Outdoor Environments Research Articles

Mobile Data Network Performance Review – A Perspective of Zambia

High speed mobile internet results in better user experience and satisfied subscriber. However factors that affect the download speed include transfer technology, number of subscribers sharing the connection, device capability and radio conditions at the subscriber location. This research was conducted to review the mobile internet performance in Zambia and determine its conformity to the regulator, ZICTA, QoS regulation. Two sets of empirical data were collected in the capital city, first in 2021 during the covid pandemic period and second in 2024. The data was compared to check for network operator developments. The results reveal that two MNOs acquired new 2600MHz spectrum, however only one MNO drew maximum benefit resulting in improved 4G download speeds. This improvement was despite an increase in market share over the same period. The second operator that deployed the 2600MHz LTE TDD mode spectrum recorded a degradation in overall downloads speeds when compared to the initial data set in spite of a reduction in market share over the same period. Thus the steps to improve the LTE network are to add more spectrum to at least reach the 3GPP Rel 10 standard of 5 carrier configuration (5CC) to reach a total 100MHz and configure network features like Carrier Aggregation (CA) to provide for higher throughputs for capable devices. Other ways to expand LTE network include add more antennas to allow for higher spectral efficiency using 8 x 8 MIMO or more and thirdly deploy Small cells solution to enhance coverage and capacity in both indoor and outdoor environment.

A Study of the Relationship between Human Behavior and Urban Design during the Winter in a High-Snowfall Urban Area

This study focuses on the relationship between the outdoor environment and usage behavior of open spaces in cities with snowy and cold climates (winter cities), using an outdoor survey conducted at AKAPURA Plaza in Sapporo, Japan. This study seeks to understand walking and staying behaviors and analyzes their relationships to snowy outdoor environments. An analysis of the survey data shows that while the number of pedestrians using AKAPLA Plaza decreased as temperatures dropped, the ratio of staying behavior to the number of pedestrians did not decrease despite dropping temperatures. This study identified the following three design principles that can be applied to encourage the usage of open urban spaces during the winter. In winter, the number of pedestrians decreases in correlation with decreases in temperature; however, during the snowy season, walking can be encouraged by providing areas with less snow (PATH). Partially snow-covered areas can encourage photography and snow play behavior (STORAGE). Finally, providing walking routes to snow-covered areas can encourage staying behavior (APPROACH). These design principles were established based on the study in Sapporo and have the potential to be widely applied in other winter cities across the world through future research and analysis.

Research on vibration pattern recognition based on phase‐sensitive optical time domain reflectometry and voting fully convolution neural networks

AbstractA method that combines phase‐sensitive optical time domain reflectometry with deep learning to construct new voting fully convolution neural networks (VoteFCNs) is proposed. Compared to the traditional convolutional network, the VoteFCN can be input with data of random size and requires less parameters so that the training speed can be improved greatly. The recognition results can be more accurate and more reliable if we use classification voting count and average recognition rate as the criteria to judge network training quality. At last, the training and identification were conducted by simulating such several disturbance events: walking, raining, climbing fence, hammering the ground optical fibre and normal outdoor environments. The results show that the average test accuracy of this method is about 93.4%.

Development of the Standardized Navigation Of Winter Mobility & Accessibility Network (SNOWMAN) course

IntroductionManual wheelchairs (MWC) users have limited mobility during winter months as they encounter many environmental barriers that restrict their community participation. This paper outlines the creation and standardization of an outdoor environment designed to simulate the real-life conditions and obstacles experienced by MWC users in winter.Methods and resultsThis study consisted of four phases. In Phase 1, researchers used a qualitative ethnographic approach to document the specific challenges and adaptive strategies used by MWC users in winter conditions. In Phase 2, key informants with expertise in MWC winter mobility were invited to co-design the Standardized Navigation Of Winter Mobility & Accessibility Network (SNOWMAN) course. Participants reviewed draft design solutions and offered their input and suggestions to expand upon the initial design. A second co-design workshop included additional key informants, including service providers, policymakers, and professionals with expertise in landscape architecture and engineering, to validate the design solution. The workshops resulted in a detailed illustration of the SNOWMAN course, including five sections: platforms with side slopes, a miniature ice rink, curbs and curb cuts, a path with uneven winter surfaces, and modular ramps at various slopes. Phases 3 and 4 marked the conclusion of the study and involved fabrication of the SNOWMAN course and establishment of a standardized protocol for course setup and maintenance.DiscussionThe project aimed to offer several additional potential benefits, supported by the various stakeholders across the study phases, that extend beyond creation of a controlled and safe environment for wheelchair users to develop their winter mobility skills. Practicing wheelchair skills in this area may assist wheelchair users in gaining confidence which may ultimately translate to increased participation in the community.

Sensory Responsive Environments: A Qualitative Study on Perceived Relationships between Outdoor Built Environments and Sensory Sensitivities

This qualitative study explored the perceived relationships between outdoor built environments and sensory sensitivities, focusing on autism, ADHD, and dyslexia. Thirty-one semi-structured interviews were conducted with participants who had lived experience with these focal groups. Through thematic analysis of their narratives, the study uncovered patterns highlighting the perceived relationships between designed landscapes and sensory sensitivities in neurodivergent individuals, encompassing both heightened sensitivity (hypersensitivity) and reduced sensitivity (hyposensitivity). Emergent themes included individual and personal factors, sensory affordances, the benefits of outdoor environments, ambient environmental factors, materiality, spatial design, navigating environments, pedestrian-centric transportation, sensorimotor movement, safety, refuge, human settlement types, social environments, and accessibility plus inclusion. Subthematic patterns within these larger thematic categories were also identified. Study participants revealed significant sensory barriers and sensorially supportive elements of designed outdoor environments, along with promising design interventions. The findings unveil the advantages of designing multi-sensory landscapes tailored to atypical sensory needs, emphasizing the importance of fostering inclusion by designing landscapes that reflect the communities they serve. This concept is encapsulated in the development of the Sensory Responsive Environments Framework (SREF), the emergent theoretical framework of this study.

Indoor and outdoor NO2 and SO2 levels in 13 randomly selected preschools from 7 districts in Mpumalanga Province, South Africa

AbstractBackgroundAir pollution is a serious worldwide issue, where both outdoor and indoor air quality have a substantial impact on the health of children. Children are more vulnerable to the effects of air pollution due to their developing respiratory systems and higher respiration rates than adults. These children dedicate a substantial amount of time to the preschool setting. The study sought to evaluate the concentration of NO2 and SO2 in both outdoor and indoor environments of preschool facilities.MethodsConcurrently, the levels of NO2 and SO2 were measured indoors and outdoors at 13 randomly selected preschools in 7 districts in Mpumalanga Province, South Africa. Radiello passive air samplers were employed to collect gaseous samples.ResultsThe mean levels of NO2 indoors and outdoors were within the recommended criteria outlined by the World Health Organization (WHO), specifically target levels 1–3. Additionally, these values were also below the air quality guides outlined by South Africa, both for yearly and 1‐h mean measurements. Nevertheless, both levels remained above the suitable threshold of 10 µg m−3 outlined by the WHO air quality guidelines.ConclusionsIt is important to implement proactive measures such as enhancing airflow systems, employing air filters and reducing potential sources of air pollution in preschools, to aid in reducing exposure to indoor and outdoor NO2 and SO2.

3D-MuPPET: 3D Multi-Pigeon Pose Estimation and Tracking

AbstractMarkerless methods for animal posture tracking have been rapidly developing recently, but frameworks and benchmarks for tracking large animal groups in 3D are still lacking. To overcome this gap in the literature, we present 3D-MuPPET, a framework to estimate and track 3D poses of up to 10 pigeons at interactive speed using multiple camera views. We train a pose estimator to infer 2D keypoints and bounding boxes of multiple pigeons, then triangulate the keypoints to 3D. For identity matching of individuals in all views, we first dynamically match 2D detections to global identities in the first frame, then use a 2D tracker to maintain IDs across views in subsequent frames. We achieve comparable accuracy to a state of the art 3D pose estimator in terms of median error and Percentage of Correct Keypoints. Additionally, we benchmark the inference speed of 3D-MuPPET, with up to 9.45 fps in 2D and 1.89 fps in 3D, and perform quantitative tracking evaluation, which yields encouraging results. Finally, we showcase two novel applications for 3D-MuPPET. First, we train a model with data of single pigeons and achieve comparable results in 2D and 3D posture estimation for up to 5 pigeons. Second, we show that 3D-MuPPET also works in outdoors without additional annotations from natural environments. Both use cases simplify the domain shift to new species and environments, largely reducing annotation effort needed for 3D posture tracking. To the best of our knowledge we are the first to present a framework for 2D/3D animal posture and trajectory tracking that works in both indoor and outdoor environments for up to 10 individuals. We hope that the framework can open up new opportunities in studying animal collective behaviour and encourages further developments in 3D multi-animal posture tracking.

Exercise Responses During Outdoor Versus Virtual Reality Indoor Arm+FES-Leg Cycling in Individuals with Spinal Cord Injury.

Background: Virtual reality (VR)-enhanced indoor hybrid cycling in people with spinal cord injury (SCI) can be comparable to outdoor hybrid cycling. Method: Eight individuals with chronic thoracic-lesion SCI performed voluntary arm and electrically assisted leg cycling on a hybrid recumbent tricycle. Exercises were conducted outdoors and indoors incorporating VR technology in which the outdoor environment was simulated on a large flat screen monitor. Electrical stimulation was applied bilaterally to the leg muscle groups. Oxygen uptake (VO2), heart rate, energy expenditures, and Ratings of Perceived Exertion were measured over a 30-minute outdoor test course that was also VR-simulated indoors. Immediately after each exercise, participants completed questionnaires to document their perceptual-psychological responses. Results: Mean 30-minute VO2 was higher for indoor VR exercise (average VO2-indoor VR-exercise: 1316 ± mL/min vs. outdoor cycling: 1255 ± 53 mL/min; highest VO2-indoor VR-exercise: 1615 ± 67 mL/min vs. outdoor cycling: 1725 ± 67 mL/min). Arm and leg activity counts were significantly higher during indoor VR-assisted hybrid functional electrical stimulation (FES) cycling than outdoors; 42% greater for the arms and 23% higher for the legs (P < 0.05). Similar responses were reported for exercise effort and perceptual-psychological outcomes during both modes. Conclusion: This study proposes that combining FES and VR technology provides new opportunities for physical activity promotion or exercise rehabilitation in the SCI population, since these modes have similar "dose-potency" and self-perceived effort. Human Research Ethics Committee of the University of Sydney Ref. No. 01-2010/12385.

Comprehensive Performance Evaluation between Visual SLAM and LiDAR SLAM for Mobile Robots: Theories and Experiments

SLAM (Simultaneous Localization and Mapping), primarily relying on camera or LiDAR (Light Detection and Ranging) sensors, plays a crucial role in robotics for localization and environmental reconstruction. This paper assesses the performance of two leading methods, namely ORB-SLAM3 and SC-LeGO-LOAM, focusing on localization and mapping in both indoor and outdoor environments. The evaluation employs artificial and cost-effective datasets incorporating data from a 3D LiDAR and an RGB-D (color and depth) camera. A practical approach is introduced for calculating ground-truth trajectories and during benchmarking, reconstruction maps based on ground truth are established. To assess the performance, ATE and RPE are utilized to evaluate the accuracy of localization; standard deviation is employed to compare the stability during the localization process for different methods. While both algorithms exhibit satisfactory positioning accuracy, their performance is suboptimal in scenarios with inadequate textures. Furthermore, 3D reconstruction maps established by the two approaches are also provided for direct observation of their differences and the limitations encountered during map construction. Moreover, the research includes a comprehensive comparison of computational performance metrics, encompassing Central Processing Unit (CPU) utilization, memory usage, and an in-depth analysis. This evaluation revealed that Visual SLAM requires more CPU resources than LiDAR SLAM, primarily due to additional data storage requirements, emphasizing the impact of environmental factors on resource requirements. In conclusion, LiDAR SLAM is more suitable for the outdoors due to its comprehensive nature, while Visual SLAM excels indoors, compensating for sparse aspects in LiDAR SLAM. To facilitate further research, a technical guide was also provided for the researchers in related fields.

Durability evaluation and lifetime prediction of recycled coarse aggregate self-compacting concrete after freeze-thaw and sulfate erosion coupling

This paper aims to study the durability of recycled coarse aggregate self-compacting concrete (RCASCC) after being subjected to freeze-thaw and sulfate coupling. The durability comprehensive evaluation index of RCASCC based on the entropy weight method was defined, and the variation law of the durability comprehensive evaluation index concerning RCA substitution rate, freeze-thaw environment, and coupling frequency was obtained. GM (1, 1) model based on grey system theory was used to evaluate the durability of RCASCC under the coupling effects of freeze-thaw and sulfate attack. The results show that there are some differences in the accuracy of the four GM (1, 1) models. It is recommended that the EGM model can be used to predict the durability of the RCASCC under the coupled effects of freeze-thaw and sulfate erosion. Moreover, the working life of RCASCC under the coupling effects in the outdoor environments of northeast, north, and northwest China was calculated, when the comprehensive evaluation index of durability decreases to 75% as the failure criterion. A multi-criteria analysis employing TOPSIS and VIKOR methods was conducted to evaluate the durability of RCASCC under these coupling effects. A multi criteria analysis was conducted on the durability of RCASCC under the coupling effects of freeze-thaw and sulfate erosion using TOPSIS and VIKOR methods. Under these two rankings, the splitting tensile strength is the index that changes the most after coupling effects, while the compressive strength changes relatively little. The importance of dynamic elastic modulus and weight is different due to different materials and evaluation methods. RC100-H typically exhibits the largest variation, while NC-H and RC50-NM typically exhibit smaller variations.

Design and Fabrication of Offroad Electric Wheelchair

Design and Fabrication of Offroad Electric Wheelchair

Study on the Impact of Design Factors of Piloti Forms on the Thermal Environment in Residential Quarters

Study on the Impact of Design Factors of Piloti Forms on the Thermal Environment in Residential Quarters

Walk with me? Part 2: Dogs synchronize with an unfamiliar person who first synchronized with their owner

Dogs exhibit sensitivity to human behaviours directed towards them (see Part 1), but dogs’ sensitivity to human third-party interactions, i.e. eavesdropping or indirect sensitivity, remains unclear. This study aimed to investigate dogs' indirect sensitivity in an ecological context devoid of food incentives. We thus explored dogs’ responsiveness to interactions between their owner and an unfamiliar person during a synchronous walk in an outdoor environment. To do so, we delineated two experimental groups of pet dogs: an unfamiliar experimenter either walked and talked with the owner for 15 minutes, maintaining a 1-metre proximity and aligning speed (n = 16 dogs) or stayed away from the owner for 15 minutes (n = 16 dogs) in the dog’s presence. We then compared the dogs’ locomotor synchronization with the experimenter and the dogs’ gaze behaviour during a straight-line walk. Dogs for which the experimenter had interacted with the owner displayed enhanced location, temporal and activity synchronization with the experimenter during the straight-line walk compared to dogs for which the experimenter had not interacted with the owner. Specifically, these dogs were closer to the experimenter, had a smaller speed difference compared to the experimenter’s speed at the beginning of the straight-line walk, and more dogs from this group adjusted their speed directly after the experimenter’s change of speed. Regarding dogs’ gaze behaviour, we did not find significant differences between the two experimental groups. Finally, we found that dogs from both experimental groups were attracted to their owner during the straight-line walk. Our results demonstrate, for the first time, that dogs’ behavioural synchronization with an unfamiliar person occurs subsequently to the dogs’ perception of intraspecific behavioural synchronization between their owner and the unfamiliar person. This third-party sensitivity may result from an automatic process of reproducing perceived behaviours, suggesting interspecific motor contagion when dogs perceive synchronous behaviour of two human agents; and/or from a transitivity of familiarity, the unfamiliar person becoming indirectly familiar to the dogs through their interaction with the dogs’ owners. These findings bear practical significance, as encounters between unfamiliar people and dog-owner dyads can be enhanced if those people first synchronize and talk with dogs’ owners before interacting with dogs.

A multi-stage localization framework for accurate and precise docking of autonomous mobile robots (AMRs)

Abstract Autonomous navigation has been a long-standing research topic, and researchers have worked on many challenging problems in indoor and outdoor environments. One application area of navigation solutions is material handling in industrial environments. With Industry 4.0, the simple problem in traditional factories has evolved into the use of autonomous mobile robots within flexible production islands in a self-decision-making structure. Two main stages of such a navigation system are safe transportation of the vehicle from one point to another and reaching destinations at industrial standards. The main concern in the former is roughly determining the vehicle’s pose to follow the route, while the latter aims to reach the target with high accuracy and precision. Often, it may not be possible or require extra effort to satisfy requirements with a single localization method. Therefore, a multi-stage localization approach is proposed in this study. Particle filter-based large-scale localization approaches are utilized during the vehicle’s movement from one point to another, while scan-matching-based methods are used in the docking stage. The localization system enables the appropriate approach based on the vehicle’s status and task through a decision-making mechanism. The decision-making mechanism uses a similarity metric obtained through the correntropy criterion to decide when and how to switch from large-scale localization to precise localization. The feasibility and performance of the developed method are corroborated through field tests. These evaluations demonstrate that the proposed method accomplishes tasks with sub-centimeter and sub-degree accuracy and precision without affecting the operation of the navigation algorithms in real time.

Analysis of window opening in arctic community housing and development of data-driven models

Achieving low-energy, comfortable buildings in remote Arctic regions like Nunavik, Canada, presents multiple challenges due to high heating demand and limited energy supply. Understanding human behavior and the impact of practices on energy use is a key element in improving building performance. While previous research on building performance in Arctic regions has often adopted a building-centered approach, this study offers a complementary approach by investigating occupant behavior, focusing on window openings. The sample includes 10 monitored houses in the village of Quaqtaq, Nunavik. Data on weather conditions and window and door status were collected from September 2018 to August 2020. Behavior trends were identified using metrics such as the opening ratio, median duration of an opening, and number of openings. Correlations between opening/closing actions and the conditions of the outdoor environment were analyzed. Findings indicate that occupants interact more with common room windows and tend to leave bedroom windows open for longer periods. Time of the day, temperature, and relative humidity influence both opening and closing actions. Solar irradiance is also an important driver for open actions, while mean wind speed is significant in predicting closing actions. Data-driven models were developed using logistic regression. Comparison between predicted and real data demonstrated a good performance in estimating the opening ratio over the year and seasonal variations but a tendency to overestimate the number of openings and underestimate the duration of an opening.

Experimental Study on Energy-Free Superhydrophobic Radiative Cooling Versatile Film with Enhanced Environmental Tolerance.

Clean, energy-free methods of cooling are an effective way to respond to the global energy crisis. To date, cooling materials using passive daytime radiative cooling (RC) technology have been applied in the fields of energy-efficient buildings, solar photovoltaic cooling, and insulating textiles. However, RC materials frequently suffer from comprehensive damage to their microstructure, resulting in the loss of their initial cooling effect in complex outdoor environments. Here, a superhydrophobic daytime passive RC porous film with environmental tolerance (SRCP film) was fabricated, which integrated strong solar reflectivity (approximately 90%), mid-infrared emissivity (approximately 0.97), and superhydrophobicity (water contact angle (WCA) of 160° and sliding angle of 3°). This study revealed that SRCP film had an average reflectivity of 14.3% higher than SiO2 particles in the 0.3-2.5 μm wavelength region, achieving a cooling effect of 13.2 °C in ambient conditions with a solar irradiance of 946 W·m-2 and a relative humidity of 74% due to the synergistic effect of effective solar reflection and thermal infrared emission. In addition, empirical results showed that the attained films possessed outstanding environmental tolerance, maintaining high WCA (156°), stable cooling effect (8.3 °C), and low SiO2 loss (less than 5.1%) after 30 consecutive days of UV irradiation and 14 days of corrosion with acidic and alkaline solutions. More importantly, this work could be flexibly prepared by various methods without the use of any fluorine-containing reagents, which greatly widens the practical application scope.

The abundance and distribution of sandflies (with emphasis on Phlebotomus pedifer) (Diptera: Psychodidae) along the altitudinal gradient in Kindo Didaye district, Wolaita Zone, South Ethiopia.

Understanding the distribution patterns of medically significant sandflies is crucial for effective vector and disease control planning. This study focused on investigating the abundance and distribution of phlebotomine sandflies, specifically emphasizing Phlebotomus pedifer (Diptera: Psychodidae), the vector of Leishmania aethiopica responsible for cutaneous leishmaniasis in the highlands of southern Ethiopia. The study employed CDC light traps and sticky paper traps in various habitats, including human houses, farm fields, and rock cliffs, with and without the presence of hyraxes. The study was conducted along an altitudinal gradient in Kindo Didaye district, Wolaita Zone. A total of 7,994 sandflies belonging to 2 genera, Phlebotomus (26.1%) and Sergentomyia (73.9%), were collected. In the genus Phlebotomus, P. pedifer (74.1%) was the most abundant, followed by P. alexandri (18.05%) and P. gibiensis (7.85%). Altitude showed a strong positive association with the density and distribution of P. pedifer and a negative association with those of P. alexandri, P. gibiensis, and Sergentomyia spp. Furthermore, the study revealed distinct habitat preferences, with P. pedifer showing the highest mean density in hyrax dwellings, followed by human houses, and the lowest in farm fields. These findings provide valuable insights for planning targeted control measures against P. pedifer in both indoor and outdoor environments, particularly in the highland and midland areas of the study region.

Characteristic structures of liquid crystal monomers in EI-MS analysis and the potential application in suspect screening

Liquid crystal monomers (LCMs) are of emerging concern due to their ubiquitous presence in indoor and outdoor environments and their potential negative impacts on human health and ecosystems. Suspect screening approaches have been developed to monitor thousands of LCMs that could enter the environment, but an updated suspect list of LCMs is difficult to maintain given the rapid development of material innovations. To facilitate suspect screening for LCMs, in-silico mass fragmentation model and quantitative structure-activity relationship (QSPR) models were applied to predict electron ionization (EI) mass spectra of LCMs. The in-silico model showed limited predictive power for EI mass spectra, while the QSPR models trained with 437 published mass spectra of LCMs achieved an acceptable absolute error of 12 percentage points in predicting the relative intensity of the molecular ion, but failed to predict the mass-to-charge ratio of the base peak. A total of 41 characteristic structures were identified from an updated suspect list of 1606 LCMs. Multi-phenyl groups form the rigid cores of 85% of LCMs and produce 154 characteristic peaks in EI mass spectra. Monitoring the characteristic structures and fragments of LCMs may help identify new LCMs with the same rigid cores as those in the suspect list.

Assessment of Natural Radioactivity Levels and Hazard Indicators in Tarakeshwor Municipality, Nepal through In-situ Technique and Multivariate Analysis

The evaluation of primordial radionuclide concentrations in rapidly urbanized and concrete-laden areas through the importation of construction materials from various regions of Nepal is both important and essential. This study utilized a portable gamma-ray spectrometer (PGIS 2) to analyze the distribution of three natural radionuclides:uranium (238U), thorium (232Th), and potassium (40K) in Tarakeshwor Municipality, Kathmandu, Nepal. The measured dose rates ranged from 70.22 nSv hr−1 to 163.66 nSv hr−1, with an average of 124.65±20.29 nSv hr−1, surpassing the global average of 59 nSv hr−1. The activity concentrations of 40K, 238U, and 232Th exceeded global averages, indicating relatively higher natural radioactivity concentrations in the region. Specifically, the average values for 40K, 238U, and 232Th were 935.26±172.30 Bq kg−1, 80.47±15.53 Bq kg−1, and 80.44±18.58 Bq kg−1, respectively. The calculated radium equivalent (Raeq) ranged from 132.26 to 351.22 Bq kg−1, and the annual gonadal equivalent dose (AGED) varied from 372.61 to 1028.81 μSv yr−1. The annual effective dose rates for indoor and outdoor environments were 0.54±0.09 mSv yr−1 and 0.15±0.03 mSv yr−1, respectively, both exceeding the global average. The representative level index (RLI) within the study area averaged 1.96±0.32, indicating an elevated radiation risk. The excess lifetime cancer risk (ELCR) values for outdoor and indoor environments were 0.52×10−3 ±0.09 ×10−3 and 1.87 ×10−3 ±0.31×10−3, respectively, surpassing the world average. Additionally, external hazard indices (Hex) ranged from 0.36 to 0.59, while internal hazard indices (Hin) ranged from 0.38 to 1.20, both indicating values higher than UNSCEAR recommendations. These findings underscore the necessity for further experimental analysis employing ex-situ equipment. The data generated in this study can provide a valuable baseline for future assessments and interventions in radiation risk management guidelines within the country.

Investigating Training Datasets of Real and Synthetic Images for Outdoor Swimmer Localisation with YOLO

In this study, we developed and explored a methodical image augmentation technique for swimmer localisation in northern German outdoor lake environments. When it comes to enhancing swimmer safety, a main issue we have to deal with is the lack of real-world training data of such outdoor environments. Natural lighting changes, dynamic water textures, and barely visible swimming persons are key issues to address. We account for these difficulties by adopting an effective background removal technique with available training data. This allows us to edit swimmers into natural environment backgrounds for use in subsequent image augmentation. We created 17 training datasets with real images, synthetic images, and a mixture of both to investigate different aspects and characteristics of the proposed approach. The datasets were used to train YOLO architectures for possible future applications in real-time detection. The trained frameworks were then tested and evaluated on outdoor environment imagery acquired using a safety drone to investigate and confirm their usefulness for outdoor swimmer localisation.