scholarly journals Partial Block Scheme and Adaptive Update Model for Kernelized Correlation Filters-Based Object Tracking

2018 ◽  
Vol 8 (8) ◽  
pp. 1349 ◽  
Author(s):  
Soowoong Jeong ◽  
Joonki Paik
Keyword(s):  
Object Tracking ◽  
Real Time ◽  
Adaptive Learning ◽  
Weighting Function ◽  
Computational Cost ◽  
Visual Object ◽  
Partial Occlusion ◽  
Block Scheme ◽  
Real Time Tracking ◽  
Scale Variation

In visual object tracking, the dynamic environment is a challenging issue. Partial occlusion and scale variation are typical challenging problems. We present a correlation-based object tracking based on the discriminative model. To attenuate the influence by partial occlusion, partial sub-blocks are constructed from the original block, and each of them operates independently. The scale space is employed to deal with scale variation using a feature pyramid. We also present an adaptive update model with a weighting function to calculate the frame-adaptive learning rate. Theoretical analysis and experimental results demonstrate that the proposed method can robustly track drastic deformed objects. The sparse update reduces the computational cost for real-time tracking. Although the partial block scheme generation increases the computational cost, we present a novel sparse update approach to reduce the computational cost drastically for real-time tracking. The experiments were performed on a variety of sequences, and the proposed method exhibited better performance compared with the state-of-the-art trackers.

Robust real-time visual object tracking via multi-scale fully convolutional Siamese networks

2018 ◽  
Vol 77 (17) ◽  
pp. 22131-22143 ◽  
Author(s):  
Longchao Yang ◽  
Peilin Jiang ◽  
Fei Wang ◽  
Xuan Wang
Keyword(s):  
Object Tracking ◽  
Real Time ◽  
Visual Object ◽  
Visual Object Tracking ◽  
Multi Scale ◽  
Siamese Networks

Cross-Domain Usage in Real-Time Video-Based Tracking

2017 ◽  
pp. 105-129
Author(s):  
Satbir Singh ◽  
Rajiv Kapoor ◽  
Arun Khosla
Keyword(s):  
Object Tracking ◽  
Real Time ◽  
Future Development ◽  
Complete Information ◽  
Cutting Edge ◽  
Edge Field ◽  
Cross Domain ◽  
Distinct Category ◽  
Real Time Tracking ◽  
The Cross

This chapter emphasizes on the approach to include information from different type of sensors into the visible domain real time tracking. Since any individual sensor is not able to retrieve the complete information, so it is better to use information from distinct category of sensors. The chapter firstly enlightens the significance of introducing the cross-domain treatment into video based tracking. Following this, some previous work in the literature related to this idea is briefed. The chapter introduces the categorization of the cross-domain activity usage for real time object tracking and then each category is separately discussed in detail. The advantages as well as the limitations of each type of supplemented cross domain activity will be discussed. Finally, the recommendation and concluding remarks from the authors in lieu of future development of this cutting-edge field will be presented.

A real-time visual object tracking system based on Kalman filter and MB-LBP feature matching

2014 ◽  
Vol 75 (4) ◽  
pp. 2393-2409 ◽  
Author(s):  
Zebin Cai ◽  
Zhenghui Gu ◽  
Zhu Liang Yu ◽  
Hao Liu ◽  
Ke Zhang
Keyword(s):  
Kalman Filter ◽  
Object Tracking ◽  
Real Time ◽  
Feature Matching ◽  
Tracking System ◽  
Visual Object ◽  
Visual Object Tracking

Adaptive Image Feature Reduction for Object Tracking

2014 ◽  
Vol 989-994 ◽  
pp. 3605-3608
Author(s):  
Cong Lin ◽  
Chi Man Pun
Keyword(s):  
Object Tracking ◽  
Adaptive Learning ◽  
Computational Cost ◽  
Texture Feature ◽  
Feature Reduction ◽  
Image Feature ◽  
Distribution Model ◽  
Appearance Model ◽  
Art Object

A novel adaptive image feature reduction approach for object tracking using vectorized texture feature is proposed in this paper. Our contributions are three-fold: 1) a statistical discriminative appearance model using texture feature was proposed. 2) Majority of dimensions of the features are removed by judging their errors of the chosen distribution model. The remaining dimensions are most discriminative ones for classification task. The dimension reduction has advantages of reducing the computational cost in classification stage. 3) An adaptive learning rate was proposed to handle drifts caused by long term occlusion. Preliminary experimental results are satisfactory and compared to state-of-the-art object tracking methods.

scholarly journals Optimisation of a Siamese Neural Network for Real-Time Energy Efficient Object Tracking

2020 ◽  
Author(s):  
Dominika Przewlocka ◽  
Mateusz Wasala ◽  
Hubert Szolc ◽  
Krzysztof Blachut ◽  
Tomasz Kryjak
Keyword(s):  
Neural Network ◽  
Object Tracking ◽  
Real Time ◽  
Video Stream ◽  
Visual Object ◽  
Vision Systems ◽  
Embedded Vision ◽  
Network Training ◽  
Binary Networks ◽  
Embedded Vision Systems

In this paper the research on optimisation of visual object tracking using a Siamese neural network for embedded vision systems is presented. It was assumed that the solution shall operate in real-time, preferably for a high resolution video stream, with the lowest possible energy consumption. To meet these requirements, techniques such as the reduction of computational precision and pruning were considered. Brevitas, a tool dedicated for optimisation and quantisation of neural networks for FPGA implementation, was used. A number of training scenarios were tested with varying levels of optimisations-from integer uniform quantisation with 16 bits to ternary and binary networks. Next, the influence of these optimisations on the tracking performance was evaluated. It was possible to reduce the size of the convolutional filters up to 10 times in relation to the original network. The obtained results indicate that using quantisation can significantly reduce the memory and computational complexity of the proposed network while still enabling precise tracking, thus allow to use it in embedded vision systems. Moreover , quantisation of weights positively affects the network training by decreasing overfitting.

scholarly journals Patch Based Multiple Instance Learning Algorithm for Object Tracking

2017 ◽  
Vol 2017 ◽  
pp. 1-7 ◽  
Author(s):  
Zhenjie Wang ◽  
Lijia Wang ◽  
Hua Zhang
Keyword(s):  
Object Tracking ◽  
Real Time ◽  
Learning Algorithm ◽  
State Of The Art ◽  
Multiple Instance Learning ◽  
Partial Occlusion ◽  
Learning Rates ◽  
Classification Score ◽  
Object Based ◽  
Illumination Changes

To deal with the problems of illumination changes or pose variations and serious partial occlusion, patch based multiple instance learning (P-MIL) algorithm is proposed. The algorithm divides an object into many blocks. Then, the online MIL algorithm is applied on each block for obtaining strong classifier. The algorithm takes account of both the average classification score and classification scores of all the blocks for detecting the object. In particular, compared with the whole object based MIL algorithm, the P-MIL algorithm detects the object according to the unoccluded patches when partial occlusion occurs. After detecting the object, the learning rates for updating weak classifiers’ parameters are adaptively tuned. The classifier updating strategy avoids overupdating and underupdating the parameters. Finally, the proposed method is compared with other state-of-the-art algorithms on several classical videos. The experiment results illustrate that the proposed method performs well especially in case of illumination changes or pose variations and partial occlusion. Moreover, the algorithm realizes real-time object tracking.

Sign in / Sign up

Export Citation Format

Share Document