Improving bag-of-poses with semi-temporal pose descriptors for skeleton-based action recognition

Agahian, Saeid; Negin, Farhood; Köse, Cemal

doi:10.1007/s00371-018-1489-7

Cited by 34 publications

(9 citation statements)

References 83 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…..50 segments. For a section, a positive label is allocated if: (1) The segment has a ground truth that overlaps with the most significant temporal intersection over Union (tIoU); or (2) For any ground reality, the section has a tIoU greater than 0.5. A section that has no overlap with any ground reality, a negative mark is assigned.…”

Section: Performance Evaluation and Analysismentioning

confidence: 99%

“…A video is a sequence of image frames that can be provided to a CNN network for image analysis. In still images, one can use CNN to identify the features [1], however, in videos, it is critical to capture the context between the image frames extracted from the video while labelling to avoid loss of data. Consider an image of a half-filled cardboard box that can be labelled as packing a box or unpacking a box depending on the frames before and after it.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

HARTIV: Human Activity Recognition Using Temporal Information in Videos

Deotale¹,

Verma²,

Suresh³

et al. 2022

Computers, Materials &Amp; Continua

View full text Add to dashboard Cite

Nowadays, the most challenging and important problem of computer vision is to detect human activities and recognize the same with temporal information from video data. The video datasets are generated using cameras available in various devices that can be in a static or dynamic position and are referred to as untrimmed videos. Smarter monitoring is a historical necessity in which commonly occurring, regular, and out-of-the-ordinary activities can be automatically identified using intelligence systems and computer vision technology. In a long video, human activity may be present anywhere in the video. There can be a single or multiple human activities present in such videos. This paper presents a deep learning-based methodology to identify the locally present human activities in the video sequences captured by a single wide-view camera in a sports environment. The recognition process is split into four parts: firstly, the video is divided into different set of frames, then the human body part in a sequence of frames is identified, next process is to identify the human activity using a convolutional neural network and finally the time information of the observed postures for each activity is determined with the help of a deep learning algorithm. The proposed approach has been tested on two different sports datasets including ActivityNet and THUMOS. Three sports activities like swimming, cricket bowling and high jump have been considered in this paper and classified with the temporal information i.e., the start and end time for every activity present in the video. The convolutional neural network and long short-term memory are used for feature extraction of temporal action recognition from video data of sports activity. The outcomes show that the proposed method for activity recognition in the sports domain outperforms the existing methods.

show abstract

Section: Performance Evaluation and Analysismentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

HARTIV: Human Activity Recognition Using Temporal Information in Videos

Deotale¹,

Verma²,

Suresh³

et al. 2022

Computers, Materials &Amp; Continua

View full text Add to dashboard Cite

show abstract

“…In the past few years, researchers have examined human actions by extracting skeleton information through video sensors. In [12], the input frame sequences were used for the extraction of temporal displacement skeleton poses and k-means clustering was applied to generate key poses. Further, SVM classifier was used to classify each action pose.…”

Section: Action Recognition Via Video Sensormentioning

confidence: 99%

Sensors-Based Ambient Assistant Living via E-Monitoring Technology

Hafeez¹,

Ghadi²,

Alarfaj³

et al. 2022

Computers, Materials &Amp; Continua

View full text Add to dashboard Cite

Independent human living systems require smart, intelligent, and sustainable online monitoring so that an individual can be assisted timely. Apart from ambient assisted living, the task of monitoring human activities plays an important role in different fields including virtual reality, surveillance security, and human interaction with robots. Such systems have been developed in the past with the use of various wearable inertial sensors and depth cameras to capture the human actions. In this paper, we propose multiple methods such as random occupancy pattern, spatio temporal cloud, waypoint trajectory, Hilbert transform, Walsh Hadamard transform and bone pair descriptors to extract optimal features corresponding to different human actions. These features sets are then normalized using min-max normalization and optimized using the Fuzzy optimization method. Finally, the Masi entropy classifier is applied for action recognition and classification. Experiments have been performed on three challenging datasets, namely, UTD-MHAD, 50 Salad, and CMU-MMAC. During experimental evaluation, the proposed novel approach of recognizing human actions has achieved an accuracy rate of 90.1% with UTD-MHAD dataset, 90.6% with 50 Salad dataset, and 89.5% with CMU-MMAC dataset. Hence experimental results validated the proposed system.

show abstract

“…HAR techniques can be divided into three groups: vision-based, sensor-based, and WiFi-based. Several image-based methods for HAR have been published in recent years, using datasets such as RGB (red, green, and blue [18]), depth [19], and skeleton images [20]. The RGB dataset may not be qualified and robust enough in this method when the video contains considerable sudden camera movements and cluttered background.…”

Section: Related Workmentioning

confidence: 99%

A CSI-Based Human Activity Recognition Using Deep Learning

Moshiri

Shahbazian²,

Nabati

et al. 2021

Sensors

View full text Add to dashboard Cite

The Internet of Things (IoT) has become quite popular due to advancements in Information and Communications technologies and has revolutionized the entire research area in Human Activity Recognition (HAR). For the HAR task, vision-based and sensor-based methods can present better data but at the cost of users’ inconvenience and social constraints such as privacy issues. Due to the ubiquity of WiFi devices, the use of WiFi in intelligent daily activity monitoring for elderly persons has gained popularity in modern healthcare applications. Channel State Information (CSI) as one of the characteristics of WiFi signals, can be utilized to recognize different human activities. We have employed a Raspberry Pi 4 to collect CSI data for seven different human daily activities, and converted CSI data to images and then used these images as inputs of a 2D Convolutional Neural Network (CNN) classifier. Our experiments have shown that the proposed CSI-based HAR outperforms other competitor methods including 1D-CNN, Long Short-Term Memory (LSTM), and Bi-directional LSTM, and achieves an accuracy of around 95% for seven activities.

show abstract

Improving bag-of-poses with semi-temporal pose descriptors for skeleton-based action recognition

Abstract: Over the last few decades, human action recognition has become one of the most challenging tasks in the field of computer vision. Employing economical depth sensors such as Microsoft Kinect as well as recent successes of deep learning approaches in image understanding has led to

Cited by 34 publications

References 83 publications

HARTIV: Human Activity Recognition Using Temporal Information in Videos

HARTIV: Human Activity Recognition Using Temporal Information in Videos

Sensors-Based Ambient Assistant Living via E-Monitoring Technology

A CSI-Based Human Activity Recognition Using Deep Learning

Contact Info

Product

Resources

About