Human action recognition using distance transform and entropy based features

Ramya, P.; Rajeswari, R.

doi:10.1007/s11042-020-10140-z

Cited by 24 publications

(15 citation statements)

References 67 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“… Method Features Classification Accuracy 1 Baccouche et al [ 3 ] 3D CNN features 94.58 2 Baccouche et al [ 3 ] + GWF (Ours) 3D CNN features 94.9 3 orelick et al [ 16 ] Space-time saliency, Action dynamics 97.83 4 Fathi et al [ 12 ] Mid-level motion features 100 5 Bilen et al [ 4 ] 2D CNN features 85.2 5 Jaouedi et al [ 19 ] hand-crafted + 2D CNN features 96.3 5 Ramya et al [ 43 ] distance transform and entropy features 91.4 5 Liu et al [ 31 ] 3D CNN features 91.93 6 Proposed 3D CNN 3D CNN features 94.14 7 Proposed 3D CNN + GWF (Ours) 3D CNN features 95.78 ± 0.58 8 Proposed method applying Transfer Learning* 3D CNN features 96.53 ± 0.07 The best performing deep learning based human activity recognition methods are highli...…”

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

An information-rich sampling technique over spatio-temporal CNN for classification of human actions in videos

Basha

Pulabaigari

Mukherjee

2022

Multimed Tools Appl

View full text Add to dashboard Cite

We propose a novel video sampling scheme for human action recognition in videos, using Gaussian Weighing Function. Traditionally in deep learning-based human activity recognition approaches, either a few random frames or every k t h frame of the video is considered for training the 3D CNN, where k is a small positive integer, like 4, 5, or 6. This kind of sampling reduces the volume of the input data, which speeds-up the training network and also avoids overfitting to some extent, thus enhancing the performance of the 3D CNN model. In the proposed video sampling technique, consecutive k frames of a video are aggregated into a single frame by computing a Gaussian-weighted summation of the k frames. The resulting frame preserves the information in a better way than the conventional approaches and experimentally shown to perform better. In this paper, a 3-Dimensional deep CNN is proposed to extract the spatio-temporal features and follows Long Short-Term Memory (LSTM) to recognize human actions. The proposed 3D CNN architecture is capable of handling the videos where the camera is placed at a distance from the performer. Experiments are performed with KTH, WEIZMANN, and CASIA-B Human Activity and Gait datasets, whereby it is shown to outperform state-of-the-art deep learning based techniques. We achieve 95.78%, 95.27%, and 95.27% over the KTH, WEIZMANN, and CASIA-B human action and gait recognition datasets, respectively.

show abstract

Section: Resultsmentioning

confidence: 99%

“…Handcrafted features played a key role in various approaches for activity recognition [ 39 ]. Very recently, Ramya et al [ 43 ] proposed a human action recognition method using distance transform and entropy features. Semantic features ease to identify similar activities that vary visually but have common semantics.…”

Section: Introduction and Related Workmentioning

confidence: 99%

An information-rich sampling technique over spatio-temporal CNN for classification of human actions in videos

Basha

Pulabaigari

Mukherjee

2022

Multimed Tools Appl

View full text Add to dashboard Cite

show abstract

“…Finally, features from both streams are combined. A different approach to human action recognition is proposed in [38]. This study is centered around the distance transform and entropy features extracted from images of human silhouettes obtained after background subtraction.…”

Section: Deep Learning-based Methodsmentioning

confidence: 99%

Abnormal Behavior Detection in Uncrowded Videos with Two-Stream 3D Convolutional Neural Networks

Mehmood

2021

Applied Sciences

View full text Add to dashboard Cite

The increasing demand for surveillance systems has resulted in an unprecedented rise in the volume of video data being generated daily. The volume and frequency of the generation of video streams make it both impractical as well as inefficient to manually monitor them to keep track of abnormal events as they occur infrequently. To alleviate these difficulties through intelligent surveillance systems, several vision-based methods have appeared in the literature to detect abnormal events or behaviors. In this area, convolutional neural networks (CNNs) have also been frequently applied due to their prevalence in the related domain of general action recognition and classification. Although the existing approaches have achieved high detection rates for specific abnormal behaviors, more inclusive methods are expected. This paper presents a CNN-based approach that efficiently detects and classifies if a video involves the abnormal human behaviors of falling, loitering, and violence within uncrowded scenes. The approach implements a two-stream architecture using two separate 3D CNNs to accept a video and an optical flow stream as input to enhance the prediction performance. After applying transfer learning, the model was trained on a specialized dataset corresponding to each abnormal behavior. The experiments have shown that the proposed approach can detect falling, loitering, and violence with an accuracy of up to 99%, 97%, and 98%, respectively. The model achieved state-of-the-art results and outperformed the existing approaches.

show abstract

“…The distance transform is a measuring tool which plays a crucial role in computer vision [18], in pattern recognition [19], [20], in robotics [21]. The calculation of the distance transform depends on the chosen underlying distance d. The classic choices for d are: the Euclidean distance from the L 2 norm, the Manhattan distance from the L 1 norm, which produces the 4-neighborhood, the Chebyshev distance from the L ∞ norm, which produces the 8-neighborhood.…”

Section: A Euclidean Distance Transformmentioning

confidence: 99%

Modeling a Local Dissimilarity Map With Weibull Distribution–Application to 2-Class and Multi-Class Image Classification

et al. 2022

View full text Add to dashboard Cite

Human action recognition using distance transform and entropy based features

Cited by 24 publications

References 67 publications

An information-rich sampling technique over spatio-temporal CNN for classification of human actions in videos

An information-rich sampling technique over spatio-temporal CNN for classification of human actions in videos

Abnormal Behavior Detection in Uncrowded Videos with Two-Stream 3D Convolutional Neural Networks

Modeling a Local Dissimilarity Map With Weibull Distribution–Application to 2-Class and Multi-Class Image Classification

Contact Info

Product

Resources

About