Object Detection During Newborn Resuscitation Activities.

The development of underwater vehicles has opportunity to be further improved. One of the most challenging for developing underwater vehicle is developing automatic tracking system for Autonomous Underwater Vehicle (AUV). This research develops AUV with automatic object detection and tracking systems. These systems are developed by using vision-based method. The AUV is designed with Penta Tubular type whereas the automatic object detection system is started from captured image taken by underwater camera in the form of Blue-Green-Red (BGR) color space, which then will go through a masking process. The object resulted by object detection system is then to be used as followed object for automatic tracking system. Meanwhile, Automatic object tracking system is established by using two vertical lines that are used as motion parameters of the AUV. By considering the object position compared with the two vertical lines, the automatic tracking guidance system can be generated. The developed automatic object detection and tracking systems can be used well for AUV, in which verage travel time for forward and backward motion are 14.20 seconds in 0.14 m/s, and 19.82 seconds in 0.1 m/s while average travel time is 15.36 seconds and 13.58 seconds for right and left motion test respectively.

In this paper a multiple object detection, recognition, and tracking system for unmanned aerial vehicles (UAVs) has been studied. The system can be implemented on any UAVs platform, with the main requirement being that the UAV has a suitable onboard computational unit and a camera. It is intended to be used in a maritime object tracking system framework for UAVs, which enables a UAV to perform multiobject tracking and situational awareness of the sea surface, in real time, during a UAV operation. Using machine vision to automatically detect objects in the camera's image stream combined with the UAV's navigation data, the onboard computer is able to georeference each object detection to measure the location of the detected objects in a local North‐East (NE) coordinate frame. A tracking algorithm which uses a Kalman filter and a constant velocity motion model utilizes an object's position measurements, automatically found using the object detection algorithm, to track and estimate an object's position and velocity. Furthermore, a global‐nearest‐neighbor algorithm is applied for data association. This is achieved using a measure of distance that is based not only on the physical distance between an object's estimated position and the measured position, but also how similar the objects appear in the camera image. Four field tests were conducted at sea to verify the object detection and tracking system. One of the flight tests was a two‐object tracking scenario, which is also used in three scenarios with an additional two simulated objects. The tracking results demonstrate the effectiveness of using visual recognition for data association to avoid interchanging the two estimated object trajectories. Furthermore, real‐time computations performed on the gathered data show that the system is able to automatically detect and track the position and velocity of a boat. Given that the system had at least 100 georeferenced measurements of the boat's position, the position was estimated and tracked with an accuracy of 5–15 m from 400 m altitude while the boat was in the camera's field of view (FOV). The estimated speed and course would also converge to the object's true trajectories (measured by Global Positioning System, GPS) for the tested scenarios. This enables the system to track boats while they are outside the FOV of the camera for extended periods of time, with tracking results showing a drift in the boat's position estimate down to 1–5 m/min outside of the FOV of the camera.

In recent years, object detection and tracking has been a dynamic research area. Rapid development of the multimedia and the associated technologies urge the processing of a huge database of video clips. The processing efficiency lies on the search methodologies utilised in the video processing system. Usage of unsuitable search methodologies may make the processing system ineffective. Hence, effective object detection and tracking system is an essential criterion for searching relevant videos from a huge collection of videos. This paper proposes a unique object detection and tracking system where video segmentation, feature extraction, object detection and tracking are combined perfectly using various features. Initially, the database video clips are segmented into different shots before performing the feature extraction process. The proposed system consists of two stages, namely, feature extraction and tracking of object in the video clips. In the feature extraction stage, firstly, colour feature is extracted based on colour quantisation. Next, edge density feature is extracted for the objects present in the query video. Then, the texture feature is extracted based on LGXP technique. Finally, based on these feature extracted, the object will be detected and the detected objects will be tracked by utilising both forward and backward tracking technique. The proposed methodology proved to be more effective and accurate in object detection and tracking.

ABSTRACTIn general, the object detection mechanism recognizes target objects in the image frames, and the tracking mechanism helps to capture the movement of target objects in diverse frames. Recent developments in Artificial Intelligence (AI) have enabled us to build computers, robots, and automated tools that are mostly designed for performing tasks and generating decisions without human assistance. The drones called Unmanned Aerial Vehicles (UAVs) are employed for many kinds of objectives, including parcel shipping, rescue operations, recognizing objects, and monitoring. Object detection and tracking systems are crucial for UAVs because they help to optimally capture moving objects, areas, and threats for enhancing security, surveillance, and awareness at an earlier stage. Also, they help to ultimately predict the category and location of UAVs from the video frames. Many researchers have developed diverse object detection and tracking methods on UAVs; yet, it is complex for continuously monitoring small objects in the gathered data, and it is affected by noise and blurriness due to the motion of UAVs. One of the greatest challenging duties for UAVs is object recognition and tracking since it needs precise, swift, and cost‐effective object detection and tracking. Pre‐trained networks are required for the detection of objects based on deep learning. Mismatches between the pre‐trained and the target domain network areas create problems in object detection. With the aim of resolving these issues, a deep learning‐assisted UAV control mechanism is developed in this research work by performing detection and tracking of objects. The developed model is helpful in improving rescue operations in disaster areas and security surveillance. At first, the input videos are accumulated from benchmark sources. From the videos, the resolution of the images is studied for an accurate object detection procedure. Next, the detection and tracking of the object are done via the developed Region Vision Transformer‐based Adaptive Multi‐scale You Only Look Once v8 (RV‐AMYOLOv8). The parameters fromYOLOv8 are optimized using the Fitness‐based Random Variable for Elk Herd Optimizer (FRVEHO) for enhancing the performance. The quantitative outcomes of the implemented approach help to analyze the suggested network's performance with conventional techniques. Here, the developed method attains 96% accuracy and 95% of precision measure to demonstrate its better performance than the existing methods. This object detection is helpful for analyzing the surrounding obstacles while controlling the UAVs.

Video surveillance applications in wireless visual sensor networks (WVSN) attract a lot of attention in recent years which demands higher performance with less complexity. Efficient and simple moving object detection and tracking (MODT) system is presented in this paper targetting the video surveillance application in WVSN. The main contribution of this paper is to develop a system that can perform both object detection and tracking with less complexity. This MODT system adopts compressed sensing (CS) to perform the background subtraction on compressive measurements and the subtracted measurements undergoes a measurement selection process (MSP) to extract the foreground measurements. MSP aims at extracting the minimum number of measurements that can yield higher detection accuracy. The detected object is tracked using the kalman filtering approach. Initially the centroid of the object is extracted from the binary image with the help of contour tracing which is then given as input to the Kalman filter to track the objects in the video. The performance of the MODT system is evaluated using parameters such as percentage of reduction in samples, energy complexity, detection and tracking accuracy. From the results it is evident that MODT system can achieve higher detection and tracking accuracy by reducing the measurements to more than 83 %. Also, the significance of the extracted measurements is observed by analyzing the detection accuracy which is around 0.88.

Autonomous vehicles represent a transformative technology with the potential to revolutionize transportation systems worldwide. One of the critical components enabling autonomous driving is robust object detection and tracking systems. This paper presents an in-depth exploration of recent advancements, challenges, and future directions in vision-based object detection and tracking for autonomous vehicles. We propose novel algorithms and methodologies aimed at enhancing detection accuracy, realtime performance, and adaptability to diverse environmental conditions. A comprehensive literature review discusses state-of-the-art techniques and identifies areas for improvement. Research challenges and objectives are outlined, followed by a detailed description of the proposed system architecture and implementation. The paper concludes with insights into the potential impact of these advancements on the future of autonomous driving technology.

Multiple objects (including humans) detection and tracking system plays an essential role in socially aware mobile robot navigation framework. Because, it provides an important input for the remaining modules of the framework. In this paper, we propose an efficient multiple objects detection and tracking system for mobile service robots in dynamic social environments using deep learning techniques. The proposed system consists of two steps: (1) multiple objects detection, and (2) multiple objects tracking. In the first step, the RGB image-based multiple objects detection is made use of to detect objects in the mobile robot's vicinity using a convolutional neural network. In the second stage of system, the detected objects are tracked using a deep simple online and realtime tracking technique. The experimental results indicate that, the proposed system is capable of detecting and tracking multiple objects including humans, providing significant information for the socially aware mobile robot navigation framework.

In order to realize real-time object detection and collaborative control of multi pan-tilts for unmanned platform, a scheme of visual object detection and tracking system based on MobileNet-SSD algorithm is proposed. This scheme can realize real-time visual object detection of people and vehicles in mobile platform without GPUs. First, objects are detected based on MobileNet-SSD algorithm. Second, the result of object detection is used for calculating attitude variation matrix for controlling multi pan-tilts. Finally, the multi pan-tilts can equip with different equipment, namely, three two-axis pan-tilts tracking objects to complete a various of tasks together. The experimental results show that the real-time performance of object detection is feasible, and the two-axis pan-tilts can track objects effectively.

With the increasing application of computer vision technology in autonomous driving, robot, and other mobile devices, more and more attention has been paid to the implementation of target detection and tracking algorithms on embedded platforms. The real-time performance and robustness of algorithms are two hot research topics and challenges in this field. In order to solve the problems of poor real-time tracking performance of embedded systems using convolutional neural networks and low robustness of tracking algorithms for complex scenes, this paper proposes a fast and accurate real-time video detection and tracking algorithm suitable for embedded systems. The algorithm combines the object detection model of single-shot multibox detection in deep convolution networks and the kernel correlation filters tracking algorithm, what is more, it accelerates the single-shot multibox detection model using field-programmable gate arrays, which satisfies the real-time performance of the algorithm on the embedded platform. To solve the problem of model contamination after the kernel correlation filters algorithm fails to track in complex scenes, an improvement in the validity detection mechanism of tracking results is proposed that solves the problem of the traditional kernel correlation filters algorithm not being able to robustly track for a long time. In order to solve the problem that the missed rate of the single-shot multibox detection model is high under the conditions of motion blur or illumination variation, a strategy to reduce missed rate is proposed that effectively reduces the missed detection. The experimental results on the embedded platform show that the algorithm can achieve real-time tracking of the object in the video and can automatically reposition the object to continue tracking after the object tracking fails.

The University of Toronto is one of eight teams competing in the SAE AutoDrive Challenge - a competition to develop a self-driving car by 2020. After placing first at the Year 1 challenge, we are headed to MCity in June 2019 for the second challenge. There, we will interact with pedestrians, cyclists, and cars. For safe operation, it is critical to have an accurate estimate of the position of all objects surrounding the vehicle. The contributions of this work are twofold: First, we present a new object detection and tracking dataset (UofTPed50), which uses GPS to ground truth the position and velocity of a pedestrian. To our knowledge, a dataset of this type for pedestrians has not been shown in the literature before. Second, we present a lightweight object detection and tracking system (aUToTrack) that uses vision, LIDAR, and GPS/IMU positioning to achieve state-of-the-art performance on the KITTI Object Tracking benchmark. We show that aUToTrack accurately estimates the position and velocity of pedestrians, in real-time, using CPUs only. aUToTrack has been tested in closed-loop experiments on a real self-driving car, and we demonstrate its performance on our dataset.

Real-time object detection and tracking is a vast, vibrant yet inconclusive area of computer vision. Automatic object detection and tracking are useful in surveillance, tracking systems used in security, mobile robots, medical therapy, driver assistance systems, and analysis of sports. Algorithms proposed in existing literature use color segmentation, edge tracking, shape detection for detection, and tracking of an object. The challenges such as tracking in dynamic environment and difficult tracking of multiple objects in multiple-camera environment and expensive computation restrict the implementation of these systems for solving real-world problems. This motivates us to develop a system that is efficient in real-time object detection and tracking. In this paper, authors develop the real-time object detection and tracking system using velocity control. Experimental results prove its efficacy in detection and tracking of simple as well as complex objects in both simple and complex backgrounds. The system is effective in detecting and tracking the co-occurrence of two objects. It clearly shows the impact of color dominance or shape dominance, self-shadow, and image of an object in a mirror.

Design and implementation of deep learning-based object detection and tracking system

We present FUS3D, a fast and lightweight system for real-time 3D object detection and tracking on edge devices. Our approach seamlessly integrates stages for 3D object detection and multi-object-tracking into a single, end-to-end trainable model. FUS3D is specially tuned for indoor 3D human behavior analysis, with target applications in Ambient Assisted Living (AAL) or surveillance. The system is optimized for inference on the edge, thus enabling sensor-near processing of potentially sensitive data. In addition, our system relies exclusively on the less privacy-intrusive 3D depth imaging modality, thus further highlighting the potential of our method for application in sensitive areas. FUS3D achieves best results when utilized in a joint detection and tracking configuration. Nevertheless, the proposed detection stage can function as a fast standalone object detection model if required. We have evaluated FUS3D extensively on the MIPT dataset and demonstrated its superior performance over comparable existing state-of-the-art methods in terms of 3D object detection, multi-object tracking, and, most importantly, runtime.

Current developments in object tracking and detection techniques have directed remarkable improvements in distinguishing attacks and adversaries. Nevertheless, adversarial attacks, intrusions, and manipulation of images/ videos threaten video surveillance systems and other object-tracking applications. Generative adversarial neural networks (GANNs) are widely used image processing and object detection techniques because of their flexibility in processing large datasets in real-time. GANN training ensures a tamper-proof system, but the plausibility of attacks persists. Therefore, reviewing object tracking and detection techniques under GANN threats is necessary to reveal the challenges and benefits of efficient defence methods against these attacks. This paper aims to systematically review object tracking and detection techniques under threats to GANN-based applications. The selected studies were based on different factors, such as the year of publication, the method implemented in the article, the reliability of the chosen algorithms, and dataset size. Each study is summarised by assigning it to one of the two predefined tasks: applying a GANN or using traditional machine learning (ML) techniques. First, the paper discusses traditional applied techniques in this field. Second, it addresses the challenges and benefits of object detection and tracking. Finally, different existing GANN architectures are covered to justify the need for tamper-proof object tracking systems that can process efficiently in a real-time environment.

BackgroundCompetence in neonatal resuscitation of the newborn is very critical to ensure the safety and well-being of newborn infants. The acquisition of neonatal resuscitation skills by birth attendants improves self-efficacy, thereby reducing neonatal mortality as a result of asphyxia. Approximately one-quarter of all neonatal deaths globally are caused by birth asphyxia. The need for neonatal resuscitation is most imperative in resource-constrained settings, where access to intrapartum obstetric care is inadequate.ObjectiveThis protocol describes the methodology of a scoping review on evidence of training in neonatal resuscitation and its association with practice in low-resource countries. The aim of the review is to map the available evidence of neonatal resuscitation training on the practices of unskilled birth attendants.MethodsThe scoping review will use the Population, Concept, and Context (PCC) framework proposed by Arksey and O’Malley, refined by Levac et al, and published by Joanna Briggs Institute, while following the PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses Extension for Scoping Reviews) guidelines. The search strategy was developed with the assistance of the college librarian. A number of databases of peer-reviewed research (PsycINFO and Wiley Online Library [via EBSCOhost], PubMed, MEDLINE with full text, Google Scholar [via ScienceDirect], and CINAHL Plus with full text [via EBSCOhost]) and databases committed to grey literature sources will be searched, and reference extraction will be performed. Two independent reviewers will screen and extract data, and discrepancies will be resolved by a third reviewer. The extracted data will undergo a descriptive analysis of contextual data and a quantitative analysis using appropriate statistical methods.ResultsData relating to neonatal resuscitation training and practices in low-resource settings will be extracted and included for analysis. We expect that the review will be completed 12 months from the publication of this protocol.ConclusionsThis scoping review will focus on the review of evidence and provide an insight into the existing literature to guide further research and identify implementation strategies to improve the practices of unskilled birth attendants through the acquisition of skills and self-efficacy in neonatal resuscitation. The results of this review will be presented at relevant conferences related to newborn and child health and neonatal nursing studies and published in a peer-reviewed journal.International Registered Report Identifier (IRRID)DERR1-10.2196/18935