Double constrained bag of words for human action recognition

Wu, Chao; Li, Yaqian; Zhang, Yaru; Liu, Bin

doi:10.1016/j.image.2021.116399

Cited by 5 publications

(2 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The proposed system was a dualstream model with sparse sampling combined with a scene image classification scheme. Wu et al [27] used a descriptor-level Improved Dense Trajectory (IDT) and optical flow for feature extraction. El-Assal et al [28] used the difference between two consecutive image frames and the rate of change of these differences for action detection.…”

Section: State Of the Artmentioning

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

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: State Of the Artmentioning

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

“…Experiments were conducted on YouTube, Hollywood2, UCF-50, UCF-101 and HMDB51 datasets and overall average accuracy of 97.1%, 71.3%, 95.2%, 95.5% and 72.3%, respectively. Double-constrained BOW (DC-BOW) was presented in [46], which utilized spatial information of features on three different scales including hidden scale, presentation scale, and descriptor scale. Length and Angle Constrained Linear Coding (LACLC) methods were obtained by constructing a loss function between local features and visual words.…”

Section: Comparison With Existing Techniquesmentioning

confidence: 99%

Improved Shark Smell Optimization Algorithm for Human Action Recognition

Mashood Nasir,

Raza,

Hussain Shah

et al. 2023

Computers, Materials &Amp; Continua

View full text Add to dashboard Cite

Human Action Recognition (HAR) in uncontrolled environments targets to recognition of different actions from a video. An effective HAR model can be employed for an application like human-computer interaction, health care, person tracking, and video surveillance. Machine Learning (ML) approaches, specifically, Convolutional Neural Network (CNN) models had been widely used and achieved impressive results through feature fusion. The accuracy and effectiveness of these models continue to be the biggest challenge in this field. In this article, a novel feature optimization algorithm, called improved Shark Smell Optimization (iSSO) is proposed to reduce the redundancy of extracted features. This proposed technique is inspired by the behavior of white sharks, and how they find the best prey in the whole search space. The proposed iSSO algorithm divides the Feature Vector (FV) into subparts, where a search is conducted to find optimal local features from each subpart of FV. Once local optimal features are selected, a global search is conducted to further optimize these features. The proposed iSSO algorithm is employed on nine (9) selected CNN models. These CNN models are selected based on their top-1 and top-5 accuracy in ImageNet competition. To evaluate the model, two publicly available datasets UCF-Sports and Hollywood2 are selected.

show abstract