A hybrid gravitational search algorithm with swarm intelligence and deep convolutional feature for object tracking optimization

Kang, Kyuchang; Bae, Changseok; Yeung, Henry Wing Fung; Chung, Yuk Ying

doi:10.1016/j.asoc.2018.02.037

Cited by 34 publications

(8 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Bat algorithm is a novel population-based evolutionary (Cai et al, 2018) and bio-inspired stochastic optimisation algorithm (Cai et al, 2016;Cui et al, 2017) and cuckoo search is a recently developed meta-heuristic (Zhang et al, 2018). These algorithms have also been applied in object tracking (Gao et al, 2016;Kang et al, 2018). Due to their high computation overhead and long processing time, these methods are very difficult to be deployed in real-time systems.…”

Section: Object Detection and People Countingmentioning

confidence: 99%

A novel squeeze YOLO-based real-time people counting approach

Ren¹,

Wang²,

Fang³

et al. 2020

IJBIC

View full text Add to dashboard Cite

Real-time people counting based on videos is one of the most popular projects in the construction of smart cities. To develop an accurate people counting approach, deep learning can be used as it greatly improves the accuracy of machine learning-based approaches. To this end, we have previously proposed an accurate you only look once (YOLO)-based people counting approach, dubbed YOLO-PC. However, the model of YOLO-PC was very large with an excessive number of parameters, thus it requires large storage space on the device and makes transmission on internet a time consuming task. In this paper, a new real-time people counting method named as squeeze YOLO-based people counting (S-YOLO-PC) is proposed. S-YOLO-PC uses the fire layer of SqueezeNet to optimise the network structure, which reduces the number of parameters used in the model without decreasing its accuracy. Based on the obtained the experimental results, S-YOLO-PC reduces the number of model parameters by 11.5% and 9% compared to YOLO and YOLO-PC, respectively. S-YOLO-PC can also detect and count people with 41 frames per second (FPS) with the average precision (AP) of person of 72%.

show abstract

Section: Object Detection and People Countingmentioning

confidence: 99%

A novel squeeze YOLO-based real-time people counting approach

Ren¹,

Wang²,

Fang³

et al. 2020

IJBIC

View full text Add to dashboard Cite

show abstract

“…Common visual features used in target tracking, including colour, grayscale, derivative histogram, optical flow, texture, and key points, are prone to failure in confusingly similar-looking backgrounds. This problem will not be eradicated if no additional information source for the target tracking is introduced (Hu et al, 2017;Kang et al, 2018;Guan et al, 2020). In the field of computer vision, depth information refers to the position information of the target in the direction perpendicular to the image plane, which cannot be obtained by traditional monocular cameras.…”

Section: Introductionmentioning

confidence: 99%

Introducing Depth Information Into Generative Target Tracking

et al. 2021

View full text Add to dashboard Cite

Common visual features used in target tracking, including colour and grayscale, are prone to failure in a confusingly similar-looking background. As the technology of three-dimensional visual information acquisition has gradually gained ground in recent years, the conditions for the wide use of depth information in target tracking has been made available. This study focuses on discussing the possible ways to introduce depth information into the generative target tracking methods based on a kernel density estimation as well as the performance of different methods of introduction, thereby providing a reference for the use of depth information in actual target tracking systems. First, an analysis of the mean-shift technical framework, a typical algorithm used for generative target tracking, is described, and four methods of introducing the depth information are proposed, i.e., the thresholding of the data source, thresholding of the density distribution of the dataset applied, weighting of the data source, and weighting of the density distribution of the dataset. Details of an experimental study conducted to evaluate the validity, characteristics, and advantages of each method are then described. The experimental results showed that the four methods can improve the validity of the basic method to a certain extent and meet the requirements of real-time target tracking in a confusingly similar background. The method of weighting the density distribution of the dataset, into which depth information is introduced, is the prime choice in engineering practise because it delivers an excellent comprehensive performance and the highest level of accuracy, whereas methods such as the thresholding of both the data sources and the density distribution of the dataset are less time-consuming. The performance in comparison with that of a state-of-the-art tracker further verifies the practicality of the proposed approach. Finally, the research results also provide a reference for improvements in other target tracking methods in which depth information can be introduced.

show abstract

“…SI has been used for object tracking in a few works [25,26], but as far as we know, the parallelized SI algorithms have been mostly tested with benchmarking functions, and less frequently used for object tracking [27]. This work uses the unique combination of: NCC as the tracker function, the HSA for heuristic search, and a GPU for hardware acceleration.…”

Section: Introductionmentioning

confidence: 99%

Parallelization of the Honeybee Search Algorithm for Object Tracking

Perez-Cham

Puente

Soubervielle‐Montalvo

et al. 2020

Applied Sciences

View full text Add to dashboard Cite

Object tracking refers to the relocation of specific objects in consecutive frames of a video sequence. Presently, this visual task is still considered an open research issue, and the computer science community attempted solutions from the standpoint of methodologies, algorithms, criteria, benchmarks, and so on. This article introduces a GPU-parallelized swarm algorithm, called the Honeybee Search Algorithm (HSA), which is a hybrid algorithm combining swarm intelligence and evolutionary algorithm principles, and was previously designed for three-dimensional reconstruction. This heuristic inspired by the search for food of honeybees, and here adapted to the problem of object tracking using GPU parallel computing, is extended from the original proposal of HSA towards video processing. In this work, the normalized cross-correlation (NCC) criteria is used as the fitness function. Experiments using 314 video sequences of the ALOV benchmark provides evidence about the quality regarding tracking accuracy and processing time. Also, according to these experiments, the proposed methodology is robust to high levels of Gaussian noise added to the image frames, and this confirms that the accuracy of the original NCC is preserved with the advantage of acceleration, offering the possibility of accelerating latest trackers using this methodology.

show abstract

A hybrid gravitational search algorithm with swarm intelligence and deep convolutional feature for object tracking optimization

Cited by 34 publications

References 25 publications

A novel squeeze YOLO-based real-time people counting approach

A novel squeeze YOLO-based real-time people counting approach

Introducing Depth Information Into Generative Target Tracking

Parallelization of the Honeybee Search Algorithm for Object Tracking

Contact Info

Product

Resources

About