scholarly journals Application of Openpose algorithm to detect consumer behavior in store

2020 ◽  
Author(s):  
Jingjing Li ◽  
Jie Zeng ◽  
Keyu Hou ◽  
Jin Zhou ◽  
Rui Wang
Keyword(s):  
Consumer Behavior ◽  
Real Time ◽  
Video Analysis ◽  
Behavioral Data ◽  
Surveillance Video ◽  
Key Technology ◽  
Specific Process ◽  
Human Posture ◽  
The Right ◽  
Space Product

Due to the importance of offline consumer behavior, more and more people had begun to study consumer behavior in store. In offline consumer behavior research, the application of video analysis technology was the most direct and convenient. Recognizing human posture was a key technology in video analysis. The OpenPose algorithm was one of the advantageous technologies that could accurately recognize multi-person poses in different environments in real time, so we used it innovatively to study consumer behavior in store. We hope to develop the potential of this application in the research of consumer behavior in store in the footwear retail industry by the technical advantages of the OpenPose algorithm. In our study, we first used an OpenPose algorithm to estimate multi-person pose and detection behavior, and then processed and recognized the videos collected in the store. We collected a week's surveillance video of a Red Dragonfly offline store from July 10 to July 16, 2020 in China. The specific process was to calibrate the area in the selected camera screen, then the algorithm performs identification and detection, and finally output in-store consumption Behavioral data. Our research results not only verified the feasibility of this application in offline retailing stores, but the data results also indicated that consumers tend to enter the store from the right, staying concentrated in the middle and back of the store. These results may be affected by the store space, product display, and staff guidance and reception.

Techniques of Viral Marketing

2019 ◽  
Vol 118 (6) ◽  
pp. 97-99
Author(s):  
Arockia Jeyasheela A ◽  
Dr.S. Chandramohan
Keyword(s):  
Social Media ◽  
Real Time ◽  
Word Of Mouth ◽  
Viral Marketing ◽  
Consumer Perception ◽  
Key Word ◽  
The Right ◽  
A Company

This study is discussed about the viral marketing. It is a one of the key success of marketing. This paper gave the techniques of viral marketing. It can be delivered word of mouth. It can be created by both the representatives of a company and consumer (individuals or communities). The right viral message with go to right consumer to the right time. Viral marketing is easy to attract the consumer. It is most important advertising to consumer. It involves consumer perception, organization contribution, blogs, SMO (Social Media Optimize), SEO (Social Engine Optimize). Principles of viral marketing are social profile gathering, Proximity Market, Real time Key word density.

Real-time Worker Safety Management System Using Deep Learning-based Video Analysis Algorithm

2020 ◽  
Vol 9 (3) ◽  
pp. 25-30
Author(s):  
So Yeon Jeon ◽  
Jong Hwa Park ◽  
Sang Byung Youn ◽  
Young Soo Kim ◽  
Yong Sung Lee ◽  
...  
Keyword(s):  
Deep Learning ◽  
Real Time ◽  
Video Analysis ◽  
Management System ◽  
Safety Management ◽  
Worker Safety ◽  
Safety Management System ◽  
Analysis Algorithm

Acute detection of optical tissue changes in real-time during pulsed field ablation (PFA)

2020 ◽  
Vol 41 (Supplement_2) ◽  
Author(s):  
K.L Hong ◽  
O Amirana ◽  
T Ransbury ◽  
B Glover
Keyword(s):  
Real Time ◽  
Right Atrium ◽  
Optical Mapping ◽  
Energy Levels ◽  
Optical Signal ◽  
Lesion Formation ◽  
Pulsed Field ◽  
Tissue Changes ◽  
Rf Energy ◽  
The Right

Abstract Background It has been established in previous animal and human studies that it is possible to assess lesion formation in real-time using optical means during the application of radiofrequency (RF) energy in cardiac ablation procedures. The optical interrogation was accomplished using a novel catheter and instrument system whereby the catheter has embedded optical fibers that transmit and receive light from the instrument. Purpose The aim of this study was to see if there are similar indications of lesion formation, detected by the same optical means, during the application of pulsed field ablation (PFA) energy to cause lesions through electroporation. Methods A series of 3 anesthetized pigs underwent PFA in the right atrium. An 8-electrode circular catheter was placed high in the right atrium, near the superior vena cava, to simulate pulmonary vein isolation as part of an AF ablation procedure. The optical catheter was placed adjacent to the circular catheter between stimulation electrode pairs. A bolus of adenosine was administered to create a window of asystole to avoid stimulation on the T-wave. Bipolar PFA was delivered immediately post drug infusion and the optical signature from the catheter was recorded and displayed in real-time. Electrograms were recorded and the mapping of the lesion was performed with the optical catheter at the following time intervals post PFA delivery: 0 min, 15 min, 1 hour, and 3 hours. Necropsy and histology followed the procedure. Results The optical signal is distinctly higher in intensity during the PFA pulse train. The optical signal showed an immediate significant decrease and a slow but steady decay over the mapping interval. Electrogram reduction accompanied PFA application and also showed a marked reduction over the mapping interval. The optical signal amplitudes were markedly lower when on the lesion compared to healthy non-ablated myocardium as predicted. Conclusions Preliminary results indicate that optical mapping detects immediate tissue changes during PFA at these energy levels and hence could be is a viable method of evaluating lesion formation during and after PFA energy application. The optical signal indicates that cell damage occurs immediately at these energy levels and continues to progress slowly in lesions made by PFA energy compared to those made by RF energy. The findings also suggest that optical mapping can identify acute lesions made with PFA energy in real-time implying that optical mapping could evolve as a PFA gap detector. Funding Acknowledgement Type of funding source: None

scholarly journals A Probabilistic Model for Real-Time Semantic Prediction of Human Motion Intentions from RGBD-Data

Sensors ◽  
2021 ◽  
Vol 21 (12) ◽  
pp. 4141
Author(s):  
Wouter Houtman ◽  
Gosse Bijlenga ◽  
Elena Torta ◽  
René van de Molengraft
Keyword(s):  
Real Time ◽  
Collision Avoidance ◽  
Probabilistic Model ◽  
Real Life ◽  
Human Motion ◽  
Model Based ◽  
Multiple Hypotheses ◽  
Navigation Algorithms ◽  
The Right ◽  
Motion Behavior

For robots to execute their navigation tasks both fast and safely in the presence of humans, it is necessary to make predictions about the route those humans intend to follow. Within this work, a model-based method is proposed that relates human motion behavior perceived from RGBD input to the constraints imposed by the environment by considering typical human routing alternatives. Multiple hypotheses about routing options of a human towards local semantic goal locations are created and validated, including explicit collision avoidance routes. It is demonstrated, with real-time, real-life experiments, that a coarse discretization based on the semantics of the environment suffices to make a proper distinction between a person going, for example, to the left or the right on an intersection. As such, a scalable and explainable solution is presented, which is suitable for incorporation within navigation algorithms.

scholarly journals Near real time ETEM streaming video analysis

2017 ◽  
Author(s):  
Yuewei Lin ◽  
Dmitri Zakharov ◽  
Remi Megret ◽  
Shinjae Yoo ◽  
Eric Stach
Keyword(s):  
Real Time ◽  
Video Analysis ◽  
Streaming Video

EdgeDIPN

2020 ◽  
Vol 14 (3) ◽  
pp. 320-328
Author(s):  
Long Guo ◽  
Lifeng Hua ◽  
Rongfei Jia ◽  
Fei Fang ◽  
Binqiang Zhao ◽  
...  
Keyword(s):  
Real Time ◽  
Large Scale ◽  
Attention Mechanism ◽  
Data Sources ◽  
User Intent ◽  
Multiple User ◽  
Shopping Experience ◽  
Data Source ◽  
Intent Prediction ◽  
The Right

With the rapid growth of e-commerce in recent years, e-commerce platforms are becoming a primary place for people to find, compare and ultimately purchase products. To improve online shopping experience for consumers and increase sales for sellers, it is important to understand user intent accurately and be notified of its change timely. In this way, the right information could be offered to the right person at the right time. To achieve this goal, we propose a unified deep intent prediction network, named EdgeDIPN, which is deployed at the edge, i.e., mobile device, and able to monitor multiple user intent with different granularity simultaneously in real-time. We propose to train EdgeDIPN with multi-task learning, by which EdgeDIPN can share representations between different tasks for better performance and saving edge resources in the meantime. In particular, we propose a novel task-specific attention mechanism which enables different tasks to pick out the most relevant features from different data sources. To extract the shared representations more effectively, we utilize two kinds of attention mechanisms, where the multi-level attention mechanism tries to identify the important actions within each data source and the inter-view attention mechanism learns the interactions between different data sources. In the experiments conducted on a large-scale industrial dataset, EdgeDIPN significantly outperforms the baseline solutions. Moreover, EdgeDIPN has been deployed in the operational system of Alibaba. Online A/B testing results in several business scenarios reveal the potential of monitoring user intent in real-time. To the best of our knowledge, EdgeDIPN is the first full-fledged real-time user intent understanding center deployed at the edge and serving hundreds of millions of users in a large-scale e-commerce platform.

Sign in / Sign up

Export Citation Format

Share Document