Tao Pang

Tao Pang

Auto-generated profile, based on publicly available information

Tao Pang

School of Electronic and Information Engineering, Shenyang Aerospace University, Shenyang, China

Research Focus & Metrics

Academic Career Length

12Years (2015-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
23 December 2020 in IEEE Access
Verified
Journal Article
Open access
EWErshen Wang
Ershen Wang
DWDonglei Wang
Donglei Wang
YHYufeng Huang
Yufeng Huang
GTGang Tong
Gang Tong
SXSong Xu
Song Xu
TPTao Pang
Tao Pang
Visual object tracking is urgent yet challenging work since it requires the simultaneous and effective classification and estimation of a target. Thus, research on tracking has been attracting a considerable amount of attention despite the limitations of existing trackers owing to deformation, occlusion and motion. For most current tracking methods, researchers have proposed various ways to adopt a multi-scale search or anchors for estimation, but these methods always need prior knowledge and too many hyperparameters. To address these issues, we proposed a novel Siamese Attentional Cascade Keypoints Tracking Network named SiamACN to exactly track the object by using keypoints prediction instead of anchors. Compared to complex target prediction, the anchor-free method is performed to avoid plaguy hyperparameters, and a simplified hourglass network with global attention is considered the backbone to improve the tracking efficiency. Further, our framework uses keypoints prediction around the target with cascade corner pooling to simplify the model. To certificate the superiority of our framework, extensive tests are conducted on five tracking benchmarks, including OTB-2015, VOT-2016, VOT-2018, LaSOT and UAV123. Our method achieves the leading performance with an accuracy of 61.2% on VOT2016 and favorably runs at 32 FPS against other competing algorithms, which confirms its effectiveness in real-time applications.

1 May 2015
Verified
Conference Paper
Closed access
RXRuan Xiaogang
Ruan Xiaogang
WDWang Danyang
Wang Danyang
PTPang Tao
Pang Tao
Aiming at the problems in unknown environment for mobile robots map building, a method combined monocular vision and DGSOM(Dynamic Growing-SOM) Algorithm is proposed. The method first uses a monocular camera to collect environment images, after treatment with monocular vision processing technology, environmental information samples for DGSOM algorithm are obtained from image information, and then they can be used as neural network training samples, thus the topologic map that describes the environment information is generated with a few SOFM neurons. The experimental result shows that autonomous mapping for robot using a combination of monocular vision and DGSOM algorithm is feasible, and the robot can realize environment mapping automatically.