Research

Jump to: Other

17 pages, 2701 KiB

Open AccessArticle

MS Location Estimation Based on the Artificial Bee Colony Algorithm

by Chien-Sheng Chen, Jen-Fa Huang, Nan-Chun Huang and Kai-Sheng Chen

Sensors 2020, 20(19), 5597; https://doi.org/10.3390/s20195597 - 29 Sep 2020

Cited by 2 | Viewed by 2102

With the mature technology of wireless communications, the function of estimating the mobile station (MS) position has become essential. Suppressing the bias resulting from non-line-of-sight (NLSO) scenarios is the main issue for a wireless location network. The artificial bee colony (ABC) algorithm, based [...] Read more.

With the mature technology of wireless communications, the function of estimating the mobile station (MS) position has become essential. Suppressing the bias resulting from non-line-of-sight (NLSO) scenarios is the main issue for a wireless location network. The artificial bee colony (ABC) algorithm, based on the depiction of bee swarm’s foraging characteristics, is widely applied to solve optimization problems in several fields. Based on three measurements of time-of-arrival (TOA), an objective function is used to quantify the additional NLOS error on the MS positioning scheme. The ABC algorithm is adopted to locate the most precise MS location by minimizing the objective function value. The performance of the proposed positioning methods is verified under various error distributions through computer simulations. Meanwhile, the localization accuracy achieved by other existing methods is also investigated. According to the simulation results, accurate estimation of the MS position is derived and therefore the efficiency of the localization process is increased. Full article

(This article belongs to the Special Issue Sensors for Multiple Object Tracking)

► Show Figures

Figure 1

Other

Jump to: Research

12 pages, 2167 KiB

Open AccessLetter

SNS-CF: Siamese Network with Spatially Semantic Correlation Features for Object Tracking

by Thierry Ntwari, Hasil Park, Joongchol Shin and Joonki Paik

Sensors 2020, 20(17), 4881; https://doi.org/10.3390/s20174881 - 28 Aug 2020

Cited by 2 | Viewed by 1994

Abstract

Recent advances in object tracking based on deep Siamese networks shifted the attention away from correlation filters. However, the Siamese network alone does not have as high accuracy as state-of-the-art correlation filter-based trackers, whereas correlation filter-based trackers alone have a frame update problem. [...] Read more.

Recent advances in object tracking based on deep Siamese networks shifted the attention away from correlation filters. However, the Siamese network alone does not have as high accuracy as state-of-the-art correlation filter-based trackers, whereas correlation filter-based trackers alone have a frame update problem. In this paper, we present a Siamese network with spatially semantic correlation features (SNS-CF) for accurate, robust object tracking. To deal with various types of features spread in many regions of the input image frame, the proposed SNS-CF consists of—(1) a Siamese feature extractor, (2) a spatially semantic feature extractor, and (3) an adaptive correlation filter. To the best of authors knowledge, the proposed SNS-CF is the first attempt to fuse the Siamese network and the correlation filter to provide high frame rate, real-time visual tracking with a favorable tracking performance to the state-of-the-art methods in multiple benchmarks. Full article

(This article belongs to the Special Issue Sensors for Multiple Object Tracking)

► Show Figures

Graphical abstract

13 pages, 3872 KiB

Open AccessLetter

Enhanced Action Recognition Using Multiple Stream Deep Learning with Optical Flow and Weighted Sum

by Hyunwoo Kim, Seokmok Park, Hyeokjin Park and Joonki Paik

Sensors 2020, 20(14), 3894; https://doi.org/10.3390/s20143894 - 13 Jul 2020

Cited by 5 | Viewed by 3022

Abstract

Various action recognition approaches have recently been proposed with the aid of three-dimensional (3D) convolution and a multiple stream structure. However, existing methods are sensitive to background and optical flow noise, which prevents from learning the main object in a video frame. Furthermore, [...] Read more.

Various action recognition approaches have recently been proposed with the aid of three-dimensional (3D) convolution and a multiple stream structure. However, existing methods are sensitive to background and optical flow noise, which prevents from learning the main object in a video frame. Furthermore, they cannot reflect the accuracy of each stream in the process of combining multiple streams. In this paper, we present a novel action recognition method that improves the existing method using optical flow and a multi-stream structure. The proposed method consists of two parts: (i) optical flow enhancement process using image segmentation and (ii) score fusion process by applying weighted sum of the accuracy. The enhancement process can help the network to efficiently analyze the flow information of the main object in the optical flow frame, thereby improving accuracy. A different accuracy of each stream can be reflected to the fused score while using the proposed score fusion method. We achieved an accuracy of 98.2% on UCF-101 and 82.4% on HMDB-51. The proposed method outperformed many state-of-the-art methods without changing the network structure and it is expected to be easily applied to other networks. Full article

(This article belongs to the Special Issue Sensors for Multiple Object Tracking)

► Show Figures

Figure 1

Journal Menu

Journal Browser

Sensors for Multiple Object Tracking

Share This Special Issue

Special Issue Editor

Special Issue Information

Keywords

Published Papers (3 papers)

Research

Other

Further Information

Guidelines

MDPI Initiatives

Follow MDPI