A Review on Computer Vision-Based Methods for Human Action Recognition

Al-Faris, Mahmoud; Chiverton, John; Ndzi, David; Ahmed, Ahmed Isam

doi:10.3390/jimaging6060046

Cited by 71 publications

(33 citation statements)

References 195 publications

(211 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Moreover, in comparison with EnvPSO and PSO devised ensemble networks with diverse base model configurations, the default ensemble networks employ fixed base model settings, i.e. a fixed number (3) of re-trained layers in combination with a fixed learning rate (0.001) and a fixed batch size (32), which constrain ensemble diversity, therefore limiting their performance.…”

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

An evolving ensemble model of multi-stream convolutional neural networks for human action recognition in still images

Slade

Zhang

et al. 2022

Neural Comput & Applic

View full text Add to dashboard Cite

Still image human action recognition (HAR) is a challenging problem owing to limited sources of information and large intra-class and small inter-class variations which requires highly discriminative features. Transfer learning offers the necessary capabilities in producing such features by preserving prior knowledge while learning new representations. However, optimally identifying dynamic numbers of re-trainable layers in the transfer learning process poses a challenge. In this study, we aim to automate the process of optimal configuration identification. Specifically, we propose a novel particle swarm optimisation (PSO) variant, denoted as EnvPSO, for optimal hyper-parameter selection in the transfer learning process with respect to HAR tasks with still images. It incorporates Gaussian fitness surface prediction and exponential search coefficients to overcome stagnation. It optimises the learning rate, batch size, and number of re-trained layers of a pre-trained convolutional neural network (CNN). To overcome bias of single optimised networks, an ensemble model with three optimised CNN streams is introduced. The first and second streams employ raw images and segmentation masks yielded by mask R-CNN as inputs, while the third stream fuses a pair of networks with raw image and saliency maps as inputs, respectively. The final prediction results are obtained by computing the average of class predictions from all three streams. By leveraging differences between learned representations within optimised streams, our ensemble model outperforms counterparts devised by PSO and other state-of-the-art methods for HAR. In addition, evaluated using diverse artificial landscape functions, EnvPSO performs better than other search methods with statistically significant difference in performance.

show abstract

Section: Resultsmentioning

confidence: 99%

“…eyes and wheels). Their efficiency has been ascertained in various HAR tasks in recent years [30][31][32][33][34][35][36]. Besides that, CNNs yield superior performances over those of traditional methods in solving diverse other image classification tasks [37][38][39][40].…”

Section: Introductionmentioning

confidence: 99%

An evolving ensemble model of multi-stream convolutional neural networks for human action recognition in still images

Slade

Zhang

et al. 2022

Neural Comput & Applic

View full text Add to dashboard Cite

show abstract

“…Other machine learning techniques have successfully been applied to many real-world problems i.e. skill transfer to robots [8] and autonomous navigation [7] etc. However, these techniques are usually suffering from fewer training samples and poor generalization.…”

Section: Value Functionmentioning

confidence: 99%

“…We are dealing with a certain number of sensors, which enable the IE [7] to be aware of the user's current action and goal. Human activities are observable through different sensors [8] and observations can be assumed to teach another environmental device or system to perform the task in a better way [9]. A typical way of teaching a system in a decision-making problem requires direct coding.…”

Section: Introductionmentioning

confidence: 99%

An Overview of Inverse Reinforcement Learning Techniques

Shah

Pietro

2021

Intelligent Environments 2021

View full text Add to dashboard Cite

In decision-making problems reward function plays an important role in finding the best policy. Reinforcement Learning (RL) provides a solution for decision-making problems under uncertainty in an Intelligent Environment (IE). However, it is difficult to specify the reward function for RL agents in large and complex problems. To counter these problems an extension of RL problem named Inverse Reinforcement Learning (IRL) is introduced, where reward function is learned from expert demonstrations. IRL is appealing for its potential use to build autonomous agents, capable of modeling others, deprived of compromising in performance of the task. This approach of learning by demonstrations relies on the framework of Markov Decision Process (MDP). This article elaborates original IRL algorithms along with their close variants to mitigate challenges. The purpose of this paper is to highlight an overview and theoretical background of IRL in the field of Machine Learning (ML) and Artificial Intelligence (AI). We presented a brief comparison between different variants of IRL in this article.

show abstract

“…Sensor-based HAR gets the input from smart sensors such as accelerometers, gyroscopes, and sound. There are hand-crafted directions [8], [9] ,and deep learning methods [10] from the methodology perspective. The main difference between them is in feature learning.…”

Section: Introductionmentioning

confidence: 99%

Human Action Recognition Based on Transfer Learning Approach

et al. 2021

View full text Add to dashboard Cite

Human action recognition techniques have gained significant attention among nextgeneration technologies due to their specific features and high capability to inspect video sequences to understand human actions. As a result, many fields have benefited from human action recognition techniques. Deep learning techniques played a primary role in many approaches to human action recognition. The new era of learning is spreading by transfer learning. Accordingly, this study's main objective is to propose a framework with three main phases for human action recognition. The phases are pre-training, preprocessing, and recognition. This framework presents a set of novel techniques that are three-fold as follows, (i) in the pre-training phase, a standard convolutional neural network is trained on a generic dataset to adjust weights; (ii) to perform the recognition process, this pre-trained model is then applied to the target dataset; and (iii) the recognition phase exploits convolutional neural network and long short-term memory to apply five different architectures. Three architectures are stand-alone and single-stream, while the other two are combinations between the first three in two-stream style. Experimental results show that the first three architectures recorded accuracies of 83.24%, 90.72%, and 90.85%, respectively. The last two architectures achieved accuracies of 93.48% and 94.87%, respectively. Moreover, The recorded results outperform other state-of-the-art models in the same field. INDEX TERMSConvolutional neural network (CNN), Human action recognition (HAR), Long short-term memory (LSTM), Spatiotemporal info, Transfer learning (TL).

show abstract

A Review on Computer Vision-Based Methods for Human Action Recognition

Cited by 71 publications

References 195 publications

An evolving ensemble model of multi-stream convolutional neural networks for human action recognition in still images

An evolving ensemble model of multi-stream convolutional neural networks for human action recognition in still images

An Overview of Inverse Reinforcement Learning Techniques

Human Action Recognition Based on Transfer Learning Approach

Contact Info

Product

Resources

About