Tracking Video Target via Particle Filtering on Manifold

Ge, Huilin; Zhu, Zhiyu; Lou, Kang

doi:10.5755/j01.itc.48.4.23939

Cited by 8 publications

(4 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…OMP-SGD combines the advantages of OMP and SGD to build a single model to optimize prediction performance [ 41 , 42 , 43 ]. The operation of the algorithm is as follows: firstly, the initial matrix of OMP is established, and then the SGD, with the goal of reducing the residual value of OMP established.…”

Section: Methodsmentioning

confidence: 99%

Development of a Check-All-That-Apply (CATA) Ballot and Machine Learning for Generation Z Consumers for Innovative Traditional Food

Wang

Shen

Zhao

et al. 2022

Foods

View full text Add to dashboard Cite

Generation Z (Gen Z) consumers account for an increasing proportion of the food market. The aim of this study took lamb shashliks as an example and developed novel products from the perspective of cooking methods in order to develop a traditional food suitable for Gen Z consumers. The sensory characterization of electric heating air (EH), microwave heating (MH), air frying (AF), and control (traditional burning charcoal (BC) of lamb shashliks) was performed using the CATA methodology with 120 Gen Z consumers as assessors. A 9-point hedonic scale was used to evaluate Gen Z consumers’ preferences for the cooking method, as well as a CATA ballot with 46 attributes which described the sensory characteristics of lamb shashliks. The machine learning algorithms were used to identify consumer preferences for different cooking methods of lamb shashliks as a function of sensory attributes and assessed the relationship between products and attributes present in the perceptual map for the degree of association. Meanwhile, sensory attributes as important variables play a relatively more important role in each cooking method. The most important variables for sensory attributes of lamb shashliks using BC are char-grilled aroma and smoky flavor. Similarly, the most important variables for AF samples are butter aroma, intensity aroma, and intensity aftertaste, the most important variables for EH samples are dry texture and hard texture, and the most important variables for MH samples are light color regarding external appearance and lumpy on chewing texture. The interviews were conducted with Gen Z consumers to investigate why they prefer innovative products—AF. Grounded theory and the social network analysis (SNA) method were utilized to explore why consumers chose AF, demonstrating that Gen Z consumers who had previously tasted AF lamb shashliks could easily perceive the buttery aroma. This study provides a theoretical and practical basis for developing lamb shashliks tailored to Gen Z consumers.

show abstract

Section: Methodsmentioning

confidence: 99%

Development of a Check-All-That-Apply (CATA) Ballot and Machine Learning for Generation Z Consumers for Innovative Traditional Food

Wang

Shen

Zhao

et al. 2022

Foods

View full text Add to dashboard Cite

show abstract

“…It is a typical algorithm for forming a margin's boundary. The ideal hyperplane is to represent the largest separation (or margin) between different classes [93]. The partitions between classes of normal activities have also been learned using kernel SVM [104,120].…”

Section: Refmentioning

confidence: 99%

Abnormal Human Behavior Detection in Videos: A Review

Sun

Yuan

et al. 2021

ITC

View full text Add to dashboard Cite

Modeling human behavior patterns for detecting the abnormal event has become an important domain in recentyears. A lot of efforts have been made for building smart video surveillance systems with the purpose ofscene analysis and making correct semantic inference from the video moving target. Current approaches havetransferred from rule-based to statistical-based methods with the need of efficient recognition of high-levelactivities. This paper presented not only an update expanding previous related researches, but also a study coveredthe behavior representation and the event modeling. Especially, we provided a new perspective for eventmodeling which divided the methods into the following subcategories: modeling normal event, predictionmodel, query model and deep hybrid model. Finally, we exhibited the available datasets and popular evaluationschemes used for abnormal behavior detection in intelligent video surveillance. More researches will promotethe development of abnormal human behavior detection, e.g. deep generative network, weakly-supervised. It isobviously encouraged and dictated by applications of supervising and monitoring in private and public space.The main purpose of this paper is to widely recognize recent available methods and represent the literature ina way of that brings key challenges into notice.

show abstract

“…SGD can be used for image processing applications as it uses the backpropagation to converge quickly using local minima. This enables tracking algorithms such as particle filters to track the object in an efficient manner by quickly converging towards the object of interest [ 22 , 23 , 24 , 25 ].…”

Section: Introductionmentioning

confidence: 99%

Tracking of a Fixed-Shape Moving Object Based on the Gradient Descent Method

Masood

Zafar

Ali

et al. 2022

Sensors

View full text Add to dashboard Cite

Tracking moving objects is one of the most promising yet the most challenging research areas pertaining to computer vision, pattern recognition and image processing. The challenges associated with object tracking range from problems pertaining to camera axis orientations to object occlusion. In addition, variations in remote scene environments add to the difficulties related to object tracking. All the mentioned challenges and problems pertaining to object tracking make the procedure computationally complex and time-consuming. In this paper, a stochastic gradient-based optimization technique has been used in conjunction with particle filters for object tracking. First, the object that needs to be tracked is detected using the Maximum Average Correlation Height (MACH) filter. The object of interest is detected based on the presence of a correlation peak and average similarity measure. The results of object detection are fed to the tracking routine. The gradient descent technique is employed for object tracking and is used to optimize the particle filters. The gradient descent technique allows particles to converge quickly, allowing less time for the object to be tracked. The results of the proposed algorithm are compared with similar state-of-the-art tracking algorithms on five datasets that include both artificial moving objects and humans to show that the gradient-based tracking algorithm provides better results, both in terms of accuracy and speed.

show abstract

Tracking Video Target via Particle Filtering on Manifold

Cited by 8 publications

References 15 publications

Development of a Check-All-That-Apply (CATA) Ballot and Machine Learning for Generation Z Consumers for Innovative Traditional Food

Development of a Check-All-That-Apply (CATA) Ballot and Machine Learning for Generation Z Consumers for Innovative Traditional Food

Abnormal Human Behavior Detection in Videos: A Review

Tracking of a Fixed-Shape Moving Object Based on the Gradient Descent Method

Contact Info

Product

Resources

About