template tracking
Recently Published Documents


TOTAL DOCUMENTS

47
(FIVE YEARS 0)

H-INDEX

10
(FIVE YEARS 0)

2019 ◽  
Vol 17 (2) ◽  
pp. 257-266
Author(s):  
Peng-Xia Cao ◽  
Wen-Xin Li ◽  
Wei-Ping Ma


Sensors ◽  
2019 ◽  
Vol 19 (18) ◽  
pp. 3945
Author(s):  
Kaiheng Dai ◽  
Yuehuan Wang ◽  
Qiong Song

In this paper, we propose a fast and accurate deep network-based object tracking method, which combines feature representation, template tracking and foreground detection into a single framework for robust tracking. The proposed framework consists of a backbone network, which feeds into two parallel networks, TmpNet for template tracking and FgNet for foreground detection. The backbone network is a pre-trained modified VGG network, in which a few parameters need to be fine-tuned for adapting to the tracked object. FgNet is a fully convolutional network to distinguish the foreground from background in a pixel-to-pixel manner. The parameter in TmpNet is the learned channel-wise target template, which initializes in the first frame and performs fast template tracking in the test frames. To enable each component to work closely with each other, we use a multi-task loss to end-to-end train the proposed framework. In online tracking, we combine the score maps from TmpNet and FgNet to find the optimal tracking results. Experimental results on object tracking benchmarks demonstrate that our approach achieves favorable tracking accuracy against the state-of-the-art trackers while running at a real-time speed of 38 fps.



Author(s):  
Xuebin Qin ◽  
Shida He ◽  
Zichen Zhang ◽  
Masood Dehghan ◽  
Jun Jin ◽  
...  


Algorithms ◽  
2018 ◽  
Vol 11 (8) ◽  
pp. 122 ◽  
Author(s):  
Chi-Yi Tsai ◽  
Kuang-Jui Hsu ◽  
Humaira Nisar

Three-Dimensional (3D) object pose estimation plays a crucial role in computer vision because it is an essential function in many practical applications. In this paper, we propose a real-time model-based object pose estimation algorithm, which integrates template matching and Perspective-n-Point (PnP) pose estimation methods to deal with this issue efficiently. The proposed method firstly extracts and matches keypoints of the scene image and the object reference image. Based on the matched keypoints, a two-dimensional (2D) planar transformation between the reference image and the detected object can be formulated by a homography matrix, which can initialize a template tracking algorithm efficiently. Based on the template tracking result, the correspondence between image features and control points of the Computer-Aided Design (CAD) model of the object can be determined efficiently, thus leading to a fast 3D pose tracking result. Finally, the 3D pose of the object with respect to the camera is estimated by a PnP solver based on the tracked 2D-3D correspondences, which improves the accuracy of the pose estimation. Experimental results show that the proposed method not only achieves real-time performance in tracking multiple objects, but also provides accurate pose estimation results. These advantages make the proposed method suitable for many practical applications, such as augmented reality.



2018 ◽  
Vol 17 (3) ◽  
pp. 437-446
Author(s):  
Bin Huang ◽  
Yongrong Sun ◽  
Qinghua Zeng


Author(s):  
Fabio Mendez ◽  
Mark Ferguson ◽  
Naim Dahnoun ◽  
Scott Tancock


2016 ◽  
Vol 24 (2) ◽  
pp. e2081
Author(s):  
Geunseop Lee ◽  
Jesse Barlow


2016 ◽  
Vol 55 (25) ◽  
pp. 7186 ◽  
Author(s):  
Jie Guo ◽  
Chang’an Zhu ◽  
Siliang Lu ◽  
Dashan Zhang ◽  
Chunyu Zhang




Sign in / Sign up

Export Citation Format

Share Document