Cite Article

Local Trajectory Occurrence Patterns for Partial Action and Gesture Recognition

Choose citation format

BibTeX

@article{IJASEIT9286,
   author = {Gustavo Garzon and Fabio Martinez},
   title = {Local Trajectory Occurrence Patterns for Partial Action and Gesture Recognition},
   journal = {International Journal on Advanced Science, Engineering and Information Technology},
   volume = {11},
   number = {1},
   year = {2021},
   pages = {20--30},
   keywords = {Action recognition; binary motion patterns; occurrence patterns; motion trajectories.},
   abstract = {Action and gesture recognition is essential in computer vision because of their multiple and potential applications. Nowadays, in the literature, dramatic advances have been reported regarding recognizing gestures and actions under uncontrolled scenarios with significant appearance and motion variations. Nevertheless, much of these approaches still require manual segmentation of temporal action boundaries and complete processing of whole sequences to obtain a prediction. This work introduces a novel motion description that can recognize actions and gestures over partial sequences. The approach starts by representing video sequences as a set of key-point trajectories. Such trajectories are then hierarchically represented from a local and regional perspective, following a statistical counting process. Firstly, each trajectory is defined as a binary occurrence pattern that allows for standing out critical motions by neighborhood densities from a local perspective. Such occurrence patterns are involved in a regional bag-of-words representation of actions. Both representations could be obtained for any interval inside the video, achieving a partial recognition of motion, and regional representation is mapped to a support vector machine to obtain a prediction. The proposed approach was evaluated on academic action recognition datasets and a large gesture dataset used for sign recognition. Regarding partial video sequence recognition, the proposed approach achieves an accuracy rate of 63% using only 20% of frames. The proposed strategy achieved a very compact description, with only 400 scalar values, which ideal for online applications.},
   issn = {2088-5334},
   publisher = {INSIGHT - Indonesian Society for Knowledge and Human Development},
   url = {http://ijaseit.insightsociety.org/index.php?option=com_content&view=article&id=9&Itemid=1&article_id=9286},
   doi = {10.18517/ijaseit.11.1.9286}
}

EndNote

%A Garzon, Gustavo
%A Martinez, Fabio
%D 2021
%T Local Trajectory Occurrence Patterns for Partial Action and Gesture Recognition
%B 2021
%9 Action recognition; binary motion patterns; occurrence patterns; motion trajectories.
%! Local Trajectory Occurrence Patterns for Partial Action and Gesture Recognition
%K Action recognition; binary motion patterns; occurrence patterns; motion trajectories.
%X Action and gesture recognition is essential in computer vision because of their multiple and potential applications. Nowadays, in the literature, dramatic advances have been reported regarding recognizing gestures and actions under uncontrolled scenarios with significant appearance and motion variations. Nevertheless, much of these approaches still require manual segmentation of temporal action boundaries and complete processing of whole sequences to obtain a prediction. This work introduces a novel motion description that can recognize actions and gestures over partial sequences. The approach starts by representing video sequences as a set of key-point trajectories. Such trajectories are then hierarchically represented from a local and regional perspective, following a statistical counting process. Firstly, each trajectory is defined as a binary occurrence pattern that allows for standing out critical motions by neighborhood densities from a local perspective. Such occurrence patterns are involved in a regional bag-of-words representation of actions. Both representations could be obtained for any interval inside the video, achieving a partial recognition of motion, and regional representation is mapped to a support vector machine to obtain a prediction. The proposed approach was evaluated on academic action recognition datasets and a large gesture dataset used for sign recognition. Regarding partial video sequence recognition, the proposed approach achieves an accuracy rate of 63% using only 20% of frames. The proposed strategy achieved a very compact description, with only 400 scalar values, which ideal for online applications.
%U http://ijaseit.insightsociety.org/index.php?option=com_content&view=article&id=9&Itemid=1&article_id=9286
%R doi:10.18517/ijaseit.11.1.9286
%J International Journal on Advanced Science, Engineering and Information Technology
%V 11
%N 1
%@ 2088-5334

IEEE

Gustavo Garzon and Fabio Martinez,"Local Trajectory Occurrence Patterns for Partial Action and Gesture Recognition," International Journal on Advanced Science, Engineering and Information Technology, vol. 11, no. 1, pp. 20-30, 2021. [Online]. Available: http://dx.doi.org/10.18517/ijaseit.11.1.9286.

RefMan/ProCite (RIS)

TY  - JOUR
AU  - Garzon, Gustavo
AU  - Martinez, Fabio
PY  - 2021
TI  - Local Trajectory Occurrence Patterns for Partial Action and Gesture Recognition
JF  - International Journal on Advanced Science, Engineering and Information Technology; Vol. 11 (2021) No. 1
Y2  - 2021
SP  - 20
EP  - 30
SN  - 2088-5334
PB  - INSIGHT - Indonesian Society for Knowledge and Human Development
KW  - Action recognition; binary motion patterns; occurrence patterns; motion trajectories.
N2  - Action and gesture recognition is essential in computer vision because of their multiple and potential applications. Nowadays, in the literature, dramatic advances have been reported regarding recognizing gestures and actions under uncontrolled scenarios with significant appearance and motion variations. Nevertheless, much of these approaches still require manual segmentation of temporal action boundaries and complete processing of whole sequences to obtain a prediction. This work introduces a novel motion description that can recognize actions and gestures over partial sequences. The approach starts by representing video sequences as a set of key-point trajectories. Such trajectories are then hierarchically represented from a local and regional perspective, following a statistical counting process. Firstly, each trajectory is defined as a binary occurrence pattern that allows for standing out critical motions by neighborhood densities from a local perspective. Such occurrence patterns are involved in a regional bag-of-words representation of actions. Both representations could be obtained for any interval inside the video, achieving a partial recognition of motion, and regional representation is mapped to a support vector machine to obtain a prediction. The proposed approach was evaluated on academic action recognition datasets and a large gesture dataset used for sign recognition. Regarding partial video sequence recognition, the proposed approach achieves an accuracy rate of 63% using only 20% of frames. The proposed strategy achieved a very compact description, with only 400 scalar values, which ideal for online applications.
UR  - http://ijaseit.insightsociety.org/index.php?option=com_content&view=article&id=9&Itemid=1&article_id=9286
DO  - 10.18517/ijaseit.11.1.9286

RefWorks

RT Journal Article
ID 9286
A1 Garzon, Gustavo
A1 Martinez, Fabio
T1 Local Trajectory Occurrence Patterns for Partial Action and Gesture Recognition
JF International Journal on Advanced Science, Engineering and Information Technology
VO 11
IS 1
YR 2021
SP 20
OP 30
SN 2088-5334
PB INSIGHT - Indonesian Society for Knowledge and Human Development
K1 Action recognition; binary motion patterns; occurrence patterns; motion trajectories.
AB Action and gesture recognition is essential in computer vision because of their multiple and potential applications. Nowadays, in the literature, dramatic advances have been reported regarding recognizing gestures and actions under uncontrolled scenarios with significant appearance and motion variations. Nevertheless, much of these approaches still require manual segmentation of temporal action boundaries and complete processing of whole sequences to obtain a prediction. This work introduces a novel motion description that can recognize actions and gestures over partial sequences. The approach starts by representing video sequences as a set of key-point trajectories. Such trajectories are then hierarchically represented from a local and regional perspective, following a statistical counting process. Firstly, each trajectory is defined as a binary occurrence pattern that allows for standing out critical motions by neighborhood densities from a local perspective. Such occurrence patterns are involved in a regional bag-of-words representation of actions. Both representations could be obtained for any interval inside the video, achieving a partial recognition of motion, and regional representation is mapped to a support vector machine to obtain a prediction. The proposed approach was evaluated on academic action recognition datasets and a large gesture dataset used for sign recognition. Regarding partial video sequence recognition, the proposed approach achieves an accuracy rate of 63% using only 20% of frames. The proposed strategy achieved a very compact description, with only 400 scalar values, which ideal for online applications.
LK http://ijaseit.insightsociety.org/index.php?option=com_content&view=article&id=9&Itemid=1&article_id=9286
DO  - 10.18517/ijaseit.11.1.9286