The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
pandangan teks lengkap
161
CNN pra-latihan di ImageNet telah digunakan secara meluas dalam penjejakan objek untuk pengekstrakan ciri. Walau bagaimanapun, disebabkan ketidakpadanan domain antara klasifikasi imej dan penjejakan objek, penenggelaman ciri khusus sasaran oleh hingar sebahagian besarnya mengurangkan keupayaan ekspresi ciri konvolusi, mengakibatkan penjejakan yang tidak cekap. Dalam kertas ini, kami mencadangkan algoritma penjejakan yang mantap dengan pengekstrakan ciri khusus sasaran dimensi rendah. Pertama, modul PCA berlatarkan novel dicadangkan untuk mempunyai pengekstrakan eksplisit ciri khusus sasaran dimensi rendah, yang menjadikan model penampilan baharu lebih berkesan dan cekap. Seterusnya, proses penapis zarah yang pantas dinaikkan untuk mempercepatkan lagi keseluruhan saluran paip penjejakan dengan berkongsi pengiraan konvolusi dengan lapisan ROI-Align. Selain itu, skema berpandukan skor klasifikasi digunakan untuk mengemas kini model penampilan untuk menyesuaikan diri dengan variasi sasaran sambil pada masa yang sama mengelakkan drift model yang disebabkan oleh oklusi objek. Keputusan eksperimen pada OTB100 dan Temple Color128 menunjukkan bahawa, algoritma yang dicadangkan telah mencapai prestasi unggul dalam kalangan penjejak masa nyata. Selain itu, algoritma kami bersaing dengan penjejak terkini dalam ketepatan semasa berjalan pada kelajuan masa nyata.
Chengcheng JIANG
Fudan University
Xinyu ZHU
Fudan University
Chao LI
Fudan University
Gengsheng CHEN
Fudan University
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Salinan
Chengcheng JIANG, Xinyu ZHU, Chao LI, Gengsheng CHEN, "A Robust Tracking with Low-Dimensional Target-Specific Feature Extraction" in IEICE TRANSACTIONS on Information,
vol. E102-D, no. 7, pp. 1349-1361, July 2019, doi: 10.1587/transinf.2019EDP7032.
Abstract: Pre-trained CNNs on ImageNet have been widely used in object tracking for feature extraction. However, due to the domain mismatch between image classification and object tracking, the submergence of the target-specific features by noise largely decreases the expression ability of the convolutional features, resulting in an inefficient tracking. In this paper, we propose a robust tracking algorithm with low-dimensional target-specific feature extraction. First, a novel cascaded PCA module is proposed to have an explicit extraction of the low-dimensional target-specific features, which makes the new appearance model more effective and efficient. Next, a fast particle filter process is raised to further accelerate the whole tracking pipeline by sharing convolutional computation with a ROI-Align layer. Moreover, a classification-score guided scheme is used to update the appearance model for adapting to target variations while at the same time avoiding the model drift that caused by the object occlusion. Experimental results on OTB100 and Temple Color128 show that, the proposed algorithm has achieved a superior performance among real-time trackers. Besides, our algorithm is competitive with the state-of-the-art trackers in precision while runs at a real-time speed.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2019EDP7032/_p
Salinan
@ARTICLE{e102-d_7_1349,
author={Chengcheng JIANG, Xinyu ZHU, Chao LI, Gengsheng CHEN, },
journal={IEICE TRANSACTIONS on Information},
title={A Robust Tracking with Low-Dimensional Target-Specific Feature Extraction},
year={2019},
volume={E102-D},
number={7},
pages={1349-1361},
abstract={Pre-trained CNNs on ImageNet have been widely used in object tracking for feature extraction. However, due to the domain mismatch between image classification and object tracking, the submergence of the target-specific features by noise largely decreases the expression ability of the convolutional features, resulting in an inefficient tracking. In this paper, we propose a robust tracking algorithm with low-dimensional target-specific feature extraction. First, a novel cascaded PCA module is proposed to have an explicit extraction of the low-dimensional target-specific features, which makes the new appearance model more effective and efficient. Next, a fast particle filter process is raised to further accelerate the whole tracking pipeline by sharing convolutional computation with a ROI-Align layer. Moreover, a classification-score guided scheme is used to update the appearance model for adapting to target variations while at the same time avoiding the model drift that caused by the object occlusion. Experimental results on OTB100 and Temple Color128 show that, the proposed algorithm has achieved a superior performance among real-time trackers. Besides, our algorithm is competitive with the state-of-the-art trackers in precision while runs at a real-time speed.},
keywords={},
doi={10.1587/transinf.2019EDP7032},
ISSN={1745-1361},
month={July},}
Salinan
TY - JOUR
TI - A Robust Tracking with Low-Dimensional Target-Specific Feature Extraction
T2 - IEICE TRANSACTIONS on Information
SP - 1349
EP - 1361
AU - Chengcheng JIANG
AU - Xinyu ZHU
AU - Chao LI
AU - Gengsheng CHEN
PY - 2019
DO - 10.1587/transinf.2019EDP7032
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E102-D
IS - 7
JA - IEICE TRANSACTIONS on Information
Y1 - July 2019
AB - Pre-trained CNNs on ImageNet have been widely used in object tracking for feature extraction. However, due to the domain mismatch between image classification and object tracking, the submergence of the target-specific features by noise largely decreases the expression ability of the convolutional features, resulting in an inefficient tracking. In this paper, we propose a robust tracking algorithm with low-dimensional target-specific feature extraction. First, a novel cascaded PCA module is proposed to have an explicit extraction of the low-dimensional target-specific features, which makes the new appearance model more effective and efficient. Next, a fast particle filter process is raised to further accelerate the whole tracking pipeline by sharing convolutional computation with a ROI-Align layer. Moreover, a classification-score guided scheme is used to update the appearance model for adapting to target variations while at the same time avoiding the model drift that caused by the object occlusion. Experimental results on OTB100 and Temple Color128 show that, the proposed algorithm has achieved a superior performance among real-time trackers. Besides, our algorithm is competitive with the state-of-the-art trackers in precision while runs at a real-time speed.
ER -