Abnormal Human Activity Recognition using Bayes Classifier and Convolutional Neural Network

Liu, Congcong; Ying, Jie; Han, Feilong; Ruan, Min

doi:10.1109/siprocess.2018.8600483

Cited by 28 publications

(7 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For image classification, we used an image dataset that contained images of each class to train the classification model. Four video datasets, namely, hockey fights, violent crowd detection, movies, and BEHAVE, are widely used for violence detection [41]. These datasets contain videos collected from different sources, such as the fight and non-fight actions of movies, fight scenes in national hockey matches, self-made videos, and videos collected from social media, and the implementation of the surveillance place was neglected.…”

Section: Sequential Cnn Architecturementioning

confidence: 99%

Real-Time Violent Action Recognition Using Key Frames Extraction and Deep Learning

Ahmed¹,

Ramzan²,

Khan³

et al. 2021

Computers, Materials &Amp; Continua

View full text Add to dashboard Cite

Violence recognition is crucial because of its applications in activities related to security and law enforcement. Existing semi-automated systems have issues such as tedious manual surveillances, which causes human errors and makes these systems less effective. Several approaches have been proposed using trajectory-based, non-object-centric, and deep-learning-based methods. Previous studies have shown that deep learning techniques attain higher accuracy and lower error rates than those of other methods. However, the their performance must be improved. This study explores the state-of-the-art deep learning architecture of convolutional neural networks (CNNs) and inception V4 to detect and recognize violence using video data. In the proposed framework, the keyframe extraction technique eliminates duplicate consecutive frames. This keyframing phase reduces the training data size and hence decreases the computational cost by avoiding duplicate frames. For feature selection and classification tasks, the applied sequential CNN uses one kernel size, whereas the inception v4 CNN uses multiple kernels for different layers of the architecture. For empirical analysis, four widely used standard datasets are used with diverse activities. The results confirm that the proposed approach attains 98% accuracy, reduces the computational cost, and outperforms the existing techniques of violence detection and recognition.

show abstract

Section: Sequential Cnn Architecturementioning

confidence: 99%

Real-Time Violent Action Recognition Using Key Frames Extraction and Deep Learning

Ahmed¹,

Ramzan²,

Khan³

et al. 2021

Computers, Materials &Amp; Continua

View full text Add to dashboard Cite

show abstract

“…However this method has a few drawbacks: First, this method is intrusive, there is no privacy for the user due to the usage of video images, as has been already shown in [26] privacy is of major importance when dealing with applications of the Internet of Things (IOT), second this method has a lot of pre-processing steps which make it slow. Other works have proposed the usage of more complex Neural Network Architectures such as Recurrent Neutral Networks [28,29] and Convolutional Neural Networks [19,20,22] with the goal of recognising three activities using accelerometer data [20]. However, Convolutional Neural Networks require a lot of data to train and their best result was only 92.71% accuracy.…”

Section: Related Workmentioning

confidence: 99%

GPU-based parallel Shadow Features generation at neural system for improving gait human activity recognition

Brito

Biuk-Aghai

Fong

2021

Multimed Tools Appl

View full text Add to dashboard Cite

In this paper, we propose a new method for improving human activity recognition (HAR) datasets in order to increase their classification accuracy when trained with a certain classifier like a Neural Network. In this paper a novel training/testing process for building/testing a classification model for human activity recognition (HAR) is proposed. Traditionally, HAR is done by a classifier that learns what activities a person is doing by training with skeletal data obtained from a motion sensor such as Microsoft Kinect or accelerometer sensors. These skeletal data are the spatial coordinates (x, y, z) of different parts of the human body. In addition to the spatial features that describe current positions in the skeletal data, new features called Shadow Features are used to improve the supervised learning efficiency and accuracy of Neural Network classifiers. Shadow Features are inferred from the dynamics of body movements, thereby modelling the underlying momentum of the performed activities. They provide extra dimensions of information for characterizing activities in the classification process and thus significantly improving the accuracy. These Shadow Features are generated based on the existing features obtained from sensor datasets. In this paper we show that the accuracy of a neural network classifier can be significantly improved by the addition of Shadow Features and we also show that the generation of Shadow Features can be achieved with little time cost, on the fly, with the NVIDIA GPU technology and the CUDA programming model, this way we can improve the Neural Network accuracy at almost no time cost. GPUs are particularly suitable for generating Shadow Features, since they possess multiple cores which can be taken advantage of, in order to generate Shadow Features for multiple data columns in parallel, therefore reducing a lot of processing time, especially when dealing with huge datasets.

show abstract

“…From the below Fig. [9,10] we can observe that the central pixel is replaced with a mutual mapped matrix so the 1x42 is replaced middle and then remaining all becomes zero in this manner we convolve images. Where in image processing convolution is nothing but the filtering process.…”

Section: Convolution Layermentioning

confidence: 99%

Human activity recognition using Deep Learning

M.V.D¹

2019

IJETER

View full text Add to dashboard Cite

Presently now a day's productive human activity acknowledgment stays a difficult zone of research in the field of PC vision. Smarter reconnaissance is the need of this time through which ordinary and unusual exercises can be naturally distinguished utilizing fake information along with PC innovation. In our paperwork, we represented a structural movement acknowledgment in reconnaissance recordings caught upon mechanical frameworks. The constant observation running image stream is first isolated in significant snaps, in which images are chosen utilizing the analysed convolutional neural network-based human saliency highlights. Next, transient highlights of action in the succession of casings are separated by using the convolutional layers of a Flow Net to the CNN model. At long last, a multilayer long transient memory (LSTM) is displayed for adapting large haul arrangements in the worldly optical stream highlights for action acknowledgment. The optical stream is determined, which gives the estimation of development, of A pixel in a succession of edges. Experiments are directed utilizing diverse activity and movement acknowledgment datasets and the outcomes uncover the viability of the proposed technique for action acknowledgment

show abstract

Abnormal Human Activity Recognition using Bayes Classifier and Convolutional Neural Network

Cited by 28 publications

References 15 publications

Real-Time Violent Action Recognition Using Key Frames Extraction and Deep Learning

Real-Time Violent Action Recognition Using Key Frames Extraction and Deep Learning

GPU-based parallel Shadow Features generation at neural system for improving gait human activity recognition

Human activity recognition using Deep Learning

Contact Info

Product

Resources

About