Unsupervised discovery of crowd activities by saliency-based clustering

Han, Tingting; Yao, Hongxun; Sun, Xingming; Zhao, Sicheng; Zhang, Yanhao

doi:10.1016/j.neucom.2015.06.048

Cited by 13 publications

(6 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Among a range of practical applications, supervised machine learning has been used to predict customer behavior [162,163], differentiate cells of different histologies [164,165] and recognize faces [166,167]. With unsupervised machine learning, the algorithm seeks to cluster entities based upon some discoverable property of the entities, for example, grouping anonymous individuals within a large crowd based upon biometric or acquired physical variables [168,169].…”

Section: Advances In Software Algorithms: Piloting the Ai Ecosystemmentioning

confidence: 99%

Leveraging the Academic Artificial Intelligence Silecosystem to Advance the Community Oncology Enterprise

McDonnell

2023

JCM

View full text Add to dashboard Cite

Over the last 75 years, artificial intelligence has evolved from a theoretical concept and novel paradigm describing the role that computers might play in our society to a tool with which we daily engage. In this review, we describe AI in terms of its constituent elements, the synthesis of which we refer to as the AI Silecosystem. Herein, we provide an historical perspective of the evolution of the AI Silecosystem, conceptualized and summarized as a Kuhnian paradigm. This manuscript focuses on the role that the AI Silecosystem plays in oncology and its emerging importance in the care of the community oncology patient. We observe that this important role arises out of a unique alliance between the academic oncology enterprise and community oncology practices. We provide evidence of this alliance by illustrating the practical establishment of the AI Silecosystem at the City of Hope Comprehensive Cancer Center and its team utilization by community oncology providers.

show abstract

Section: Advances In Software Algorithms: Piloting the Ai Ecosystemmentioning

confidence: 99%

Leveraging the Academic Artificial Intelligence Silecosystem to Advance the Community Oncology Enterprise

McDonnell

2023

JCM

View full text Add to dashboard Cite

show abstract

“…One category clusters pedestrians based on different motion patterns of crowds [27] , [28] , [29] , [30] , [31] , [32] , with wide applications in medium and high-density crowd scenes, such as crowd flow monitoring and crowd behaviour analysis. For example, Shao et al [27] adopted a robust group detection algorithm and a rich set of group-property visual descriptors through learning the collective transition prior; they then utilised visual descriptors to quantify group-level properties for crowd understanding [28] .…”

Section: Related Workmentioning

confidence: 99%

“…Chen et al [29] proposed an anchor-based manifold ranking (AMR) method to classify individuals into local clusters according to topological relationship to the anchors, and exploited a coherent merging strategy to recognise global consistency in crowed scenes. Wang et al [30] designed a multi-view clustering method for group detection by combining the orientation and context similarities of feature points, whereas Han et al [31] developed a crowd activity discovery algorithm to explore latent action patterns among crowd activities and clustering them. Considering that scene context can promote clustering, Zhang et al [32] incorporated scene information to present a scene perception-guided clustering strategy, and they fully utilised various attributes of the pedestrians to make the clustering process more reasonable.…”

Section: Related Workmentioning

confidence: 99%

A new approach for social group detection based on spatio-temporal interpersonal distance measurement

Su¹,

Huang²,

Qing

et al. 2022

Heliyon

View full text Add to dashboard Cite

“…Researchers usually focus on the longitudinal automatic landing, but few scholars research the lateral landing system. For example, Lungu et al combine neural network and dynamic inverse to establish a horizontal ACLS, which could automatically manipulate the aircraft lineup with the trajectory (Lungu and Lungu, 2016). A lateral-directional ACLS is developed based on dynamic inversion, a neural network and a Pseudo Control Hedging block (Lungu and Lungu, 2018).…”

Section: Introductionmentioning

confidence: 99%

“…Guidance signals in lateral direction are generated based on deck motion compensation for pilots during landing, which inspired design of ACLS control law (Chen et al , 2017). NDI and H-∞ are used to establish an automatic landing system in lateral direction (Lungu and Lungu, 2016), which can reduce disturbances and provide the precision tracking performance. A new automatic control system is developed by H-∞ control and dynamic inversion approach (Lungu and Lungu, 2015).…”

Section: Introductionmentioning

confidence: 99%

Lateral autonomous carrier-landing control with high-dimension landing risks consideration

Wang

Zhang

Zhu

et al. 2020

AEAT

View full text Add to dashboard Cite

Purpose This paper aims to propose a novel model predictive control (MPC) with time varying weights to develop a lateral control law in an automatic carrier landing system (ACLS), which minimizes landing risk and improves flight quality. Design/methodology/approach First, a nonlinear mathematic model of an F/A-18 aircraft during lateral landing is established. Then the landing model is linearized in the form of state deviations on the equilibrium points. Second, landing risk windows are proposed and a high-dimensional landing risk model is addressed through a back propagation (BP) neural network. The trained samples are acquired based on a pilot behavior model. Third, time varying weights created from the lateral landing risk are introduced into the performance function of MPC. Optimal solution is solved quicker and some state deviations are focused on and eliminated. Fourth, the algebraic inequalities are substituted by the linear matrix inequalities (LMIs), which are easily calculated by the computers. Findings On a semi-physical platform, the proposed method compares with a traditional MPC algorithm and a modified MPC with an additional term. The test results indicate that the proposed algorithm brings about an excellent landing performance as well as an ability of eliminating landing risk. Practical implications The landing phase of a carrier-based aircraft is one of the most dangerous and complicated stages, and the algorithm proposed by this paper plays a vital role in the lateral landing. Originality/value This paper establishes a lateral landing risk model, which considers not only the current landing state but also the future touchdown point. This lateral landing risk is integrated into the time varying weights of the MPC algorithm so that the state deviations and landing risk can be both reduced in the rolling optimization.

show abstract

Unsupervised discovery of crowd activities by saliency-based clustering

Cited by 13 publications

References 45 publications

Leveraging the Academic Artificial Intelligence Silecosystem to Advance the Community Oncology Enterprise

Leveraging the Academic Artificial Intelligence Silecosystem to Advance the Community Oncology Enterprise

A new approach for social group detection based on spatio-temporal interpersonal distance measurement

Lateral autonomous carrier-landing control with high-dimension landing risks consideration

Contact Info

Product

Resources

About