A Deep Sequence Learning Framework for Action Recognition in Small-Scale Depth Video Dataset

<div><p>Depth video sequence-based deep models for recognizing human actions are scarce compared to RGB and skeleton video sequences-based models. This scarcity limits the research advancements based on depth data, as training deep models with small-scale data is challenging. In this wor...

وصف كامل

محفوظ في:
التفاصيل البيبلوغرافية
المؤلف الرئيسي: Mohammad Farhad Bulbul (18278689) (author)
مؤلفون آخرون: Amin Ullah (12015113) (author), Hazrat Ali (421019) (author), Daijin Kim (18278692) (author)
منشور في: 2022
الموضوعات:
الوسوم: إضافة وسم
لا توجد وسوم, كن أول من يضع وسما على هذه التسجيلة!
الوصف
الملخص:<div><p>Depth video sequence-based deep models for recognizing human actions are scarce compared to RGB and skeleton video sequences-based models. This scarcity limits the research advancements based on depth data, as training deep models with small-scale data is challenging. In this work, we propose a sequence classification deep model using depth video data for scenarios when the video data are limited. Unlike summarizing the frame contents of each frame into a single class, our method can directly classify a depth video, i.e., a sequence of depth frames. Firstly, the proposed system transforms an input depth video into three sequences of multi-view temporal motion frames. Together with the three temporal motion sequences, the input depth frame sequence offers a four-stream representation of the input depth action video. Next, the DenseNet121 architecture is employed along with ImageNet pre-trained weights to extract the discriminating frame-level action features of depth and temporal motion frames. The extracted four sets of feature vectors about frames of four streams are fed into four bi-directional (BLSTM) networks. The temporal features are further analyzed through multi-head self-attention (MHSA) to capture multi-view sequence correlations. Finally, the concatenated genre of their outputs is processed through dense layers to classify the input depth video. The experimental results on two small-scale benchmark depth datasets, MSRAction3D and DHA, demonstrate that the proposed framework is efficacious even for insufficient training samples and superior to the existing depth data-based action recognition methods.</p><p> </p></div><h2>Other Information</h2> <p> Published in: Sensors<br> License: <a href="https://creativecommons.org/licenses/by/4.0/" target="_blank">https://creativecommons.org/licenses/by/4.0/</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.3390/s22186841" target="_blank">https://dx.doi.org/10.3390/s22186841</a></p>