similarity evaluation of the KDE colour model and the NCC template matching acts as global localizer to bound possible drift of the tracker and the optical flow tracker has a role of adopting frame to frame variation. [52,54,55] is an appearance based single object tracker that uses a set of image based features and correlation maps including histograms of gradient magnitude, gradient orientation, neighbourhood intensity, and shape based on the eigenvalues of the Hessian matrix. LOFT performs feature fusion by comparing a target appearance model within a search region using Bayesian maps which estimate the likelihood of each pixel within the search window belonging to part of the target [54].…”

Section: A36 Dtrackermentioning

confidence: 99%

The Visual Object Tracking VOT2016 Challenge Results

Kristan

Leonardis

Matas

et al. 2016

Lecture Notes in Computer Science

511

678

View full text Add to dashboard Cite

Section: A36 Dtrackermentioning

confidence: 99%

The Visual Object Tracking VOT2016 Challenge Results

Kristan

Leonardis

Matas

et al. 2016

Lecture Notes in Computer Science

511

678

View full text Add to dashboard Cite

“…For example, using imagery regions, edges, and texture support both target and background analysis. Typically, the feature information is used as likelihood values [25] (shown in Figure 2) or features can be grouped together for target recognition to enhance tracking. Table 1 contains a sampling of data sets that facilitate the developments of elements of dismount tracking .These data sets offer ground-based and overhead views for dismount detection analysis.…”

Section: Feature Tracking and Identification (Targets)mentioning

confidence: 99%

Dismount tracking and identification from electro-optical imagery

Blasch

Ling

et al. 2012

Evolutionary and Bio-Inspired Computation: Theory and Applications VI

View full text Add to dashboard Cite

With the advent of new technology in wide-area motion imagery (WAMI) and full-motion video (FMV), there is a capability to exploit the imagery in conjunction with other information sources for improving confidence in detection, tracking, and identification (DTI) of dismounts. Image exploitation, along with other radar and intelligence information can aid decision support and situation awareness. Many advantages and limitations exist in dismount tracking analysis using WAMI/FMV; however, through layered management of sensing resources, there are future capabilities to explore that would increase dismount DTI accuracy, confidence, and timeliness. A layered sensing approach enables commandlevel strategic, operational, and tactical analysis of dismounts to combine multiple sensors and databases, to validate DTI information, as well as to enhance reporting results. In this paper, we discuss WAMI/FMV, compile a list of issues and challenges of exploiting the data for WAMI, and provide examples from recently reported results. Our aim is to provide a discussion to ensure that nominated combatants are detected, the sensed information is validated across multiple perspectives, the reported confidence values achieve positive combatant versus non-combatant detection, and the related situational awareness attributes including behavior analysis, spatial-temporal relations, and cueing are provided in a timely and reliable manner to stakeholders.

show abstract

“…Histogram of oriented gradients are feature descriptors that have been successfully used in many recent object detection and people detection applications [5,21]. HOG uses the histogram of gradient orientations weighted by corresponding gradient magnitudes over a patch or small region of an image.…”

Section: Evmentioning

confidence: 99%

“…We follow a bag-of-features approach and compute a highdimensional set of features for each channel [21]. This includes the following features:…”

Section: Multichannel Feature Estimationmentioning

confidence: 99%

Classification of cell cycle phases in 3D confocal microscopy using PCNA and chromocenter features

Jaeger

Palaniappan

Casas-Delucchi

et al. 2010

Proceedings of the Seventh Indian Conference on Computer Vision, Graphics and Image Processing

View full text Add to dashboard Cite

Cell cycle progression studies using subcellular markers offer important insight into cellular mechanisms of disease and therapeutic drug development. Due to the large volumes of microscopy data involved in such studies, a manual approach to extracting quantitative information is not only prohibitive but error prone. We present an automatic cell cycle phase identification algorithm applied to 3D spinning disk confocal microscopy imagery of mouse embryonic fibroblast cells. In our training dataset, each 3D image stack depicts a single cell in a manually identified cell phase, and is recorded via two channels showing the fluorescently marked protein PCNA and the chromocenters, respectively. We use a 3D k-means approach to segment each volume and extract a set of shape and curvature features to characterize the subcellular foci patterns associated with cell cycle phases for each channel. Radial features are used to describe the spatial distribution of PCNA over the course of the cell cycle. A support vector machine (SVM) classifier using 234 features was trained and achieved a recognition rate of 83% for the chromocenter and 86% for the PCNA channels separately on the testing data. A combined SVM classifier using both channels and 468 features further improved the accuracy to nearly 92% for five phases (G1, SE, SM, SL, G2) and shows promising scalability.

show abstract

Efficient feature extraction and likelihood fusion for vehicle tracking in low frame rate airborne video

Cited by 98 publications

References 19 publications

The Visual Object Tracking VOT2016 Challenge Results

The Visual Object Tracking VOT2016 Challenge Results

Dismount tracking and identification from electro-optical imagery

Classification of cell cycle phases in 3D confocal microscopy using PCNA and chromocenter features

Contact Info

Product

Resources

About