Skip to Main Content
 

Global Search Box

 
 
 

ETD Abstract Container

Abstract Header

Directional Ringlet Intensity Feature Transform for Tracking in Enhanced Wide Area Motion Imagery

Krieger, Evan
http://rave.ohiolink.edu/etdc/view?acc_num=dayton1447950509

Abstract Details

2015, Master of Science (M.S.), University of Dayton, Electrical Engineering.
Object tracking in the wide area motion imagery (WAMI) data may be subjected to many challenges including object occlusion, rotation, scaling, illumination changes, and background variations. In addition, the target objects for tracking in WAMI data are typically low resolution and captured in complex lighting conditions. A novel feature extraction method along with a preprocessing stage is proposed in this thesis research to improve the accuracy of object tracking in these challenging environments. The local preprocessing algorithm performs illumination and spatial enhancement. The illumination enhancement algorithm utilizes a self-tunable transformation function (STTF), which is a nonlinear inverse sine transform, along with an improved color restoration and a halo reduction technique. The spatial enhancement algorithm is a single image super resolution technique that uses Fourier phase features and an adaptive kernel regression technique on the intensity channel. An intelligent methodology for integrating the intensity and spatial enhancement algorithms is developed to improve the tracking performance in the WAMI data. A robust feature-based tracking solution based on the Gaussian ringlet intensity distribution (GRID) feature extraction method is proposed in this thesis. GRID uses Gaussian ring histograms to create features that are robust to object rotation, illumination, and partial object occlusion. However, certain conditions, such as background variations and object structural information distortions, continue to cause feature mismatching. Hence, a new ringlet masking strategy that utilizes the rotational invariance of the Gaussian ringlet and directional edge information of the Kirsch kernel is proposed as the feature descriptor. The new Directional Ringlet Intensity Feature Transform (DRIFT) descriptor weighs the intensity and edge information of the reference object with the ringlet features to achieve robustness to object distortions and background variations. When utilized with a tracking technique with occlusion handling, the DRIFT feature will allow for more accurate tracking of the target object in complex lighting and background conditions. The performance of the proposed feature extraction technique is evaluated on a variety of WAMI object sequences from the Columbus Large Image Format (CLIF) dataset to determine their impact on the tracking process. The results from these evaluations show that the proposed DRIFT algorithm improves the accuracy of tracking on WAMI data and surpasses the performance of other state-of-the-art tracking methods. Future works in this direction include creating a method to handle scale change and automatic selection of super resolution factors based on the target object properties.
Vijayan Asari (Committee Chair)
Eric Balster (Committee Member)
Russell Hardie (Committee Member)
69 p.
Electrical Engineering
object tracking; Kirsch mask; Gaussian ringlet; image enhancement; super-resolution; feature extraction

Recommended Citations

Citations

  • Krieger, E. (2015). Directional Ringlet Intensity Feature Transform for Tracking in Enhanced Wide Area Motion Imagery [Master's thesis, University of Dayton]. OhioLINK Electronic Theses and Dissertations Center. http://rave.ohiolink.edu/etdc/view?acc_num=dayton1447950509

    APA Style (7th edition)

  • Krieger, Evan. Directional Ringlet Intensity Feature Transform for Tracking in Enhanced Wide Area Motion Imagery. 2015. University of Dayton, Master's thesis. OhioLINK Electronic Theses and Dissertations Center, http://rave.ohiolink.edu/etdc/view?acc_num=dayton1447950509.

    MLA Style (8th edition)

  • Krieger, Evan. "Directional Ringlet Intensity Feature Transform for Tracking in Enhanced Wide Area Motion Imagery." Master's thesis, University of Dayton, 2015. http://rave.ohiolink.edu/etdc/view?acc_num=dayton1447950509

    Chicago Manual of Style (17th edition)

dayton1447950509
834
© 2015, all rights reserved.
This open access ETD is published by University of Dayton and OhioLINK.