Object tracking under nonuniform illumination with adaptive correlation filtering

2013 ◽  
Author(s):  
Kenia Picos ◽  
Víctor H. Díaz-Ramírez ◽  
Vitaly Kober
Keyword(s):  
Object Tracking ◽  
Nonuniform Illumination ◽  
Correlation Filtering

Visual object tracking with discriminative correlation filtering and hybrid color feature

2019 ◽  
Vol 78 (24) ◽  
pp. 34725-34744 ◽  
Author(s):  
Yang Huang ◽  
Zhiqiang Zhao ◽  
Bin Wu ◽  
Zhuolin Mei ◽  
Zongmin Cui ◽  
...  
Keyword(s):  
Object Tracking ◽  
Visual Object ◽  
Visual Object Tracking ◽  
Color Feature ◽  
Correlation Filtering

scholarly journals Long-term real time object tracking based on multi-scale local correlation filtering and global re-detection

Computing ◽  
2020 ◽  
Vol 102 (6) ◽  
pp. 1487-1501 ◽  
Author(s):  
Qi Zhao ◽  
Boxue Zhang ◽  
Wenquan Feng ◽  
Zhiying Du ◽  
Hong Zhang ◽  
...  
Keyword(s):  
Object Tracking ◽  
Real Time ◽  
Local Correlation ◽  
Multi Scale ◽  
Correlation Filtering

scholarly journals Deep Directional Network for Object Tracking

Algorithms ◽  
2018 ◽  
Vol 11 (11) ◽  
pp. 178 ◽  
Author(s):  
Zhaohua Hu ◽  
Xiaoyi Shi
Keyword(s):  
Neural Network ◽  
Object Tracking ◽  
Visual Object ◽  
Negative Sample ◽  
Directional Information ◽  
Sample Classification ◽  
Tracking Time ◽  
The One ◽  
Correlation Filtering ◽  
Scale Variation

Existing object trackers are mostly based on correlation filtering and neural network frameworks. Correlation filtering is fast but has poor accuracy. Although a neural network can achieve high precision, a large amount of computation increases the tracking time. To address this problem, we utilize a convolutional neural network (CNN) to learn object direction. We propose a target direction classification network based on CNNs that has a directional shortcut to the tracking target, unlike the particle filter that randomly finds the target. Our network uses an end-to-end approach to determine scale variation that has good robustness to scale variation sequences. In the pretraining stage, the Visual Object Tracking Challenges (VOT) dataset is used to train the network for learning positive and negative sample classification and direction classification. In the online tracking stage, the sliding window operation is performed by using the obtained directional information to determine the exact position of the object. The network only calculates a single sample, which guarantees a low computational burden. The positive and negative sample redetection strategies can successfully ensure that the samples are not lost. The one-pass evaluation (OPE) evaluation results of the object tracking benchmark (OTB) demonstrate that the algorithm is very robust and is also faster than several deep trackers.

Real-time object tracking with correlation filtering and state prediction

2013 ◽  
Author(s):  
Viridiana Contreras ◽  
Victor H. Díaz-Ramírez ◽  
Vitaly Kober ◽  
Juan J. Tapia-Armenta
Keyword(s):  
Object Tracking ◽  
Real Time ◽  
State Prediction ◽  
Correlation Filtering

Multiple-Object Tracking

2011 ◽  
Vol 58 (3) ◽  
pp. 196-200 ◽  
Author(s):  
K. Botterill ◽  
R. Allen ◽  
P. McGeorge
Keyword(s):  
Object Tracking ◽  
Cognitive Processes ◽  
Spatial Location ◽  
Multiple Object Tracking ◽  
Tracking Performance ◽  
Multiple Object

The Multiple-Object Tracking paradigm has most commonly been utilized to investigate how subsets of targets can be tracked from among a set of identical objects. Recently, this research has been extended to examine the function of featural information when tracking is of objects that can be individuated. We report on a study whose findings suggest that, while participants can only hold featural information for roughly two targets this task does not affect tracking performance detrimentally and points to a discontinuity between the cognitive processes that subserve spatial location and featural information.

Predictable paths increase the use of motion in object tracking

2010 ◽  
Author(s):  
Adriane E. Seiffert ◽  
Rebecca St. Clair
Keyword(s):  
Object Tracking
Sign in / Sign up

Export Citation Format

Share Document