Robust object tracking using enhanced random ferns

• Published in: The Visual computer Vol. 30; no. 4; pp. 351 - 358
• Main Authors: Quan, Wei, Chen, Jim X., Yu, Nanyang
• Format: Journal Article
• Language: English
• Published: Berlin/Heidelberg Springer Berlin Heidelberg 01-04-2014; Springer Nature B.V
• Subjects: Artificial Intelligence; Clustering; Computer Graphics; Computer Science; Data points; Ferns; Image Processing and Computer Vision; Kernel functions; Original Article; Probability; Random variables; Robustness; Sensors; Sequences; Tracking; Hidden classes; Enhanced random ferns; Object tracking; On-line clustering
• ISSN: 0178-2789; 1432-2315
• DOI: 10.1007/s00371-013-0860-y

This paper presents a method to address the problem of long-term robust object tracking in unconstrained environments. An enhanced random fern is proposed and integrated into our tracking framework as the object detector, whose main idea is to exploit the potential distribution properties of feature vectors which are here called
hidden classes
by on-line clustering of feature space for each leaf-node of ferns. The kernel density estimation technique is then used to evaluate unlabeled samples based on the hidden classes which are set as the data points of the kernel function. Experimental results on challenging real-world video sequences demonstrate the effectiveness and robustness of our approach. Comparisons with several state-of-the-art approaches are provided.