کد مقاله کد نشریه سال انتشار مقاله انگلیسی نسخه تمام متن
407861 678236 2014 17 صفحه PDF دانلود رایگان
عنوان انگلیسی مقاله ISI
Online MIL tracking with instance-level semi-supervised learning
موضوعات مرتبط
مهندسی و علوم پایه مهندسی کامپیوتر هوش مصنوعی
پیش نمایش صفحه اول مقاله
Online MIL tracking with instance-level semi-supervised learning
چکیده انگلیسی


• We propose an online MIL algorithm with instance-level semi-supervised learning.
• We solve the unselective treatment of instances in positive bags during updating.
• The algorithm introduces the object prior knowledge in instance modeling.
• The unlabeled instances in positive bags are predicted by semi-supervised learning.
• Experiments demonstrate the superior tracking performance of our algorithm.

In this paper we propose an online multiple instance boosting algorithm with instance-level semi-supervised learning, termed SemiMILBoost, to achieve robust object tracking. Our work revisits the multiple instance learning (MIL) formulation to alleviate the drifting problem in tracking, which addresses two key issues in the existing MIL based tracking-by-detection methods, i.e., the unselective treatment of instances in the positive bag during weak classifier updating and the lack of object prior knowledge in instance modeling. We tackle both issues in a principled way by using a robust SemiMILBoost algorithm, which treats instances in the positive bag as unlabeled while the ones in the negative bag as negative. To improve the discriminability of weak classifiers online, we iteratively update them with the pseudo-labels and importance of all instances in the positive bag, which are predicted by employing the instance-level semi-supervised learning technique with object prior knowledge during boosting. Experimental results demonstrate that our proposed algorithm outperforms the state-of-the-art tracking methods on several challenging video sequences.

ناشر
Database: Elsevier - ScienceDirect (ساینس دایرکت)
Journal: Neurocomputing - Volume 139, 2 September 2014, Pages 272–288
نویسندگان
, , , , ,