Mapping utility poles using side-view images acquired with car-mounted cameras is a time-consuming task, mainly in larger areas due to the need for street-by-street surveying. Aerial images cover larger areas and can be feasible alternatives although the detection and mapping of the utility poles in urban environments using top-view images is challenging. Thus, we propose the use of Adaptive Training Sample Selection (ATSS) for detecting utility poles in urban areas since it is a novel method and has not yet investigated in remote sensing applications. Here, we compared ATSS with Faster Region-based Convolutional Neural Networks (Faster R-CNN) and Focal Loss for Dense Object Detection (RetinaNet ), currently used in remote sensing applications, to assess the performance of the proposed methodology. We used 99,473 patches of 256 × 256 pixels with ground sample distance (GSD) of 10 cm. The patches were divided into training, validation and test datasets in approximate proportions of 60%, 20% and 20%, respectively. As the utility pole labels are point coordinates and the object detection methods require a bounding box, we assessed the influence of the bounding box size on the ATSS method by varying the dimensions from to pixels. For the proposal task, our findings show that ATSS is, on average, 5% more accurate than Faster R-CNN and RetinaNet. For a bounding box size of , we achieved Average Precision with intersection over union of 50% () of 0.913 for ATSS, 0.875 for Faster R-CNN and 0.874 for RetinaNet. Regarding the influence of the bounding box size on ATSS, our results indicate that the is about 6.5% higher for compared to . For , this margin reaches 23.1% in favor of the bounding box size. In terms of computational costs, all the methods tested remain at the same level, with an average processing time around of 0.048 s per patch. Our findings show that ATSS outperforms other methodologies and is suitable for developing operation tools that can automatically detect and map utility poles.
Both the excess and alteration of bed sediments in river systems can cause socioeconomic and environmental damage; thus, the quantification of bedload transport is an important tool to assess the health of rivers and help in decision-making imposed by the agencies responsible for water resource management. This work aims to evaluate the efficiency of pressure-difference samplers (Helley–Smith) qualitatively and quantitatively when used in environments with sandy characteristics. The experiments were carried out in a stream with full transparency and two pressure-difference samplers with nozzle dimensions of 7.20 × 7.20 cm and 8.89 × 7.50 cm. The Particle Image Velocimetry technique was used to analyze the sampler efficiency simultaneously with an Acoustic Doppler Current Profiler. Qualitative results showed that the way the equipment is allocated at the bottom of the river can generate overestimated or underestimated sediment transport measurements. Additionally, evaluating it quantitatively, we see that the collection efficiency of the equipment varied between 15.45% and 534.78% when compared to the results obtained by the Particle Image Velocimetry technique.