Explore the vast range of titles available.

During the armed conflict in Colombia, homemade improvised antipersonnel landmines were used to neutralize the adversary. Many active artifacts remain buried, causing damage to biodiversity by exploding. The extensive literature describes the effects and injuries caused to humans by conventional landmines. However, there is considerably less information on the behavior and effects of homemade antipersonnel landmines on fauna and good field investigation practices. Our objectives were to describe the characteristics of a controlled explosion of a homemade antipersonnel landmine (using ammonium nitrate as an explosive substance), to compare the effectiveness of some evidence search patterns used in forensic investigation, and to determine the effects on a piece of an animal carcass. The explosion generated a shock wave and an exothermic reaction, generating physical effects on the ground and surrounding structures near the point of explosion. The amputation of the foot in direct contact with the device during the explosion and multiple fractures were the main effects on the animal carcass. Finally, it was determined that finding evidence was more effective in a smaller search area. Many factors can influence the results, which must be weighed when interpreting the results, as discussed in this manuscript.

This paper presents a pioneering study in the application of real-time surface landmine detection using a combination of robotics and deep learning. We introduce a novel system integrated within a demining robot, capable of detecting landmines in real time with high recall. Utilizing YOLOv8 models, we leverage both optical imaging and artificial intelligence to identify two common types of surface landmines: PFM-1 (butterfly) and PMA-2 (starfish with tripwire). Our system runs at 2 FPS on a mobile device missing at most 1.6% of targets. It demonstrates significant advancements in operational speed and autonomy, surpassing conventional methods while being compatible with other approaches like UAV. In addition to the proposed system, we release two datasets with remarkable differences in landmine and background colors, built to train and test the model performances.

This work presents an enhanced autonomous airborne Synthetic Aperture Radar (SAR) imaging system able to provide full 3D radar images from the subsurface. The proposed prototype and methodology allow the safe detection of both metallic and non-metallic buried targets even in difficult-to-access scenarios without interacting with the ground. Thus, they are particularly suitable for detecting dangerous targets, such as landmines and Improvised Explosive Devices (IEDs). The prototype is mainly composed by an Ultra-Wide-Band (UWB) radar module working from Ultra-High-Frequency (UHF) band and a high accuracy dual-band Real Time Kinematic (RTK) positioning system mounted on board an Unmanned Aerial Vehicle (UAV). The UAV autonomously flies over the region of interest, gathering radar measurements. These measurements are accurately geo-referred so as to enable their coherent combination to obtain a well-focused SAR image. Improvements in the processing chain are also presented in order to deal with some issues associated to UAV-based measurements (such as non-uniform acquisition grids) as well as to enhance the resolution and the signal to clutter ratio of the image. Both the prototype and the methodology were validated with measurements, showing their capability to provide high-resolution 3D SAR images.

Autonomous weapons guided by artificial intelligence are already in use. Researchers, legal experts and ethicists are struggling with what should be allowed on the battlefield. Autonomous weapons guided by artificial intelligence are already in use. Researchers, legal experts and ethicists are struggling with what should be allowed on the battlefield.

Why did you do this work?Drowning is a leading cause of child accidental death, with a 22% increase in drownings in Wales in 2023, compared to the 2016–2018 average (Water Safety Wales, 2023). Those with epilepsy and Autism, particularly those with significant intellectual impairment, are at increased risk of drowning (Denny et al., 2019). Swimming should be included in the Health and Wellbeing Area of Learning during primary education in Wales, to improve water safety and promote lifelong sport (Swim Wales, 2024).What did you do?We conducted an evaluation of families’ experiences with community and specialist swimming lessons amongst children with disabilities accessing a specialist swimming program. Sparkle and Disability Sport Wales evaluated specialist swimming lessons which take place in a hydrotherapy pool at Serennu Children’s Centre. All children have 1:1 support in the water, in addition to trained disability swim instructors and lifeguards. Parents/carers (72) of children with conditions including ASD, ADHD, Cerebral Palsy and Down Syndrome (aged 5–17 years) were invited to participate; 58 took part in a survey at the beginning and end of a 10-week block of lessons, tailored to the children’s swimming abilities. Families were also asked to share their previous experiences of school or community-based swimming lessons.What did you find?Barriers to community-based swimming lessons for their child with a disability were reported by 81% of parents/carers. These barriers included a lack of staff training and understanding; inappropriate environments and facilities; children being explicitly denied access to community and school lessons due to their complex needs.The evaluation found small improvements to water safety and swimming ability following 10 specialist lessons. Improvements related to confidence, enjoyment of water and a positive impact on family wellbeing was also found. Among parents/carers, 95% said their child enjoyed water, and participants described greater opportunities for their families related to exercise, social interaction and quality family time following this block of lessons.What does it mean?Accidental drownings in Wales almost double those of the UK (Water Safety Wales, 2020). Swimming, a potentially lifesaving skill, is critically important for children lacking an awareness of danger. Clear recommendations from this evaluation relate to equity of access for disabled children. An appropriate pool environment, tailored focus of lessons, suitable equipment and facilities, and the level of support offered at specialist lessons should be provided in school/community settings for children with disabilities or learning difficulties.ReferencesDenny S A, Quan L, Gilchrist J, et al. AAP council on injury, violence, and poison prevention. Prevention of drowning. Pediatrics 2019;143(5). https://static1.squarespace.com/static/5d1bf693cbbe87000194cc34/t/5d92548f37ce1d2592a7eaa3/1569870993380/AAP-Drowning.full.pdfSwim Wales. (2024). Nofio Ysgol. Retrieved from https://www.swimwales.org/learn-to-swim-wales/nofio-ysgol/Water Safety Wales. (2020). Drowning Prevention Strategy. Retrieved from https://nationalwatersafety.org.uk/wales/drowning-prevention-strategyWater Safety Wales. (2023). WAID 2023 Summary for Water Safety Wales. Retrieved from https://nationalwatersafety.org.uk/media/1405/waid-wales-2023-summary.pdf

Recent advances in unmanned-aerial-vehicle- (UAV-) based remote sensing utilizing lightweight multispectral and thermal infrared sensors allow for rapid wide-area landmine contamination detection and mapping surveys. We present results of a study focused on developing and testing an automated technique of remote landmine detection and identification of scatterable antipersonnel landmines in wide-area surveys. Our methodology is calibrated for the detection of scatterable plastic landmines which utilize a liquid explosive encapsulated in a polyethylene or plastic body in their design. We base our findings on analysis of multispectral and thermal datasets collected by an automated UAV-survey system featuring scattered PFM-1-type landmines as test objects and present results of an effort to automate landmine detection, relying on supervised learning algorithms using a Faster Regional-Convolutional Neural Network (Faster R-CNN). The RGB visible light Faster R-CNN demo yielded a 99.3% testing accuracy for a partially withheld testing set and 71.5% testing accuracy for a completely withheld testing set. Across multiple test environments, using centimeter scale accurate georeferenced datasets paired with Faster R-CNN, allowed for accurate automated detection of test PFM-1 landmines. This method can be calibrated to other types of scatterable antipersonnel mines in future trials to aid humanitarian demining initiatives. With millions of remnant PFM-1 and similar scatterable plastic mines across post-conflict regions and considerable stockpiles of these landmines posing long-term humanitarian and economic threats to impacted communities, our methodology could considerably aid in efforts to demine impacted regions.

Existing frameworks for classifying the fidelity for object detection tasks do not consider false positive likelihood and object uniqueness. Inspired by the Detection, Recognition, Identification (DRI) framework proposed by Johnson 1958, we propose a new modified framework that defines three categories as visible anomaly, identifiable anomaly, and unique identifiable anomaly (AIU) as determined by human interpretation of imagery or geophysical data. These categories are designed to better capture false positive rates and emphasize the importance of identifying unique versus non-unique targets compared to the DRI Index. We then analyze visual, thermal, and multispectral UAV imagery collected over a seeded minefield and apply the AIU Index for the landmine detection use-case. We find that RGB imagery provided the most value per pixel, achieving a 100% identifiable anomaly rate at 125 pixels on target, and the highest unique target classification compared to thermal and multispectral imaging for the detection and identification of surface landmines and UXO. We also investigate how the AIU Index can be applied to machine learning for the selection of training data and informing the required action to take after object detection bounding boxes are predicted. Overall, the anomaly, identifiable anomaly, and unique identifiable anomaly index prescribes essential context for false-positive-sensitive or resolution-poor object detection tasks with applications in modality comparison, machine learning, and remote sensing data acquisition.

An important consideration for UAV-based (unmanned aerial vehicle) object detection in the natural environment is vegetation height and foliar cover, which can visually obscure the items a machine learning model is trained to detect. Hence, the accuracy of aerial detection of objects such as surface landmines and UXO (unexploded ordnance) is highly dependent on the height and density of vegetation in a given area. In this study, we develop a model that estimates the detection accuracy (recall) of a YOLOv8 object’s detection implementation as a function of occlusion due to vegetation coverage. To solve this function, we developed an algorithm to extract vegetation height and coverage of the UAV imagery from a digital surface model generated using structure-from-motion (SfM) photogrammetry. We find the relationship between recall and percent occlusion is well modeled by a sigmoid function using the PFM-1 landmine test case. Applying the sigmoid recall-occlusion relationship in conjunction with our vegetation cover algorithm to solve for percent occlusion, we mapped the uncertainty in detection rate due to vegetation in UAV-based SfM orthomosaics in eight different minefield environments. This methodology and model have significant implications for determining the optimal location and time of year for UAV-based object detection tasks and quantifying the uncertainty of deep learning object detection models in the natural environment.