Video based action detection and recognition human using optical flow and SVM classifier

Basavaiah, Jagadeesh; Patil, Chandrashekar M

doi:10.1109/rteict.2016.7808136

Cited by 19 publications

(9 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…B Jagadeesh et al [12] (2016) described that human actions were detected and recognized based on video on the KTH dataset and on videos of real-time. Initially, the extraction of 100 frames was completed from every video sequence and the optical flow was evaluated among the frames.…”

Section: Dogo Rangsang Researchmentioning

confidence: 99%

Design and Implementation of Improved Ensemble Classification Algorithm for Human Activity Recognition (Har)

Tahmid¹,

Pal²

2022

DRSR

View full text Add to dashboard Cite

To recognize the human activity is considered very essential in human-to-human interaction and interpersonal relations due to its nature of providing information regarding the identity of a people, their personality and psychological state. The extraction of this information is very challenging. The main operation occurred before the systematic fields of computer vision as well as ML is the potential for recognizing the activities of different person. The human activity recognition technique is executed in various stages such as to pre-process the data, extract the features and classifying the data. This work proposes a improved ensemble model in the human activity recognition which is the combination of K-mean clustering, PCA and of multiple classifiers which are merged through voting methodology. Python is executed to get evaluated the presented framework and various metrics such as accuracy, precision and recall are considered to analyse the results. The major subject of study of the scientific and research areas of computer vision and ML is the potential of human for identifying the activities of particular person. A sequence of human body movements in which different body parts (head, hands, legs etc.) are engaged in concurrent manner is known as action.

show abstract

Section: Dogo Rangsang Researchmentioning

confidence: 99%

Design and Implementation of Improved Ensemble Classification Algorithm for Human Activity Recognition (Har)

Tahmid¹,

Pal²

2022

DRSR

View full text Add to dashboard Cite

show abstract

“…Many SVM-based action recognition algorithms have been developed, such as Liu and Zhi-Pan [20], who proposed an action recognition algorithm based on Kinect and SVM methods. Jagadeesh and Patil et al [21] proposed that video-based human action recognition is addressed and performed on a public baseline dataset to conduct verification. Karpathy and Toderici et al [22] combined local spatial-temporal feature information and proposed multiresolution action recognition methods and improved network speeding of the training.…”

Section: Related Workmentioning

confidence: 99%

Hi-EADN: Hierarchical Excitation Aggregation and Disentanglement Frameworks for Action Recognition Based on Videos

Lee

2021

Symmetry

View full text Add to dashboard Cite

Most existing video action recognition methods mainly rely on high-level semantic information from convolutional neural networks (CNNs) but ignore the discrepancies of different information streams. However, it does not normally consider both long-distance aggregations and short-range motions. Thus, to solve these problems, we propose hierarchical excitation aggregation and disentanglement networks (Hi-EADNs), which include multiple frame excitation aggregation (MFEA) and a feature squeeze-and-excitation hierarchical disentanglement (SEHD) module. MFEA specifically uses long-short range motion modelling and calculates the feature-level temporal difference. The SEHD module utilizes these differences to optimize the weights of each spatiotemporal feature and excite motion-sensitive channels. Moreover, without introducing additional parameters, this feature information is processed with a series of squeezes and excitations, and multiple temporal aggregations with neighbourhoods can enhance the interaction of different motion frames. Extensive experimental results confirm our proposed Hi-EADN method effectiveness on the UCF101 and HMDB51 benchmark datasets, where the top-5 accuracy is 93.5% and 76.96%.

show abstract

“…The SVM is also known as a binary classifier, in which data is classified according to the hyperplane [27]. It supports classification and regression functions, and can handle several continuous and categorical variables [39]. The SVM demonstrated to be an extremely robust and effective categorization and regression algorithm [40].…”

Section: Scalp Problem Classificationmentioning

confidence: 99%

Pre-trained classification of scalp conditions using image processing

Ibrahim

Azmy

Mangshor

et al. 2020

IJEECS

View full text Add to dashboard Cite

<span>Scalp problems may occur due to the miscellaneous factor, which includes genetics, stress, abuse and hair products. The conventional technique for scalp and hair treatment involves high operational cost and complicated diagnosis. Besides, it is becoming progressively important for the payer to investigate the value of new treatment selection in the management of a specific scalp problem. As they are generally expensive and inconvenient, there is an increasing need for an affordable and convenient way of monitoring scalp conditions. Thus, this paper presents a study of pre-trained classification of scalp conditions using image processing techniques. Initially, the scalp image went through the pre-processing such as image enhancement and greyscale conversion. Next, three features of color, texture, and shape were extracted from each input image, and stored in a Region of Interest (ROI) table. The knowledge of the values of the pre-trained features is used as a reference in the classification process subsequently. A technique of Support Vector Machine (SVM) is employed to classify the three types of scalp conditions which are alopecia areata (AA), dandruff and normal. A total of 120 images of the scalp conditions were tested. The classification of scalp conditions indicated a good performance of 85% accuracy. It is expected that the outcome of this study may automatically classify the scalp condition, and may assist the user on a selection of suitable treatment available.</span>

show abstract

Video based action detection and recognition human using optical flow and SVM classifier

Cited by 19 publications

References 9 publications

Design and Implementation of Improved Ensemble Classification Algorithm for Human Activity Recognition (Har)

Design and Implementation of Improved Ensemble Classification Algorithm for Human Activity Recognition (Har)

Hi-EADN: Hierarchical Excitation Aggregation and Disentanglement Frameworks for Action Recognition Based on Videos

Pre-trained classification of scalp conditions using image processing

Contact Info

Product

Resources

About