Motion history image: its variants and applications

Ahad, Md. Atiqur Rahman; Tan, Joo Kooi; Kim, H.; Ishikawa, Seiji

doi:10.1007/s00138-010-0298-4

Cited by 244 publications

(112 citation statements)

References 88 publications

Supporting

Mentioning

112

Contrasting

Order By: Relevance

“…Davis and Bobick [13] in their paper have presented the usage of temporal templates for recognizing human actions. References [7,14] have presented a detailed survey on human motion and behavior analysis using MHI and its variants. Other approaches like Optical Flow and Random Sample Consensus (RANSAC) by [8] decipher the representation and recognition technique of human actions.…”

Section: Literature Reviewmentioning

confidence: 99%

To detect abnormal event at ATM system by using image processing based on IOT technologies

Archana¹,

REDDY²

2018

IJET

View full text Add to dashboard Cite

Now a day' s ATMs are equipped with money there is possibility of robberies. This paper proposes a framework which will provide high security in ATMs. The Prototype includes ARM controller, Vibration Sensor, GSM and GPS Technique, DC Motor, Stepper motor, Buzz-er, LCD Display, and Keil Tool. Whenever robbery occurs, Vibration sensor is used here which senses vibration produced from ATM machine. This system uses ARM controller based embedded system to process real time data collected using the vibration sensor. Once the vibration is sensed the beep sound will occur from the buzzer. DC Motor is used for closing the door of ATM.Stepper motor is used to leak the gas inside the ATM to bring the thief into unconscious stage. Camera is always in processing and sending video continuous to the PC and it will be saved in computer. RTC used to capture the robber occur time and sends the SMS and MMS to the nearby police station and corresponding bank through the GSM and GPS. Here LCD displays board using showing the output of the message continuously. This will prevent the robbery and the person involving in robbery can be easily caught. Here, Keil tools are used to implement the idea and results are obtained. keil tools is used for run the DC motor and stepper motor for automatic door lock and also leak the gas inside the ATM. By this system robberies will be stopped and the complaints cases also reduced maximally. Thus the proposed framework results are revealed that the framework can be providing high security to the ATM System's

show abstract

Section: Literature Reviewmentioning

confidence: 99%

To detect abnormal event at ATM system by using image processing based on IOT technologies

Archana¹,

REDDY²

2018

IJET

View full text Add to dashboard Cite

show abstract

“…Its abilities for pose shape representation were demonstrated in [1,19]. The images are tiled using a six-by-six grid and the raw pixel values ([0,1]) are used to compute up to the third moment from each block.…”

Section: Histogram Of Oriented Gradients (Hog)mentioning

confidence: 99%

“…The set of modality trusts {w 1 Trust Normalization. Finally, the trusts are estimated with following equation:…”

Section: Trust Estimationmentioning

confidence: 99%

Sleep Pose Recognition in an ICU Using Multimodal Data and Environmental Feedback

Torres

Hammond

Fried

et al. 2015

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. Clinical evidence suggests that sleep pose analysis can shed light onto patient recovery rates and responses to therapies. In this work, we introduce a formulation that combines features from multimodal data to classify human sleep poses in an Intensive Care Unit (ICU) environment. As opposed to the current methods that combine data from multiple sensors to generate a single feature, we extract features independently. We then use these features to estimate candidate labels and infer a pose. Our method uses modality trusts -each modality's classification ability -to handle variable scene conditions and to deal with sensor malfunctions. Specifically, we exploit shape and appearance features extracted from three sensor modalities: RGB, depth, and pressure. Classification results indicate that our method achieves 100 % accuracy (outperforming previous techniques by 6 %) in bright and clear (ideal) scenes, 70 % in poorly illuminated scenes, and 90 % in occluded ones.

show abstract

“…Many approaches have been proposed for action recognition [1], [2]. However, many traditional methods usually depend on accurate actor segmentation, body tracking or interest point detection.…”

Section: Introductionmentioning

confidence: 99%

Learning a Similarity Constrained Discriminative Kernel Dictionary from Concatenated Low-Rank Features for Action Recognition

Huang

Wang

et al. 2016

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

SUMMARYTraditional low-rank feature lose the temporal information among action sequence. To obtain the temporal information, we split an action video into multiple action subsequences and concatenate all the low-rank features of subsequences according to their time order. Then we recognize actions by learning a novel dictionary model from concatenated low-rank features. However, traditional dictionary learning models usually neglect the similarity among the coding coefficients and have bad performance in dealing with non-linearly separable data. To overcome these shortcomings, we present a novel similarity constrained discriminative kernel dictionary learning for action recognition. The effectiveness of the proposed method is verified on three benchmarks, and the experimental results show the promising results of our method for action recognition.

show abstract

Motion history image: its variants and applications

Cited by 244 publications

References 88 publications

To detect abnormal event at ATM system by using image processing based on IOT technologies

To detect abnormal event at ATM system by using image processing based on IOT technologies

Sleep Pose Recognition in an ICU Using Multimodal Data and Environmental Feedback

Learning a Similarity Constrained Discriminative Kernel Dictionary from Concatenated Low-Rank Features for Action Recognition

Contact Info

Product

Resources

About