Multi-experts Joint Decision with Adaptive Model Updater for Robust Visual Tracking

Over these years, correlation filters based trackers have shown edges both in accuracy and speed. However, variations of target appearance caused by heavy occlusion, rotation, background clutters and target deformations are the major challenges for tracking. To solve these problems, many works put on exploiting the power of target representation, such as high-level convolutional features. Nonetheless, these methods make a great compromise between the speed and performance. At the same time, there are few researches on improving the performance of model updater and the ensemble methods. In this paper, a multi-experts joint decision strategy base on kernelized correlation filters is proposed to obtain robust and accurate visual tracking, two trackers with handcrafted features and deep convolutional neural network features are integrated in this framework. We also investigate the mechanism of tracking failure caused by occlusion and background clutters, and propose a novel criterion to evaluate the reliability of samples. Our work includes extending the kernelized correlation filter-based tracker with the capability of handling scale changes as well. The proposed tracker is extensively evaluated on the OTB-2013, OTB-2015 and VOT2015 benchmark datasets. Compared with the state-of-the-art trackers, the distinguished experimental results demonstrate the effectiveness of the proposed framework.

METHODS OF IMAGE RECOGNITION IN A VIDEO STREAM

The article examines the problem of automatic object recognition using a video stream as a digital image. Algorithms for recognizing and tracking objects in the video stream are considered, methods used in video processing are analyzed, and the use of machine learning tools in working with video is described.The main approaches to solving the problem of recognizing moving objects in a video stream are investigated: the detection-based approach and the tracking-based approach. Arguments are made in favor of the tracking-based approach, and, in addition, modern methods of tracking objects in the video stream are considered. In particular, the algorhythms: Online Boosting Tracker - one of the first object tracking algorithms with high tracking accuracy, MIL Tracker (Multiple Instance Learning Tracker), which is a development of the idea of learning with a teacher and the Online Boosting algorithm and the KCF Tracker algorithm (Kernelized Correlation Filters Tracker) - a method that uses the mathematical properties of overlapping areas of positive examples.As a result, the advantages and disadvantages of the considered methods and algorithms for recognizing and tracking objects for various applications are highlighted.

A Novel Scale Insensitive KCF Tracker Based on HOG and Color Features

Kernelized Correlation Filters (KCF) for visual tracking have received much attention due to their fast speed and outstanding performances in real scenarios. However, the KCF sometimes still fails to track the targets with different scales, and it may drift because the target response is fixed and the original histogram of orientation gradient (HOG) features cannot represent the targets well. In this paper, we propose a novel fast tracker, which is based on KCF and insensitive to scale changes by learning two independent correlation filters (CFs) where one filter is designed for position estimation and the other is for scale estimation. In addition, it can adaptively change the target response and multiple features are integrated to improve the performance for our tracker. Finally, we employ an adaptive high confidence filters updating scheme to avoid errors. Evaluated on the popular OTB50 and OTB100 datasets, our proposed trackers show superior performances in terms of efficiency and accuracy compared to the existing methods.