TY - GEN
T1 - Toward semantic action recognition for avocado harvesting process based on single shot multibox detector
AU - Vasconez, Juan Pablo
AU - Salvo, Jaime
AU - Auat, Fernando
N1 - Publisher Copyright:
© 2018 IEEE.
PY - 2019/1/10
Y1 - 2019/1/10
N2 - To date, human action recognition is still a challenging topic and has been addressed from many perspectives. Detection of human actions can be useful to obtain relevant information to improve complex processes, which is the case of agricultural applications. In this work, the detection of objects that can provide information for human action recognition based on semantic representations is studied. For this purpose, a convolutional neuronal network based on Single Shot MultiBox Detector meta-architecture and MobileNet feature extractor was implemented, which has been trained to detect nine classes of objects during the process of collecting avocados in a Chilean farm. We have found that such detected objects are related to seven possible actions that can be detected during avocado harvesting process. Such information could allow to directly detect certain actions in still images, or improve conventional action detection methods during the harvesting process. The results show that is possible to detect human actions during the process, obtaining action recognition performances from 41% to 80% depending on the task. This approach can help to obtain information about how to improve harvesting process and reduce human workload in near future, which may be an important contribution for the search of sustainable agricultural practices.
AB - To date, human action recognition is still a challenging topic and has been addressed from many perspectives. Detection of human actions can be useful to obtain relevant information to improve complex processes, which is the case of agricultural applications. In this work, the detection of objects that can provide information for human action recognition based on semantic representations is studied. For this purpose, a convolutional neuronal network based on Single Shot MultiBox Detector meta-architecture and MobileNet feature extractor was implemented, which has been trained to detect nine classes of objects during the process of collecting avocados in a Chilean farm. We have found that such detected objects are related to seven possible actions that can be detected during avocado harvesting process. Such information could allow to directly detect certain actions in still images, or improve conventional action detection methods during the harvesting process. The results show that is possible to detect human actions during the process, obtaining action recognition performances from 41% to 80% depending on the task. This approach can help to obtain information about how to improve harvesting process and reduce human workload in near future, which may be an important contribution for the search of sustainable agricultural practices.
KW - agriculture
KW - avocado harvesting
KW - Semantic action recognition
KW - Single Shot MultiBox Detector
UR - http://www.scopus.com/inward/record.url?scp=85062183511&partnerID=8YFLogxK
U2 - 10.1109/ICA-ACCA.2018.8609848
DO - 10.1109/ICA-ACCA.2018.8609848
M3 - Conference contribution
AN - SCOPUS:85062183511
T3 - IEEE ICA-ACCA 2018 - IEEE International Conference on Automation/23rd Congress of the Chilean Association of Automatic Control: Towards an Industry 4.0 - Proceedings
BT - IEEE ICA-ACCA 2018 - IEEE International Conference on Automation/23rd Congress of the Chilean Association of Automatic Control
A2 - Munoz, Carlos
A2 - Lefranc, Gaston
A2 - Fernandez-Fernandez, Mario
A2 - Rubio, Ernesto
A2 - Duran-Faundez, Cristian
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - IEEE International Conference on Automation/23rd Congress of the Chilean Association of Automatic Control: Towards an Industry 4.0, ICA-ACCA 2018
Y2 - 17 October 2018 through 19 October 2018
ER -
