Recent Applications of Object Detection, Tracking, and Abnormal Detection Based on AI

A special issue of Electronics (ISSN 2079-9292). This special issue belongs to the section "Bioelectronics".

Deadline for manuscript submissions: closed (30 June 2022) | Viewed by 2389

Special Issue Editors

School of Computer Science, University of Lincoln, Lincoln LN6 7TS, UK
Interests: machine learning; statistical signal processing; image/video processing; knowledge extraction and modelling

E-Mail Website1 Website2
Guest Editor
School of Computer Science, University of Lincoln, Lincoln LN6 7TS, UK
Interests: image and video processing, analysis, coding, storage, retrieval; multimedia systems; computer graphics and virtual reality; artificial intelligence; neural networks; human–computer interaction; medical imaging
Special Issues, Collections and Topics in MDPI journals

E-Mail Website
Guest Editor
School of Computer Science, University of Lincoln, Lincoln LN6 7TS, UK
Interests: medical image analysis; multimodal brain image analysis; image segmentation; computer-aided detection (CAD); computer vision; pattern recognition
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

Modern AI techniques have been dramatically developed in recent decades and widely applied in a variety of application areas, permeating every aspect of a person’s daily life. One important application area of modern AI techniques is object detection, tracking, and abnormal detection. A variety of signal processing and machine learning—especially deep learning—technologies have been developed for object detection and the tracking and detection of abnormalities based on different sensor modality recordings (including but not limited to vision sensors, acoustic sensors, accelerometers/gyroscope sensors, etc.) in different areas (such as healthcare, agriculture, robotics, energy, surveillance, and so on).

The main aim of this Special Issue is to seek high-quality submissions that highlight emerging applications and address recent breakthroughs in modern signal processing, machine learning, and deep learning techniques for object detection/tracking and abnormal detection. The topics of interest include but are not limited to:

  • ML/DL algorithm development and applications for object detection/tracking and abnormal detection in healthcare/robotics/agriculture/surveillance/energy;
  • Multimodal information fusion for object detection/tracking and abnormal detection;
  • Signal processing algorithms for object tracking;
  • Combining application specific domain knowledge and data-driven approaches for object detection/tracking and abnormal detection;
  • Uncertainty estimations for object detection/tracking and abnormal detection algorithms;
  • Multiple-sensor-based object detection/tracking and abnormal detection.

Dr. Miao Yu
Prof. Dr. Stefanos Kollias
Prof. Dr. Xujiong Ye
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

  • object detection
  • object tracking
  • abnormal detection
  • machine learning
  • signal processing
  • deep learning
  • information fusion

Published Papers (1 paper)

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

Research

16 pages, 6571 KiB  
Article
Active Mask-Box Scoring R-CNN for Sonar Image Instance Segmentation
by Fangjin Xu, Jianxing Huang, Jie Wu and Longyu Jiang
Electronics 2022, 11(13), 2048; https://doi.org/10.3390/electronics11132048 - 29 Jun 2022
Cited by 6 | Viewed by 1524
Abstract
Instance segmentation of sonar images is an effective method for underwater target recognition. However, the mismatch among positioning accuracy found by boxIoU and classification confidence, which is used as NMS score in current instance segmentation models; and the high annotation cost of sonar [...] Read more.
Instance segmentation of sonar images is an effective method for underwater target recognition. However, the mismatch among positioning accuracy found by boxIoU and classification confidence, which is used as NMS score in current instance segmentation models; and the high annotation cost of sonar images, are two major problems in the task. To tackle these problems, in this paper, we present a novel instance segmentation method called Mask-Box Scoring R-CNN and embedded it in our proposed deep active learning framework. For the mismatch problem between boxIoU and NMS score, Mask-Box Scoring R-CNN uses a boxIoU head to predict the quality of the bounding boxes. We amend the non-maximum suppression (NMS) score predicted by BoxIoU to preserve high-quality bounding boxes in inference flow. To deal with the annotating problem, we propose a triplets-measure-based active learning (TBAL) method and a balanced-sampling method applicable for deep learning. The TBAL method evaluates the amount of information of unlabeled samples from the aspects of classification confidence, positioning accuracy, and mask quality. The balanced-sampling method selects hard samples from the dataset to train the model to improve performance. The experimental results show that Mask-Box Scoring R-CNN achieves improvements of 1% in boxAP and 1.3% boxAP on our sonar image dataset compared with Mask Scoring R-CNN and Mask R-CNN, respectively. The active learning framework with TBAL and balanced sampling can achieve a competitive performance with less labeled samples than other frameworks, which can better facilitate underwater target recognition. Full article
Show Figures

Figure 1

Back to TopTop