Emerging Technologies in Object Detection, Tracking, and Localization

A special issue of Electronics (ISSN 2079-9292). This special issue belongs to the section "Computer Science & Engineering".

Deadline for manuscript submissions: closed (31 August 2023) | Viewed by 3780

Special Issue Editors

School of Automation, Northwestern Polytechnical University, Xi'an 710072, China
Interests: estimation and filtering; information fusion; target tracking; intelligent sensing; cooperative guidance; machine learning
Department of Electronic Engineering, Harbin Institute of Technology, Harbin 150001, China
Interests: estimation; tracking; detection; information fusion; signal processing
College of Electronics and Information Engineering, Shenzhen University, Shenzhen 518060, China
Interests: fuzzy information processing; target detection, localization and tracking; state estimation; particle filtering
School of Automation Science and Engineering, Faculty of Electronic and Information Engineering, Xi’an Jiaotong University, Xi’an 710049, China
Interests: target tracking; cooperative localization; distributed estimation fusion

Special Issue Information

Dear Colleagues,

Target detection, tracking, and localization (TDTL) aim to acquire the kinematic state (i.e., position and velocity) or other spatiotemporal characteristics of a single target or multiple targets based on the available sensory observations. Much effort has been dedicated to upgrading the TDTL techniques to maintain pace with the growing needs and increasing requirements of both military and civil applications. Such techniques are mainly model-based, since the observation data are relatively limited especially for the traditional radar tracking problems.

In recent years, there has been a move towards a new paradigm that combines model-based techniques with data-driven or machine learning inference algorithms. The background of such a move lies in the development of sensor technology and the application of large-scale heterogeneous senor networks. Benefiting from the thriving data science and artificial intelligence technology, TDTL is developing towards networking and collaboration. The advantage of this new paradigm is that the problems of TDTL are solved by capitalizing on both expert knowledge and learning solutions from massive data. Not only can it beat the traditional model-based techniques and enable more accurate results, but it also provides additional capabilities and flexibilities that are important to handle many TDTL problems.

This Special Issue will focus on the latest advances in intelligent TDTL techniques. Its core topics include artificial intelligence, machine learning, and TDTL techniques. Prospective authors are invited to submit their novel and original manuscripts about the theoretical underpinnings and the practical applications of these techniques. Potential topics of interest include, but are not limited to:

  • Signal detection, estimation, and filtering;
  • Nonparametric analysis of time series;
  • Mathematical optimization;
  • Advanced signal and information processing;
  • Machine learning and neural network approaches for TDTL;
  • Networked estimation and filtering;
  • Cooperative localization;
  • Cooperative tracking;
  • Simultaneous localization and target tracking;
  • Sensor fusion in navigation systems;
  • Bayesian target tracking;
  • Interesting applications to TDTL.

Dr. Linfeng Xu
Prof. Dr. Gongjian Zhou
Prof. Dr. Liangqun Li 
Dr. Yongxin Gao
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Electronics is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2400 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • signal detection
  • estimation and filtering
  • machine learning
  • neural network
  • cooperative localization
  • simultaneous localization and target tracking
  • information fusion
  • target tracking

Published Papers (3 papers)

Order results
Result details
Select all
Export citation of selected articles as:

Research

24 pages, 3923 KiB  
Article
Sensor Management with Dynamic Clustering for Bearings-Only Multi-Target Tracking via Swarm Intelligence Optimization
by Xiaoxiao Jiang, Tianming Ma, Jie Jin and Yujie Jiang
Electronics 2023, 12(16), 3397; https://doi.org/10.3390/electronics12163397 - 10 Aug 2023
Cited by 1 | Viewed by 720
Abstract
Sensor management is a crucial research subject for multi-sensor multi-target tracking in wireless sensor networks (WSNs) with limited resources. Bearings-only tracking produces further challenges related to high nonlinearity and poor observability. Moreover, energy efficiency and energy balancing should be considered for sensor management [...] Read more.
Sensor management is a crucial research subject for multi-sensor multi-target tracking in wireless sensor networks (WSNs) with limited resources. Bearings-only tracking produces further challenges related to high nonlinearity and poor observability. Moreover, energy efficiency and energy balancing should be considered for sensor management in WSNs, which involves networking and transmission. This paper formulates the sensor management problem in the partially observable Markov decision process (POMDP) framework and uses the cardinality-balanced multi-target multi-Bernoulli (CBMeMBer) filter for tracking. A threshold control method is presented to reduce the impact on tracking accuracy when using bearings-only measurements for sequential update. Moreover, a Cauchy–Schwarz divergence center is defined to construct a new objective function for efficiently finding the optimal sensor subset via swarm intelligence optimization. This is also conducive to dynamic clustering for the energy efficiency and energy balancing of the network. The simulation results illustrate that the proposed solution can achieve good tracking performance with less energy, and especially that it can effectively balance network energy consumption and prolong network lifetime. Full article
(This article belongs to the Special Issue Emerging Technologies in Object Detection, Tracking, and Localization)
Show Figures

Figure 1

13 pages, 2035 KiB  
Article
A Data-Efficient Training Method for Deep Reinforcement Learning
by Wenhui Feng, Chongzhao Han, Feng Lian and Xia Liu
Electronics 2022, 11(24), 4205; https://doi.org/10.3390/electronics11244205 - 16 Dec 2022
Viewed by 1285
Abstract
Data inefficiency is one of the major challenges for deploying deep reinforcement learning algorithms widely in industry control fields, especially in regard to long-horizon sparse reward tasks. Even in a simulation-based environment, it is often prohibitive to take weeks to train an algorithm. [...] Read more.
Data inefficiency is one of the major challenges for deploying deep reinforcement learning algorithms widely in industry control fields, especially in regard to long-horizon sparse reward tasks. Even in a simulation-based environment, it is often prohibitive to take weeks to train an algorithm. In this study, a data-efficient training method is proposed in which a DQN is used as a base algorithm, and an elaborate curriculum is designed for the agent in the simulation scenario to accelerate the training process. In the early stage of the training process, the distribution of the initial state is set close to the goal so the agent can obtain an informative reward easily. As the training continues, the initial state distribution is set farther from the goal for the agent to explore more state space. Thus, the agent can obtain a reasonable policy through fewer interactions with the environment. To bridge the sim-to-real gap, the parameters for the output layer of the neural network for the value function are fine-tuned. An experiment on UAV maneuver control is conducted in the proposed training framework to verify the method. We demonstrate that data efficiency is different for the same data in different training stages. Full article
(This article belongs to the Special Issue Emerging Technologies in Object Detection, Tracking, and Localization)
Show Figures

Figure 1

15 pages, 607 KiB  
Article
An Efficient Estimation Method for Dynamic Systems in the Presence of Inaccurate Noise Statistics
by Guanghua Zhang, Feng Lian, Xin Gao, Yinan Kong, Gong Chen and Shasha Dai
Electronics 2022, 11(21), 3548; https://doi.org/10.3390/electronics11213548 - 30 Oct 2022
Cited by 1 | Viewed by 1116
Abstract
The uncertainty of noise statistics in dynamic systems is one of the most important issues in engineering applications, and significantly affects the performance of state estimation. The optimal Bayesian Kalman filter (OBKF) is an important approach to solve this problem, as it is [...] Read more.
The uncertainty of noise statistics in dynamic systems is one of the most important issues in engineering applications, and significantly affects the performance of state estimation. The optimal Bayesian Kalman filter (OBKF) is an important approach to solve this problem, as it is optimal over the posterior distribution of unknown noise parameters. However, it is not suitable for online estimation because the posterior distribution of unknown noise parameters at each time is derived from its prior distribution by incorporating the whole measurement sequence, which is computationally expensive. Additionally, when the system is subjected to large disturbances, its response is slow and the estimation accuracy deteriorates. To solve the problem, we improve the OBKF mainly in two aspects. The first is the calculation of the posterior distribution of unknown noise parameters. We derive it from the posterior distribution at a previous time rather than the prior distribution at the initial time. Instead of the whole measurement sequence, only the nearest fixed number of measurements are used to update the posterior distribution of unknown noise parameters. Using the sliding window technique reduces the computational complexity of the OBKF and enhances its robustness to jump noise. The second aspect is the estimation of unknown noise parameters. The posterior distribution of an unknown noise parameter is represented by a large number of samples by the Markov chain Monte Carlo approach. In the OBKF, all samples are equivalent and the noise parameter is estimated by averaging the samples. In our approach, the weights of samples, which are proportional to their likelihood function values, are taken into account to improve the estimation accuracy of the noise parameter. Finally, simulation results show the effectiveness of the proposed method. Full article
(This article belongs to the Special Issue Emerging Technologies in Object Detection, Tracking, and Localization)
Show Figures

Figure 1

Back to TopTop