Study of Human Action Recognition Based on Improved Spatio-Temporal Features

Liu, Honghai; Ju, Zhaojie; Ji, Xiaofei; Chan, Chee Seng; Khoury, Mehdi

doi:10.1007/978-3-662-53692-6_11

Cited by 19 publications

(5 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Table 9 and Figure 10 show the accuracy of recent state-of-the-art methods on the KTH dataset. It can be seen that the proposed method was slightly weaker than the methods proposed in [111,112], but it should be noted that these two methods are more complex than the proposed method. Table 10 and Figure 11 show the results for the Weizmann dataset, which confirm that the proposed method was more efficient than most existing methods.…”

Section: Comparison With Other Methodsmentioning

confidence: 84%

See 1 more Smart Citation

Deep Learning Approach for Human Action Recognition Using a Time Saliency Map Based on Motion Features Considering Camera Movement and Shot in Video Image Sequences

Alavigharahbagh,

Hajihashemi,

Machado

et al. 2023

Information

View full text Add to dashboard Cite

In this article, a hierarchical method for action recognition based on temporal and spatial features is proposed. In current HAR methods, camera movement, sensor movement, sudden scene changes, and scene movement can increase motion feature errors and decrease accuracy. Another important aspect to take into account in a HAR method is the required computational cost. The proposed method provides a preprocessing step to address these challenges. As a preprocessing step, the method uses optical flow to detect camera movements and shots in input video image sequences. In the temporal processing block, the optical flow technique is combined with the absolute value of frame differences to obtain a time saliency map. The detection of shots, cancellation of camera movement, and the building of a time saliency map minimise movement detection errors. The time saliency map is then passed to the spatial processing block to segment the moving persons and/or objects in the scene. Because the search region for spatial processing is limited based on the temporal processing results, the computations in the spatial domain are drastically reduced. In the spatial processing block, the scene foreground is extracted in three steps: silhouette extraction, active contour segmentation, and colour segmentation. Key points are selected at the borders of the segmented foreground. The last used features are the intensity and angle of the optical flow of detected key points. Using key point features for action detection reduces the computational cost of the classification step and the required training time. Finally, the features are submitted to a Recurrent Neural Network (RNN) to recognise the involved action. The proposed method was tested using four well-known action datasets: KTH, Weizmann, HMDB51, and UCF101 datasets and its efficiency was evaluated. Since the proposed approach segments salient objects based on motion, edges, and colour features, it can be added as a preprocessing step to most current HAR systems to improve performance.

show abstract

Section: Comparison With Other Methodsmentioning

confidence: 84%

“…Accuracy of state-of-the-art and the proposed methods on the KTH dataset[111][112][113][114][115][116][117][118][119][120][121][122][123][124].…”

mentioning

confidence: 99%

Deep Learning Approach for Human Action Recognition Using a Time Saliency Map Based on Motion Features Considering Camera Movement and Shot in Video Image Sequences

Alavigharahbagh,

Hajihashemi,

Machado

et al. 2023

Information

View full text Add to dashboard Cite

show abstract

“…The method also uses LGSR classifier for obtaining the multiscale-oriented features and achieves better classification. Ji et al [ 120 ] proposed an improved interest point detection to extract the 3D SIFT descriptors from single and multiple frames by applying PCA. The quantification of combined features using SVM increases computational cost and causes a drop in accuracy rate.…”

Section: Experimentation Setup and Analysismentioning

confidence: 99%

A Novel Parameter Initialization Technique Using RBM-NN for Human Action Recognition

Johnson

Uthariaraj

2020

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

Human action recognition is a trending topic in the field of computer vision and its allied fields. The goal of human action recognition is to identify any human action that takes place in an image or a video dataset. For instance, the actions include walking, running, jumping, throwing, and much more. Existing human action recognition techniques have their own set of limitations when it concerns model accuracy and flexibility. To overcome these limitations, deep learning technologies were implemented. In the deep learning approach, a model learns by itself to improve its recognition accuracy and avoids problems such as gradient eruption, overfitting, and underfitting. In this paper, we propose a novel parameter initialization technique using the Maxout activation function. Firstly, human action is detected and tracked from the video dataset to learn the spatial-temporal features. Secondly, the extracted feature descriptors are trained using the RBM-NN. Thirdly, the local features are encoded into global features using an integrated forward and backward propagation process via RBM-NN. Finally, an SVM classifier recognizes the human actions in the video dataset. The experimental analysis performed on various benchmark datasets showed an improved recognition rate when compared to other state-of-the-art learning models.

show abstract

“…As a result, 94% success was achieved with the KTH. In a different study conducted by Liu et al [62], a novel video descriptor by combining local spatiotemporal features and global positional distribution information of interest points was proposed. As a result of the classification using SVM, KTH data were classified with 94.92% accuracy.…”

Section: Related Workmentioning

confidence: 99%

Human action recognition with bag of visual words using different machine learning methods and hyperparameter optimization

Aslan

Durdu

Sabancı

2019

Neural Comput & Applic

View full text Add to dashboard Cite

Human activity recognition (HAR) has quite a wide range of applications. Due to its widespread use, new studies have been developed to improve the HAR performance. In this study, HAR is carried out using the commonly preferred KTH and Weizmann dataset, as well as a dataset which we created. Speeded up robust features (SURF) are used to extract features from these datasets. These features are reinforced with bag of visual words (BoVW). Different from the studies in the literature that use similar methods, SURF descriptors are extracted from binary images as well as grayscale images. Moreover, four different machine learning (ML) methods such as k-nearest neighbors, decision tree, support vector machine and naive Bayes are used for classification of BoVW features. Hyperparameter optimization is used to set the hyperparameters of these ML methods. As a result, ML methods are compared with each other through a comparison with the activity recognition performances of binary and grayscale image features. The results show that if the contrast of the environment decreases when a human enters the frame, the SURF of the binary image are more effective than the SURF of the gray image for HAR. Keywords Human activity recognition Á Image processing Á Speeded up robust features Á Bag of visual words Á Machine learning Á k-Nearest neighbors Á Decision tree Á Support vector machine Á Naive Bayes Á Hyperparameter optimization

show abstract

Study of Human Action Recognition Based on Improved Spatio-Temporal Features

Cited by 19 publications

References 23 publications

Deep Learning Approach for Human Action Recognition Using a Time Saliency Map Based on Motion Features Considering Camera Movement and Shot in Video Image Sequences

Deep Learning Approach for Human Action Recognition Using a Time Saliency Map Based on Motion Features Considering Camera Movement and Shot in Video Image Sequences

A Novel Parameter Initialization Technique Using RBM-NN for Human Action Recognition

Human action recognition with bag of visual words using different machine learning methods and hyperparameter optimization

Contact Info

Product

Resources

About