Open Access Open Access  Restricted Access Subscription Access

UAV Target Tracking Based on Improved TLD Algorithm

Zhongjian Li, Yuting Yi

Abstract


When tracking UAV targets in complex environments, it requires to realize online tracking. At the same time, the target may be obscured and lost in some frames. In order to overcome these problems, the TLD(Tracking Learning and Detecting) algorithm containing tracking module, learning module and detecting module is improved. In the framework of improved algorithm, detection module based on the method of building targets neighborhood constructs the scan windows. Also a location prediction module based on Kalman filter is introduced. The experimental results show that the improved TLD algorithm can be applied to the case of target obscured with high recognition rate and low error detection rate. At the same time, it has good real-time performance and can satisfy the demands of general online tracking system.

Full Text:

PDF

References


Fukanaga K, Hostetler L D. The estimation of the gradient of a density function with application in pattern recognition [J]. IEEE Trans. Information Theory, 1975, 21(1):32-40.

Yizong Cheng. Mean shift, mode seeking, and clustering [J]. IEEE Trans. Pattern Analysis and Machine Intelligence,1995,17(8):790-799.

Bradski G R. Real time face and object tracking as a component of a perceptual user interface [C]. Proc. IEEE Workshop on Applications of Computer Vision,1998:214-219.

Comaniciu D, Ramesh V, Meer P. Real-time tracking of non-grid objects using meanshift [C]. Proc. IEEE Conference on Computer Vision and Pattern Recognition, 2000:142-149.

Comaniciu D, Ramesh V, Meer P. Kernel-based object tracking [J]. IEEE Trans. Pattern Analysis and Machine Intelligence, 2003, 25(5):564-577.

Lucas B,Kanade T. An Iterative Image Registration Technique with an Application to Stereo Vision[C]//Proc. Internat. Joint Conf. on Artificial intelligence,1981,2:674-679.

Black M J, Yacoob Y. Recognizing facial expressions in image sequences using local parameterized models of image motion [J]. International Journal of Computer Vision (s1573-1405), 1997, 25(1): 23-48.

Matthews Iain, Ishikawa T, Baker S. The Template Update Problem [J]. IEEE Trans. Pattern Anal. Machine Intell (S0162-8828), 2004, 26(6): 810-815.

David Schreiber. Robust template tracking with drift correction [J]. Pattern Recognition Letters (S0167-8655), 2007, 28(12): 1483-1491.

Wang Kun-peng, YANG Gui. Robust Tracking Method with Drift Correction [C]//IEEE International Conference on Image Analysis and Signal Processing, Zhejiang, China, April 9-11, 2010: 403-406.

Kalal Z, Matas J, Mikolajczyk K. Online learning of robust object

detectors during unstable tracking[C//12th IEEE International Conference on Computer Vision Workshops(ICCV Workshops),2009:1417-1424.

Kalal Z, Mikolajczyk K, Matas J. Face-TLD: Tracking-Learning-Detection applied to face[C]//17th IEEE International Conference on Image Processing(ICIP),2010:3789-3792.

Kalman R E. A new approach to linear filtering and prediction problem[J]. Transactions of the ASME-Journal of Basic Engineering, 1960, 82 (Series D):35-45.




DOI: http://dx.doi.org/10.21535%2FProICIUS.2015.v11.677

Refbacks

  • There are currently no refbacks.