A hybrid occlusion free object tracking method using particle filter and modified galaxy based search meta-heuristic algorithm

Sardari, Faegheh; Moghaddam, Mohsen Ebrahimi

doi:10.1016/j.asoc.2016.11.028

Cited by 27 publications

(10 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Video target trackers in category 2 of the classification given in [ 14 ] based on SIAs work as follows: In each frame,

particles are scattered at random within the solution space given by

where

and

are the total pixels of the horizontal and vertical dimensions of the frame, respectively.…”

Section: Architecturementioning

confidence: 99%

“…Tracker models can be classified into two categories according to [ 14 ]: Category 1 whose models are based on stochastic algorithms. These algorithms are used to predict the position of the target in each frame according to a pattern of movement and observable characteristics of the target.…”

Section: Introductionmentioning

confidence: 99%

“…It is worth mentioning that many authors have proposed the use of SIA to optimize the trackers based on PF algorithm [ 14 , 24 , 25 ]. Furthermore, in recent years, great progress and importance have been given to trackers based on Correlation Filter (CF) [ 26 , 27 , 28 ] and Deep Learning (DL) [ 29 , 30 , 31 ] due to the good results in visual tracking.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A New Approach to Enhanced Swarm Intelligence Applied to Video Target Tracking

Castro

Salles

Ciarelli

2021

Sensors

View full text Add to dashboard Cite

This work proposes a new approach to improve swarm intelligence algorithms for dynamic optimization problems by promoting a balance between the transfer of knowledge and the diversity of particles. The proposed method was designed to be applied to the problem of video tracking targets in environments with almost constant lighting. This approach also delimits the solution space for a more efficient search. A robust version to outliers of the double exponential smoothing (DES) model is used to predict the target position in the frame delimiting the solution space in a more promising region for target tracking. To assess the quality of the proposed approach, an appropriate tracker for a discrete solution space was implemented using the meta-heuristic Shuffled Frog Leaping Algorithm (SFLA) adapted to dynamic optimization problems, named the Dynamic Shuffled Frog Leaping Algorithm (DSFLA). The DSFLA was compared with other classic and current trackers whose algorithms are based on swarm intelligence. The trackers were compared in terms of the average processing time per frame and the area under curve of the success rate per Pascal metric. For the experiment, we used a random sample of videos obtained from the public Hanyang visual tracker benchmark. The experimental results suggest that the DSFLA has an efficient processing time and higher quality of tracking compared with the other competing trackers analyzed in this work. The success rate of the DSFLA tracker is about 7.2 to 76.6% higher on average when comparing the success rate of its competitors. The average processing time per frame is about at least 10% faster than competing trackers, except one that was about 26% faster than the DSFLA tracker. The results also show that the predictions of the robust DES model are quite accurate.

show abstract

“…Video target trackers in category 2 of the classification given in [ 14 ] based on SIAs work as follows: In each frame,

particles are scattered at random within the solution space given by

where

and

are the total pixels of the horizontal and vertical dimensions of the frame, respectively.…”

Section: Architecturementioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A New Approach to Enhanced Swarm Intelligence Applied to Video Target Tracking

Castro

Salles

Ciarelli

2021

Sensors

View full text Add to dashboard Cite

show abstract

“…Besides, the task scheduling of cloud platform is complex and frequent. Heuristic algorithm can offer a feasible solution to living example of combination optimization problem to be solved at reasonable cost [35]. However, owing to the complex and dynamic environment of cloud platform, it is very slow to search the optimal combination.…”

Section: A Scheduling Control Enginementioning

confidence: 99%

AI-Powered Green Cloud and Data Center

et al. 2019

View full text Add to dashboard Cite

As the scale of cloud computing expands, its impact on energy and the environment is becoming more and more prominent. According to statistics, data centers' energy consumption has accounted for 50% of operating costs of the data centers. The rising energy consumption not only needs energy in large quantity but also imposes heavy pressure on the environment. The high energy consumption of cloud data center has become an issue, people pay close attention to, in the information technology field. It is also a problem to be solved urgently. At present, high energy consumption is caused by two reasons. First, a resource scheduling mechanism with the priority of completion time causes low server use ratio, and it is a pervasive phenomenon that small tasks take high consumption. Second, the current refrigerating system of the data center is based on peak value strategy, which causes excessive cooling supply, increases operation cost, and leads to huge waste of energy. In this paper, considering the reason of high energy consumption of the data center, a new framework of green cloud data center is put forward. Using the techniques relevant to artificial intelligence, we put forward a scheduling control engine and an intelligent refrigerating engine aiming at reduction of energy consumption. In addition, we build a green cloud data center platform, realize the scheduling control engine, and verify the feasibility of the framework. It indicates that the framework can realize a cloud platform with low power consumption and a high-energy-efficient data center operation. INDEX TERMS Green cloud and data center, energy optimizing, deep learning, particle swarm optimization.

show abstract

“…It is difficult to coordinate and cause it to suffer significant losses. In recent years, due to the impact of risk events occurred in a series of supply chain disruptions, the global economy has been a huge loss [9]. This paper analyzes how the supply chain enterprises to risk management, highlighting the supply chain risk management and traditional risk management of the difference.…”

mentioning

confidence: 99%