Object Tracking Using High Resolution Satellite Imagery

Meng, Lingfei; Kerekes, John P.

doi:10.1109/jstars.2011.2179639

Cited by 61 publications

(43 citation statements)

References 16 publications

(5 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Finally, Cohen's κ, overall accuracy, F1-score [52], False alarm rate (False changes detected/total "unchanged") and Missed alarm rate (Missed changes/total "changed") are assessed using the best parameters (σ,λ,γ * ,k * ). Ten independent training and validation sets are used to validate the approach on the test set composed of the remaining samples in the image.…”

Section: A Experimental Setupmentioning

confidence: 99%

Semi-Supervised Novelty Detection Using SVM Entire Solution Path

Morsier

Tuia

Borgeaud

et al. 2013

IEEE Trans. Geosci. Remote Sensing

View full text Add to dashboard Cite

Abstract-Very often, the only reliable information available to perform change detection is the description of some unchanged regions. Since sometimes these regions do not contain all the relevant information to identify their counterpart (the changes), we consider the use of unlabeled data to perform Semi-Supervised Novelty detection (SSND). SSND can be seen as an unbalanced classification problem solved using the Cost-Sensitive Support Vector Machine (CS-SVM), but this requires a heavy parameter search. We propose here to use entire solution path algorithms for the CS-SVM in order to facilitate and accelerate the parameter selection for SSND. Two algorithms are considered and evaluated. The first one is an extension of the CS-SVM algorithm that returns the entire solution path in a single optimization. This way, the optimization of a separate model for each hyperparameter set is avoided. The second forces the solution to be coherent through the solution path, thus producing classification boundaries that are nested (included in each other). We also present a low density criterion for selecting the optimal classification boundaries, thus avoiding the recourse to cross-validation that usually requires information about the "change" class. Experiments are performed on two multitemporal change detection datasets (flood and fire detection). Both algorithms tracing the solution path provide similar performances than the standard CS-SVM while being significantly faster. The low density criterion proposed achieves results that are close to the ones obtained by cross-validation, but without using information about the changes.

show abstract

Section: A Experimental Setupmentioning

confidence: 99%

Semi-Supervised Novelty Detection Using SVM Entire Solution Path

Morsier

Tuia

Borgeaud

et al. 2013

IEEE Trans. Geosci. Remote Sensing

View full text Add to dashboard Cite

show abstract

“…Histogram intersection has been introduced in computer vision by [14], and histogram intersection distance used as a distance measure to compare histograms [15][16][17]. For two normalized histograms p and q , the histogram intersection between them is defined to be:…”

Section: B Histogram Intersectionmentioning

confidence: 99%

An improved similarity measure in particle filters for robust object tracking

Wang

Chen

Shi

et al. 2013

2013 6th International Congress on Image and Signal Processing (CISP)

View full text Add to dashboard Cite

Infrared object tracking plays a key role in many research fields, and there is a series of work on applying particle filter to this tracking problem. Most of the PF-based tracking algorithms utilize the Bhattacharyya coefficient as a similarity measure, however, its performance in infrared object tracking is limited due to insufficient discriminative power. In this paper, we present a combined similarity measure under the particle filter framework, which integrates the advantages of the Bhattacharyya coefficient, histogram intersection, and structural similarity. The experimental results are gained by using different infrared image sequences, which show that the proposed measure gives superior discriminative power and achieves more robust and stable tracking performance than the traditional approach.

show abstract

“…The techniques for vehicle detection are based on classification [2] , principal components analysis (PCA), Bayesian background transformation [3] , gradient threshold [4] , and top-hat transformation. Furthermore, the displacement of a moving vehicle can be determined by various change detection methods, including image differencing [5] , background modelling [6] , PCA [7] , spectral and spatial (SNS) analysis [8] , and ERGAS-SNS analysis [9] . The detection and speed determination of moving vehicles using very-high-resolution (VHR) images is meaningful for activities such as traffic monitoring, estimation of traffic volume, or urban traffic modelling and planning [10] .…”

Section: Introductionmentioning

confidence: 99%