Implementation of convolutional-LSTM network based on CPU, GPU and pynq-zl board
Authors:
- 1 April 2019
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
Abstract
Deep learning is among the most commonly investigated approach in computer vision area. Quite recently, considerable attention has been paid to develop an end-to-end deep learning approach for action recognition. According to the developments of these time and resource consuming deep learning models, there is now a growing interest in implementing an accelerator low-power hardware architecture. The main objective of this paper is to implement an optimized convolutional-Long Short Term Memory (LSTM) architecture based a low-cost pynq-zl design tool for human action recognition applications. Firstly, the pre-trained Convolutional Neural Network (CNN) model is applied to extract relevant features from videos. Secondly, the classification of these sequences is done using the LSTM with optimized parameters. Finally, the model testing step is performed on the ARM of the pynq-zl FPGA platform and compared with the performances obtained by the central processing unit and graphics processing tools. The experimental results, performed in UTD-MHAD dataset, prove the efficiency of our proposed approach.Keywords
This publication has 18 references indexed in Scilit:
- Script identification in natural scene image and video frames using an attention based Convolutional-LSTM networkPattern Recognition, 2019
- Asymmetric 3D Convolutional Neural Networks for action recognitionPattern Recognition, 2019
- On How to Efficiently Implement Deep Learning Algorithms on PYNQ Platform2018
- Multi-stream CNN: Learning representations based on human-related regions for action recognitionPattern Recognition, 2018
- A survey on deep learning for big dataInformation Fusion, 2018
- Attention-Based Temporal Weighted Convolutional Neural Network for Action Recognition2018
- Global Context-Aware Attention LSTM Networks for 3D Action Recognition2017
- Human action recognition using transfer learning with deep representations2017
- Rethinking the Inception Architecture for Computer Vision2016
- UTD-MHAD: A multimodal dataset for human action recognition utilizing a depth camera and a wearable inertial sensor2015