A new tracking approach for visible and infrared sequences based on tracking-before-fusion

Xiao, Gang; Xiao, Yun; Wu, Jianmin

doi:10.1007/s40435-014-0115-4

Cited by 16 publications

(4 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Results obtained from our algorithm were compared with five different states of the art trackers viz. ordinary visible colour particle filter (VPF) [18], individual visible template matching (VTM), Track before fusion in Thermal and Visible (TBF) [19] , Adaptive Data Fusion of Thermal and Visible (ADF) [16], and Adaptive Data fusion via color and gradient (ACGF) [17]. All the computations were performed with MATLAB on the I3 processor system.…”

Section: Resultsmentioning

confidence: 99%

Object Tracking with a Novel Visual-Thermal Sensor Fusion Method in Template Matching

Singh¹,

Khosla²,

Kapoor³

2019

IJIGSP

View full text Add to dashboard Cite

Recently there has been an increase in the use of thermal-visible conjunction technique in the field of surveillance applications due to complementary advantages of both. An amalgamation of these for tracking requires a reasonable scientific procedure that can efficiently make decisions with sound accuracy and excellent precision. The proposed research presents a unique idea for obtaining a robust track estimate with the thermo-visual fusion in the context of fundamental template matching. This method firstly introduces a haphazard transporting control mechanism for individual modality tracking that avoids unexpected estimates. Then it brings together an efficient computation procedure for providing the weighted output using minimal information from the individual trackers. Experiments performed on publically available datasets mark the usefulness of the proposed idea in the context of accuracy, precision and process time in comparison with the state of art methods.

show abstract

Section: Resultsmentioning

confidence: 99%

Object Tracking with a Novel Visual-Thermal Sensor Fusion Method in Template Matching

Singh¹,

Khosla²,

Kapoor³

2019

IJIGSP

View full text Add to dashboard Cite

show abstract

“…The particle filter method was first introduced into the field of target tracking in 1998 [15], which combined the statistical factor sampling algorithm for static non-Gaussian problems and the stochastic model of target motion. In addition, the traditional prefusion tracking strategy still has the situation of mutual influence between multiple sensors, so an improved particle filter algorithm appeared [16], which used a color histogram with spatial information to represent the target model and give the color feature weight of each particle. At the same time, it improved the rules of fusing the tracking results of visible light and infrared sequences.…”

Section: Early Classical Methodsmentioning

confidence: 99%

Visible and infrared images fusion target tracking based on deep learning, progress, and prospects

Fang¹,

Li²,

Liu³

2022

5th International Conference on Computer Information Science and Application Technology (CISAT 2022)

View full text Add to dashboard Cite

“…Note that the modality weights were not applied in template features which were computed based on the first frame. Therefore, multiplication operation is not needed in equation (5). The fused search feature was computed as…”

Section: ) Feature Fusionmentioning

confidence: 99%

“…Before deep learning and correlation filters, researchers performed fusion tracking with traditional techniques [3], [5], such as mean-shift and Camshift algorithms. These methods were not able to obtain good tracking performance when challenging factors present.…”

Section: Introductionmentioning

confidence: 99%

SiamFT: An RGB-Infrared Fusion Tracking Method via Fully Convolutional Siamese Networks

Zhang

Peng

et al. 2019

IEEE Access

Self Cite

View full text Add to dashboard Cite

Object tracking based on visible images may fail when the visible images are unreliable, for example when the illumination condition is poor. Infrared images reveal thermal radiation of objects and are insensitive to these factors. Due to the complementary features of visible and infrared images, RGB-infrared fusion tracking has attracted widespread attention recently. In this paper, an RGB-infrared fusion tracking method based on the fully convolutional Siamese Networks, termed as SiamFT, is proposed. Visible and infrared images are firstly processed by two Siamese Networks, namely visible network and infrared network, respectively. Then, convolutional features of visible and infrared template images extracted from two Siamese Networks are concatenated to form fused template image. Convolutional features of visible and infrared search image are fused through the proposed feature fusion network adaptively. In particular, a modality weight computation method based on the response value of Siamese network is proposed to predict the reliability of different images. Cross-relation is then applied to the fused template feature and the fused search feature to produce the final response map, based on which the tracking results can be obtained. Extensive experiments indicate that the proposed SiamFT shows better performance than thestate-of-art fusion tracking algorithms at real-time speed. INDEX TERMS Deep learning, fusion tracking, object tracking, Siamese network.

show abstract

A new tracking approach for visible and infrared sequences based on tracking-before-fusion

Cited by 16 publications

References 11 publications

Object Tracking with a Novel Visual-Thermal Sensor Fusion Method in Template Matching

Object Tracking with a Novel Visual-Thermal Sensor Fusion Method in Template Matching

Visible and infrared images fusion target tracking based on deep learning, progress, and prospects

SiamFT: An RGB-Infrared Fusion Tracking Method via Fully Convolutional Siamese Networks

Contact Info

Product

Resources

About