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
A fim de resolver a influência da mudança de escala no rastreamento de alvos usando o drone, é proposto um algoritmo de rastreamento de alvos em múltiplas escalas, baseado no algoritmo de rastreamento de recursos de cores. O algoritmo realizou rastreamento de escala adaptativo treinando filtros de correlação de posição e escala. Ele pode primeiro obter a posição central alvo do próximo quadro calculando o máximo da resposta, onde o filtro de correlação de posição é aprendido pelo classificador de mínimos quadrados e a redução de dimensionalidade para recursos de cor é analisada por análise de componentes principais. O filtro de correlação de escala é obtido pelas características de cor em 33 áreas retangulares que é definido pelo fator de escala em torno da localização central e tem dimensões reduzidas pela decomposição de triângulo ortogonal. Finalmente, a localização e o tamanho do alvo são atualizados pelo máximo da resposta. Ao testar 13 sequências de vídeo desafiadoras tiradas pelo drone, os resultados mostram que o algoritmo tem adaptabilidade às mudanças na escala alvo e sua robustez, juntamente com muitos outros indicadores de desempenho, são melhores do que os métodos mais avançados em Variação de iluminação, movimento rápido, desfoque de movimento e outras situações complexas.
Qiusheng HE
Taiyuan University of Science and Technology
Xiuyan SHAO
University of Oulu
Wei CHEN
China University of Mining and Technology,Xi'an University of Science and Technology
Xiaoyun LI
Taiyuan University of Science and Technology
Xiao YANG
China University of Mining and Technology
Tongfeng SUN
China University of Mining and Technology
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.
Copiar
Qiusheng HE, Xiuyan SHAO, Wei CHEN, Xiaoyun LI, Xiao YANG, Tongfeng SUN, "Adaptive Multi-Scale Tracking Target Algorithm through Drone" in IEICE TRANSACTIONS on Communications,
vol. E102-B, no. 10, pp. 1998-2005, October 2019, doi: 10.1587/transcom.2018DRP0040.
Abstract: In order to solve the influence of scale change on target tracking using the drone, a multi-scale target tracking algorithm is proposed which based on the color feature tracking algorithm. The algorithm realized adaptive scale tracking by training position and scale correlation filters. It can first obtain the target center position of next frame by computing the maximum of the response, where the position correlation filter is learned by the least squares classifier and the dimensionality reduction for color features is analyzed by principal component analysis. The scale correlation filter is obtained by color characteristics at 33 rectangular areas which is set by the scale factor around the central location and is reduced dimensions by orthogonal triangle decomposition. Finally, the location and size of the target are updated by the maximum of the response. By testing 13 challenging video sequences taken by the drone, the results show that the algorithm has adaptability to the changes in the target scale and its robustness along with many other performance indicators are both better than the most state-of-the-art methods in illumination Variation, fast motion, motion blur and other complex situations.
URL: https://global.ieice.org/en_transactions/communications/10.1587/transcom.2018DRP0040/_p
Copiar
@ARTICLE{e102-b_10_1998,
author={Qiusheng HE, Xiuyan SHAO, Wei CHEN, Xiaoyun LI, Xiao YANG, Tongfeng SUN, },
journal={IEICE TRANSACTIONS on Communications},
title={Adaptive Multi-Scale Tracking Target Algorithm through Drone},
year={2019},
volume={E102-B},
number={10},
pages={1998-2005},
abstract={In order to solve the influence of scale change on target tracking using the drone, a multi-scale target tracking algorithm is proposed which based on the color feature tracking algorithm. The algorithm realized adaptive scale tracking by training position and scale correlation filters. It can first obtain the target center position of next frame by computing the maximum of the response, where the position correlation filter is learned by the least squares classifier and the dimensionality reduction for color features is analyzed by principal component analysis. The scale correlation filter is obtained by color characteristics at 33 rectangular areas which is set by the scale factor around the central location and is reduced dimensions by orthogonal triangle decomposition. Finally, the location and size of the target are updated by the maximum of the response. By testing 13 challenging video sequences taken by the drone, the results show that the algorithm has adaptability to the changes in the target scale and its robustness along with many other performance indicators are both better than the most state-of-the-art methods in illumination Variation, fast motion, motion blur and other complex situations.},
keywords={},
doi={10.1587/transcom.2018DRP0040},
ISSN={1745-1345},
month={October},}
Copiar
TY - JOUR
TI - Adaptive Multi-Scale Tracking Target Algorithm through Drone
T2 - IEICE TRANSACTIONS on Communications
SP - 1998
EP - 2005
AU - Qiusheng HE
AU - Xiuyan SHAO
AU - Wei CHEN
AU - Xiaoyun LI
AU - Xiao YANG
AU - Tongfeng SUN
PY - 2019
DO - 10.1587/transcom.2018DRP0040
JO - IEICE TRANSACTIONS on Communications
SN - 1745-1345
VL - E102-B
IS - 10
JA - IEICE TRANSACTIONS on Communications
Y1 - October 2019
AB - In order to solve the influence of scale change on target tracking using the drone, a multi-scale target tracking algorithm is proposed which based on the color feature tracking algorithm. The algorithm realized adaptive scale tracking by training position and scale correlation filters. It can first obtain the target center position of next frame by computing the maximum of the response, where the position correlation filter is learned by the least squares classifier and the dimensionality reduction for color features is analyzed by principal component analysis. The scale correlation filter is obtained by color characteristics at 33 rectangular areas which is set by the scale factor around the central location and is reduced dimensions by orthogonal triangle decomposition. Finally, the location and size of the target are updated by the maximum of the response. By testing 13 challenging video sequences taken by the drone, the results show that the algorithm has adaptability to the changes in the target scale and its robustness along with many other performance indicators are both better than the most state-of-the-art methods in illumination Variation, fast motion, motion blur and other complex situations.
ER -