scholarly journals Target Tracking Algorithm Using Angular Point Matching Combined with Compressive Tracking

2015 ◽  
Vol 2015 ◽  
pp. 1-10
Author(s):  
Jing Luo ◽  
Tingting Dong ◽  
Chunyuan Zi ◽  
Chunbo Xiu ◽  
Huixin Tian ◽  
...  
Keyword(s):  
Target Position ◽  
Tracking Algorithm ◽  
Angular Point ◽  
Measurement Matrix ◽  
Illumination Change ◽  
Tracking Errors ◽  
Point Matching ◽  
Compressive Tracking ◽  
Pose Variation ◽  
Better Than

To solve the problems of tracking errors such as target missing that emerged in compressive tracking (CT) algorithm due to factors such as pose variation, illumination change, and occlusion, a novel tracking algorithm combined angular point matching with compressive tracking (APMCCT) was proposed. A sparse measurement matrix was adopted to extract the Haar-like features. The offset of the predicted target position was integrated into the angular point matching, and the new target position was calculated. Furthermore, the updating mechanism of the template was optimized. Experiments on different video sequences have shown that the proposed APMCCT performs better than CT algorithm in terms of accuracy and robustness and adaptability to pose variation, illumination change, and occlusion.

A New Method for Feature Point Matching: Inner and Exterior Product

2011 ◽  
Vol 48-49 ◽  
pp. 79-83
Author(s):  
Xu Guang Wang ◽  
Li Jun Lin ◽  
Hai Yan Cheng
Keyword(s):  
Feature Point ◽  
Feature Descriptor ◽  
Feature Points ◽  
Correlation Measure ◽  
Exterior Product ◽  
Illumination Change ◽  
Point Matching ◽  
Feature Point Matching ◽  
Estimate Precision ◽  
Better Than

In this paper, a novel feature descriptor called gradient correlation descriptor (GCD) is proposed. The GCD descriptor uses the gradient correlation measure defined by the inner and exterior product to characterize the gradient distributions in neighborhoods of feature points, and it has the following advantages: Its construction is very simple because of only the inner and exterior product operations are used; Its distinctive performance is better than the region-based SIFT descriptors since the gradient correlation measure can effectively characterize the gradient distributions in neighborhoods of feature points; In the gradient correlation measure the use of gradient mean makes it is not sensitive to the estimate precision of main orientation of feature point, and thus can provide a better stabilization to image rotation; The gradient correlation measure makes it also has very good adaptability to image affine transform, image blur, JPEG compression as well as illumination change.

scholarly journals An Improved Fast Compressive Tracking Algorithm Based on Online Random Forest Classifier

2016 ◽  
Vol 59 ◽  
pp. 01003 ◽  
Author(s):  
Jintao Xiong ◽  
Pan Jiang ◽  
Jianyu Yang ◽  
Zhibin Zhong ◽  
Ran Zou ◽  
...  
Keyword(s):  
Random Forest ◽  
Random Forest Classifier ◽  
Tracking Algorithm ◽  
Compressive Tracking

Tracking algorithm of snowboard target in intelligent system

2020 ◽  
pp. 1-9
Author(s):  
Zhipeng Li ◽  
Xiaolan Li ◽  
Ming Shi ◽  
Wenli Song ◽  
Guowei Zhao ◽  
...  
Keyword(s):  
Target Tracking ◽  
High Speed ◽  
Intelligent System ◽  
Mean Shift ◽  
Target Position ◽  
Tracking Algorithm ◽  
Tracking Accuracy ◽  
Mean Shift Algorithm ◽  
Target Track ◽  
The Mean

Snowboarding is a kind of sport that takes snowboarding as a tool, swivels and glides rapidly on the specified slope line, and completes all kinds of difficult actions in the air. Because the sport is in the state of high-speed movement, it is difficult to direct guidance during the sport, which is not conducive to athletes to find problems and correct them, so it is necessary to track the target track of snowboarding. The target tracking algorithm is the main solution to this task, but there are many problems in the existing target tracking algorithm that have not been solved, especially the target tracking accuracy in complex scenes is insufficient. Therefore, based on the advantages of the mean shift algorithm and Kalman algorithm, this paper proposes a better tracking algorithm for snowboard moving targets. In the method designed in this paper, in order to solve the problem, a multi-algorithm fusion target tracking algorithm is proposed. Firstly, the SIFT feature algorithm is used for rough matching to determine the fuzzy position of the target. Then, the good performance of the mean shift algorithm is used to further match the target position and determine the exact position of the target. Finally, the Kalman filtering algorithm is used to further improve the target tracking algorithm to solve the template trajectory prediction under occlusion and achieve the target trajectory tracking algorithm design of snowboarding.

Tracking 3D seismic horizons with a new hybrid tracking algorithm

2020 ◽  
Vol 8 (4) ◽  
pp. SQ39-SQ45
Author(s):  
Rahul Gogia ◽  
Raman Singh ◽  
Paul de Groot ◽  
Harshit Gupta ◽  
Seshan Srirangarajan ◽  
...  
Keyword(s):  
Tracking Algorithm ◽  
Seismic Events ◽  
3D Seismic ◽  
Data Set ◽  
Standard Practice ◽  
Small Set ◽  
Dense Set ◽  
Better Than ◽  
Inversion Loop

We have developed a new algorithm for tracking 3D seismic horizons. The algorithm combines an inversion-based, seismic-dip flattening technique with conventional, similarity-based autotracking. The inversion part of the algorithm aims to minimize the error between horizon dips and computed seismic dips. After each cycle in the inversion loop, more seeds are added to the horizon by the similarity-based autotracker. In the example data set, the algorithm is first used to quickly track a set of framework horizons, each guided by a small set of user-picked seed positions. Next, the intervals bounded by the framework horizons are infilled to generate a dense set of horizons, also known as HorizonCube. This is done under the supervision of a human interpreter in a similar manner. The results show that the algorithm behaves better than unconstrained flattening techniques in intervals with trackable events. Inversion-based algorithms generate continuous horizons with no holes to be filled posttracking with a gridding algorithm and no loop skips (jumping to the wrong event) that need to be edited as is standard practice with autotrackers. Because editing is a time-consuming process, creating horizons with inversion-based algorithms tends to be faster than conventional autotracking. Horizons created with the adopted algorithm follow seismic events more closely than horizons generated with the inversion-only algorithm, and the fault crossings are sharper.

A Tracking Window Adaptive Compressive Tracking Algorithm

2019 ◽  
Vol 33 (14) ◽  
pp. 1959045 ◽  
Author(s):  
Wenhao Wang ◽  
Mingxin Jiang ◽  
Xiaobing Chen ◽  
Li Hua ◽  
Shangbing Gao
Keyword(s):  
Texture Features ◽  
Candidate Region ◽  
Tracking Algorithm ◽  
Experimental Results ◽  
Scale Invariant ◽  
Compressive Tracking ◽  
Multi Scale ◽  
Feature Normalization ◽  
Object Region ◽  
Candidate Regions

In the original compression tracking algorithm, the size of the tracking box is fixed. There should be better tracking results for scale-invariant objects, but worse tracking results for scale-variant objects. To overcome this defect, a scale-adaptive compressive tracking (CT) algorithm is proposed. First of all, the imbalance of the gray and texture features in the original CT algorithm is balanced by the multi-feature method, which makes the algorithm more robust. Then, searching different candidate regions by using the method of multi-scale search along with feature normalization makes the features extracted from different scales comparable. Finally, the candidate region with the maximum discriminate degree is selected as the object region. Thus, the tracking-box size is adaptive. The experimental results show that when the object scale changes, the improving CT algorithm has higher accuracy and robustness than the original CT algorithm.

Style Analysis and Its Application of Domestic Mutual Funds

2011 ◽  
Vol 19 (1) ◽  
pp. 91-120
Author(s):  
Bong Chan Kho ◽  
Uk Chang ◽  
Youngsoo Choi
Keyword(s):  
Fund Performance ◽  
Style Analysis ◽  
Tracking Errors ◽  
Short Sale ◽  
Index Model ◽  
Market Index ◽  
Out Of Sample ◽  
Style Indices ◽  
Domestic Stock ◽  
Better Than

We illustrate empirically the use of return-based style analysis for domestic stock funds. We search the optimal style model according to the tracking errors, investigate the consistency of the fund style for the optimally selected model, and finally investigate the relationship between fund styles and their fund performance. We use weekly fund return data of domestic stock funds from January 2, 2002 to June 30, 2008, and do style analyses based on the various style indices. The major findings are as follows. Firstly, we find that the style index models with constraint which in practice restricts short sale are better than those with no such constraint. Secondly, we find that the style index model which divides stock market with four categorized indices based on the dimension of size and book-to market and includes the bond market index is the most useful if they are evaluated based on the out-of-sample tracking errors. While adding the Fama-French 3 factors to the selected model does not improve the explanation power, adding the industry sector indexes improves the explanation power. Thirdly, we investigate the consistency of the fund style models and find that the better performing funds are more volatile in the change of the fund style. Fourthly, we find that, contrary to the expectation that the growth-oriented funds perform better than the value-oriented one, the fund performance and style are observed to be mixed. This finding shows that the fund styles are frequently changed according to their performances and market conditions.

scholarly journals Object Tracking Algorithm Based on Dual Color Feature Fusion with Dimension Reduction

Sensors ◽  
2018 ◽  
Vol 19 (1) ◽  
pp. 73 ◽  
Author(s):  
Shuo Hu ◽  
Yanan Ge ◽  
Jianglong Han ◽  
Xuguang Zhang
Keyword(s):  
Dimension Reduction ◽  
Object Tracking ◽  
Feature Fusion ◽  
Target Position ◽  
Input Image ◽  
Tracking Algorithm ◽  
Tracking Accuracy ◽  
Color Feature ◽  
Color Distribution ◽  
Dual Color

Aiming at the problem of poor robustness and the low effectiveness of target tracking in complex scenes by using single color features, an object-tracking algorithm based on dual color feature fusion via dimension reduction is proposed, according to the Correlation Filter (CF)-based tracking framework. First, Color Name (CN) feature and Color Histogram (CH) feature extraction are respectively performed on the input image, and then the template and the candidate region are correlated by the CF-based methods, and the CH response and CN response of the target region are obtained, respectively. A self-adaptive feature fusion strategy is proposed to linearly fuse the CH response and the CN response to obtain a dual color feature response with global color distribution information and main color information. Finally, the position of the target is estimated, based on the fused response map, with the maximum of the fused response map corresponding to the estimated target position. The proposed method is based on fusion in the framework of the Staple algorithm, and dimension reduction by Principal Component Analysis (PCA) on the scale; the complexity of the algorithm is reduced, and the tracking performance is further improved. Experimental results on quantitative and qualitative evaluations on challenging benchmark sequences show that the proposed algorithm has better tracking accuracy and robustness than other state-of-the-art tracking algorithms in complex scenarios.

Sign in / Sign up

Export Citation Format

Share Document