Vision-based Human Action Recognition on Pre-trained AlexNet

Citation

Zamri, NorulNarijah and Goh, Fan Ling and Pang, Ying Han and Ooi, Shih Yin (2019) Vision-based Human Action Recognition on Pre-trained AlexNet. In: 2019 9th IEEE International Conference on Control System, Computing and Engineering (ICCSCE), 29 Nov.-1 Dec. 2019, Penang, Penang, Malaysia.

[img] Text
136.pdf - Published Version
Restricted to Repository staff only

Download (764kB)

Abstract

The Deep learning analysis has been extensively carried out in the context of object/ pattern recognition due to its excellence in feature extraction and classification. However, the superior performance just can be guaranteed with the availability of huge amounts of training data and also highspecification data processing unit to process the data deeper at high speeds. Hence, another alternative is by applying transfer learning. In transfer learning, a neural network model is first trained on a data similar to the targeted data. With that, the knowledge such as features, weights etc. could be leveraged from the trained model to train the new model. In this project, a vision-based human action recognition via a transfer learning is conducted. Specifically, in the proposed approach, the earlier layers of a pre-trained AlexNet is preserved since those extracted low-level features are characterizing generic features which are common to most data. However, the pre-train network is fine-tuned based on our interested data, that is human action data. Since AlexNet requires input data of size 227*227*3, the frames of each video are processed into 3 different templates. The three computed templates are: (1) Motion History Image carrying spatio-temporal information, (2) Binary Motion Energy Image incorporating motion region information and (3) optical flow template holding accumulative motion speed information. The proposed approach is validated on two publicly available databases, which are Weizmann database and KTH database. From the empirical results, a promising performance is obtained with about 90% accuracy from the databases.

Item Type: Conference or Workshop Item (Paper)
Uncontrolled Keywords: Human activity recognition, human action, pre-trained AlexNet, binary energy image, motion historical image, optical flow magniture
Subjects: T Technology > TK Electrical engineering. Electronics Nuclear engineering > TK7800-8360 Electronics
Divisions: Faculty of Information Science and Technology (FIST)
Depositing User: Ms Rosnani Abd Wahab
Date Deposited: 13 Oct 2021 02:53
Last Modified: 13 Oct 2021 02:53
URII: http://shdl.mmu.edu.my/id/eprint/9565

Downloads

Downloads per month over past year

View ItemEdit (login required)