Drone-Person Tracking in Uniform Appearance Crowd: A New Dataset.
Ontology highlight
ABSTRACT:
SUBMITTER: Alansari M
PROVIDER: S-EPMC10762134 | biostudies-literature | 2024 Jan
REPOSITORIES: biostudies-literature
Publications
Drone-Person Tracking in Uniform Appearance Crowd: A New Dataset.
Alansari Mohamad M Abdul Hay Oussama O Alansari Sara S Javed Sajid S Shoufan Abdulhadi A Zweiri Yahya Y Werghi Naoufel N
Scientific data 20240102 1
Drone-person tracking in uniform appearance crowds poses unique challenges due to the difficulty in distinguishing individuals with similar attire and multi-scale variations. To address this issue and facilitate the development of effective tracking algorithms, we present a novel dataset named D-PTUAC (Drone-Person Tracking in Uniform Appearance Crowd). The dataset comprises 138 sequences comprising over 121 K frames, each manually annotated with bounding boxes and attributes. During dataset cre ...[more]
Similar Datasets
Project description:The use of small and remotely controlled unmanned aerial vehicles (UAVs), referred to as drones, has increased dramatically in recent years, both for professional and recreative purposes. This goes in parallel with (intentional or unintentional) misuse episodes, with an evident threat to the safety of people or facilities [1]. As a result, the detection of UAV has also emerged as a research topic [2]. Most of the existing studies on drone detection fail to specify the type of acquisition device, the drone type, the detection range, or the employed dataset. The lack of proper UAV detection studies employing thermal infrared cameras is also acknowledged as an issue, despite its success in detecting other types of targets [2]. Beside, we have not found any previous study that addresses the detection task as a function of distance to the target. Sensor fusion is indicated as an open research issue as well to achieve better detection results in comparison to a single sensor, although research in this direction is scarce too [3], [4], [5], [6]. To help in counteracting the mentioned issues and allow fundamental studies with a common public benchmark, we contribute with an annotated multi-sensor database for drone detection that includes infrared and visible videos and audio files. The database includes three different drones, a small-sized model (Hubsan H107D+), a medium-sized drone (DJI Flame Wheel in quadcopter configuration), and a performance-grade model (DJI Phantom 4 Pro). It also includes other flying objects that can be mistakenly detected as drones, such as birds, airplanes or helicopters. In addition to using several different sensors, the number of classes is higher than in previous studies [4]. The video part contains 650 infrared and visible videos (365 IR and 285 visible) of drones, birds, airplanes and helicopters. Each clip is of ten seconds, resulting in a total of 203,328 annotated frames. The database is complemented with 90 audio files of the classes drones, helicopters and background noise. To allow studies as a function of the sensor-to-target distance, the dataset is divided into three categories (Close, Medium, Distant) according to the industry-standard Detect, Recognize and Identify (DRI) requirements [7], built on the Johnson criteria [8]. Given that the drones must be flown within visual range due to regulations, the largest sensor-to-target distance for a drone in the dataset is 200 m, and acquisitions are made in daylight. The data has been obtained at three airports in Sweden: Halmstad Airport (IATA code: HAD/ICAO code: ESMT), Gothenburg City Airport (GSE/ESGP) and Malmö Airport (MMX/ESMS). The acquisition sensors are mounted on a pan-tilt platform that steers the cameras to the objects of interest. All sensors and the platform are controlled with a standard laptop vis a USB hub.
| S-EPMC8573135 | biostudies-literature
Project description:The dataset is constructed from the drone flight log messages extracted from publicly available drone image datasets provided by VTO Labs under the Drone Forensic Program. The entire process of building this dataset includes extraction, decryption, parsing, cleansing, unique filtering, annotation, splitting, and analysis. The resulting dataset is in CoNLL format, annotated using the IOB2 scheme with six entity types. The total number of log messages acquired from 12 DJI drone models is 1850. The data are split based on the drone models, resulting in 1412 messages for training and 438 messages for testing. The average length of log messages is 6.5 globally, 6.6 and 8.8 for the train and the test sets, respectively.
| S-EPMC10293979 | biostudies-literature
Project description:Tracking and action-recognition algorithms are currently widely used in video surveillance, monitoring urban activities and in many other areas. Their development highly relies on benchmarking scenarios, which enable reliable evaluations/improvements of their efficiencies. Presently, benchmarking methods for tracking and action-recognition algorithms rely on manual annotation of video databases, prone to human errors, limited in size and time-consuming. Here, using gained experiences, an alternative benchmarking solution is presented, which employs methods and tools obtained from the computer-game domain to create simulated video data with automatic annotations. Presented approach highly outperforms existing solutions in the size of the data and variety of annotations possible to create. With proposed system, a potential user can generate a sequence of random images involving different times of day, weather conditions, and scenes for use in tracking evaluation. In the design of the proposed tool, the concept of crowd simulation is used and developed. The system is validated by comparisons to existing methods.
| S-EPMC7506927 | biostudies-literature
Project description:A manual assessment of sperm motility requires microscopy observation, which is challenging due to the fast-moving spermatozoa in the field of view. To obtain correct results, manual evaluation requires extensive training. Therefore, computer-aided sperm analysis (CASA) has become increasingly used in clinics. Despite this, more data is needed to train supervised machine learning approaches in order to improve accuracy and reliability in the assessment of sperm motility and kinematics. In this regard, we provide a dataset called VISEM-Tracking with 20 video recordings of 30 seconds (comprising 29,196 frames) of wet semen preparations with manually annotated bounding-box coordinates and a set of sperm characteristics analyzed by experts in the domain. In addition to the annotated data, we provide unlabeled video clips for easy-to-use access and analysis of the data via methods such as self- or unsupervised learning. As part of this paper, we present baseline sperm detection performances using the YOLOv5 deep learning (DL) model trained on the VISEM-Tracking dataset. As a result, we show that the dataset can be used to train complex DL models to analyze spermatozoa.
| S-EPMC10167330 | biostudies-literature
Project description:Innovative technology and improvements in intelligent machinery, transportation facilities, emergency systems, and educational services define the modern era. It is difficult to comprehend the scenario, do crowd analysis, and observe persons. For e-learning-based multiobject tracking and predication framework for crowd data via multilayer perceptron, this article recommends an organized method that takes e-learning crowd-based type data as input, based on usual and abnormal actions and activities. After that, super pixel and fuzzy c mean, for features extraction, we used fused dense optical flow and gradient patches, and for multiobject tracking, we applied a compressive tracking algorithm and Taylor series predictive tracking approach. The next step is to find the mean, variance, speed, and frame occupancy utilized for trajectory extraction. To reduce data complexity and optimization, we applied T-distributed stochastic neighbor embedding (t-SNE). For predicting normal and abnormal action in e-learning-based crowd data, we used multilayer perceptron (MLP) to classify numerous classes. We used the three-crowd activity University of California San Diego, Department of Pediatrics (USCD-Ped), Shanghai tech, and Indian Institute of Technology Bombay (IITB) corridor datasets for experimental estimation based on human and nonhuman-based videos. We achieve a mean accuracy of 87.00%, USCD-Ped, Shanghai tech for 85.75%, and IITB corridor of 88.00% datasets.
| S-EPMC10280427 | biostudies-literature
Project description:ObjectiveParents' tracking of developmental milestones can assist healthcare providers with early detection of developmental delays and appropriate referrals to early intervention. Crowdsourcing is one way to update the content and age data distribution of developmental checklists for parents and providers. This feasibility study examined which developmental milestones parents chose to track and what they added beyond traditional milestones, using the babyTRACKS crowd-based mobile app.MethodWe analyzed the developmental diaries of 3,832 children, registered in the babyTRACKS app at an average age of 9.3 months. Their parents recorded a median of 5 milestones per diary, selecting from the accumulating lists of age-appropriate milestones or authoring new milestones. The final database included 645 types of milestones; 89.15% were developmental, of which 43.6% were comparable to the Centers for Disease Control (CDC) milestones while the rest were crowd-authored. Milestones were categorized into developmental domains: Gross Motor, Fine Motor, Oral Motor, Self-Care, Cognitive, Language Comprehension, Speech, Non-Verbal Communication, Social, Emotional, and Regulation.ResultsOn average, the milestone domains of Gross Motor, Fine Motor, Cognitive and Social were the most added to diaries (20%-30% of a diary). Within the Cognitive, Speech and Language Comprehension domains there were significantly more CDC comparable versus crowd-authored milestones (29% versus 21%, 22% versus 10%, 8% versus 4%). In contrast, within the Regulation and Oral Motor domains there were more crowd versus CDC milestones (17% versus 3%, 9% versus 3%). Crowd-authored Speech milestones were significantly older by 7 months than CDC milestones.ConclusionTracking daily observations of child development provides a window into personally relevant milestones for the child and parent. The crowd of parents can independently track and add new milestones across main developmental domains. Regulation and Oral Motor development especially interest parents. Parents may be less aware of early progress in Language Comprehension and Speech; thus, these domains require more structured screening. Designing mobile early screening which is crowd-based engages parents as proactive partners in developmental tracking.
| S-EPMC9135273 | biostudies-literature
Project description:Enzymes that catalyze DNA modifying activities including cytidine deamination and cytosine methylation play important biological roles and have been implicated pathologically in diseases such as cancer. Here, we report Direct Resolution of ONE dalton difference (DRONE), an ultra high performance liquid chromatography (UHPLC)-based analytical method to track a single dalton change in the cytosine-to-uracil conversion catalyzed by the human apolipoprotein B m-RNA editing catalytic polypeptide-like 3 (APOBEC3) cytidine deaminases, implicated in cancer and antiviral defense. Additionally, we demonstrate broad applicability by tracking other important DNA modifications and assessing epigenetic enzyme inhibition. We have extended our methodology to obtain data on two distinct deamination events in the same oligonucleotide substrate designed from a putative APOBEC substrate, diversifying the utility of the described method. DRONE provides an important foundation for in-depth analysis of DNA-modifying enzymes and versatile detection of novel DNA modifications of interest.
| S-EPMC6410358 | biostudies-literature
Project description:The distribution of parcels is one of the most complex and challenging processes in supply chain execution. Lately, the development of both electronic and quick commerce has driven carriers and courier operators to identify more effective methods for express parcel delivery. To this end, the development of efficient distribution networks that aim in increasing customer experience while maintaining low operating costs is significant importance both for researchers as well as for practitioners. This article presents a dataset for the Van Drone Routing Problem with Multiple Delivery Points and Cooperation (VDRPMDPC). The latter examines a van-drone team from an operational viewpoint, where a van moves along a road network while the drone egress and ingress from a van to a nearby delivery location and then travels back to the van. This problem has been created with the aim of assessing the design of more sustainable and cost-effective delivery routes in urban and semi urban environments via the use of Unmanned Aerial Vehicles (UAVs). For the development of this dataset real geographical positions have been used located at two different areas of Athens, Greece. The entire benchmark is composed of 14 instances comprised by 20, 40, 60 and 100 clients respectively. The dataset is publicly available for its use and modification.
| S-EPMC10184041 | biostudies-literature
Project description:State freedom of information laws are vital mechanisms for providing public access to government records and supporting civic engagement through the effectuation of a public policy of transparency at the state level within the United States, not unlike their federal counterpart, the Freedom of Information Act (FOIA). New Jersey state law facilitates public access to government records under the Open Public Records Act (OPRA). Codified at N.J.S.A. 47:1A-1 et seq., OPRA applies to state, county and local public authorities but exempts the judicial and legislative branches from its disclosure requirements. Since OPRA took effect in 2002, it has been difficult to track the full extent of law's impact across New Jersey's 21 counties, 565 municipalities, and numerous state agencies, school districts and independent authorities, all of which must individually respond to requests under the law. To the best of the author's knowledge, no official source has compiled detailed metadata tracking the content and disposition of OPRA requests at the state, regional and municipal levels within New Jersey using individual requests, and authorities rarely proactively disclose their responses to requests they receive, necessitating further data collection to support research into the impacts of this law. This article presents the OPRAmachine dataset: data containing detailed metadata on public records requests submitted to state & local public authorities in New Jersey since October 2017 collected through the implementation of information and communication technologies (ICT) to facilitate the freedom of information request process. The data was collected using an open-source web interface that allowed users to submit an OPRA request to public authorities, with responses stored in a database and made available via the internet. After their request received a response, users were asked to answer a single survey question describing the status of their request, with their answer used to classify the request. Descriptive statistics, tables and frequencies were produced for the dataset and are included in this article. These data will assist state policymakers and other interested parties with assessing trends in OPRA requests across multiple types of public authorities & geographic regions. These data can inform more efficient government records management procedures, foster civic engagement by increasing government transparency and can inform the development of possible reforms to the OPRA law by showing trends in requests & responses that can be used to evaluate the law's implementation throughout the state.
| S-EPMC7467104 | biostudies-literature
Project description:The understanding of human-object interactions is fundamental in First Person Vision (FPV). Visual tracking algorithms which follow the objects manipulated by the camera wearer can provide useful information to effectively model such interactions. In the last years, the computer vision community has significantly improved the performance of tracking algorithms for a large variety of target objects and scenarios. Despite a few previous attempts to exploit trackers in the FPV domain, a methodical analysis of the performance of state-of-the-art trackers is still missing. This research gap raises the question of whether current solutions can be used "off-the-shelf" or more domain-specific investigations should be carried out. This paper aims to provide answers to such questions. We present the first systematic investigation of single object tracking in FPV. Our study extensively analyses the performance of 42 algorithms including generic object trackers and baseline FPV-specific trackers. The analysis is carried out by focusing on different aspects of the FPV setting, introducing new performance measures, and in relation to FPV-specific tasks. The study is made possible through the introduction of TREK-150, a novel benchmark dataset composed of 150 densely annotated video sequences. Our results show that object tracking in FPV poses new challenges to current visual trackers. We highlight the factors causing such behavior and point out possible research directions. Despite their difficulties, we prove that trackers bring benefits to FPV downstream tasks requiring short-term object tracking. We expect that generic object tracking will gain popularity in FPV as new and FPV-specific methodologies are investigated.Supplementary informationThe online version contains supplementary material available at 10.1007/s11263-022-01694-6.
| S-EPMC9816211 | biostudies-literature