Mapping Utility Poles in Aerial Orthoimages Using ATSS Deep Learning Method

Enhancing grid reliability through advanced insulator defect identification

The article presents an innovative approach for detecting defects in insulators used in high-voltage power transmission lines, employing an enhanced Detection Transformer (DETR) model, termed IF-DETR. The study addresses the significant challenges in traditional insulator defect detection methods, such as the loss of small defect features and confusion with background features. Firstly, we propose a multi-scale backbone network to better extract features of small objects. Secondly, as the contextual information surrounding objects plays a critical role in detecting small objects, we introduce a fusion module composed of ECA-Net and SAU to replace the original attention module for improved contextual information extraction. Lastly, we introduce the insulator defect (IDIoU) loss to optimize the instability in the matching process caused by small defects. Extensive experiments demonstrate the model's effectiveness, particularly in detecting small defects, marking a notable advancement in insulator defect detection technology. The IF-DETR achieved a 2.3% increase in AP compared to existing advanced methods. This method not only enhances the accuracy of defect detection, crucial for maintaining the reliability and safety of power transmission systems but also has broader implications for the maintenance and inspection of high-voltage power infrastructure.

A deep learning approach based on graphs to detect plantation lines

Identifying plantation lines in aerial images of agricultural landscapes is re-quired for many automatic farming processes. Deep learning-based networks are among the most prominent methods to learn such patterns and extract this type of information from diverse imagery conditions. However, even state-of-the-art methods may stumble in complex plantation patterns. Here, we propose a deep learning approach based on graphs to detect plantation lines in UAV-based RGB imagery, presenting a challenging scenario containing spaced plants. The first module of our method extracts a feature map throughout the backbone, which consists of the initial layers of the VGG16. This feature map is used as an input to the Knowledge Estimation Module (KEM), organized in three concatenated branches for detecting 1) the plant positions, 2) the plantation lines, and 3) the displacement vectors between the plants. A graph modeling is applied considering each plant position on the image as vertices, and edges are formed between two vertices (i.e. plants). Finally, the edge is classified as pertaining to a certain plantation line based on three probabilities (higher than 0.5): i) in visual features obtained from the backbone; ii) a chance that the edge pixels belong to a line, from the KEM step; and iii) an alignment of the displacement vectors with the edge, also from the KEM step. Experiments were conducted initially in corn plantations with different growth stages and patterns with aerial RGB imagery to present the advantages of adopting each module. We assessed the generalization capability in the other two cultures (orange and eucalyptus) datasets. The proposed method was compared against state-of-the-art deep learning methods and achieved superior performance with a significant margin considering all three datasets. This approach is useful in extracting lines with spaced plantation patterns and could be implemented in scenarios where plantation gaps occur, generating lines with few-to-no interruptions.

Geospatial mapping of distribution grid with machine learning and publicly-accessible multi-modal data

Detailed and location-aware distribution grid information is a prerequisite for various power system applications such as renewable energy integration, wildfire risk assessment, and infrastructure planning. However, a generalizable and scalable approach to obtain such information is still lacking. In this work, we develop a machine-learning-based framework to map both overhead and underground distribution grids using widely-available multi-modal data including street view images, road networks, and building maps. Benchmarked against the utility-owned distribution grid map in California, our framework achieves > 80% precision and recall on average in the geospatial mapping of grids. The framework developed with the California data can be transferred to Sub-Saharan Africa and maintain the same level of precision without fine-tuning, demonstrating its generalizability. Furthermore, our framework achieves a R2 of 0.63 in measuring the fraction of underground power lines at the aggregate level for estimating grid exposure to wildfires. We offer the framework as an open tool for mapping and analyzing distribution grids solely based on publicly-accessible data to support the construction and maintenance of reliable and clean energy systems around the world.

Active Fire Mapping on Brazilian Pantanal Based on Deep Learning and CBERS 04A Imagery

Fire in Brazilian Pantanal represents a serious threat to biodiversity. The Brazilian National Institute of Spatial Research (INPE) has a program named Queimadas, which estimated from January 2020 to October 2020, a burned area in Pantanal of approximately 40,606 km2. This program also provides daily data of active fire (fires spots) from a methodology that uses MODIS (Aqua and Terra) sensor data as reference satellites, which presents limitations mainly when dealing with small active fires. Remote sensing researches on active fire dynamics have contributed to wildfire comprehension, despite generally applying low spatial resolution data. Convolutional Neural Networks (CNN) associated with high- and medium-resolution remote sensing data may provide a complementary strategy to small active fire detection. We propose an approach based on object detection methods to map active fire in the Pantanal. In this approach, a post-processing strategy is adopted based on Non-Max Suppression (NMS) to reduce the number of highly overlapped detections. Extensive experiments were conducted, generating 150 models, as five-folds were considered. We generate a public dataset with 775-RGB image patches from the Wide Field Imager (WFI) sensor onboard the China Brazil Earth Resources Satellite (CBERS) 4A. The patches resulted from 49 images acquired from May to August 2020 and present a spatial and temporal resolutions of 55 m and five days, respectively. The proposed approach uses a point (active fire) to generate squared bounding boxes. Our findings indicate that accurate results were achieved, even considering recent images from 2021, showing the generalization capability of our models to complement other researches and wildfire databases such as the current program Queimadas in detecting active fire in this complex environment. The approach may be extended and evaluated in other environmental conditions worldwide where active fire detection is still a required information in fire fighting and rescue initiatives.

Benchmarking Anchor-Based and Anchor-Free State-of-the-Art Deep Learning Methods for Individual Tree Detection in RGB High-Resolution Images

Urban forests contribute to maintaining livability and increase the resilience of cities in the face of population growth and climate change. Information about the geographical distribution of individual trees is essential for the proper management of these systems. RGB high-resolution aerial images have emerged as a cheap and efficient source of data, although detecting and mapping single trees in an urban environment is a challenging task. Thus, we propose the evaluation of novel methods for single tree crown detection, as most of these methods have not been investigated in remote sensing applications. A total of 21 methods were investigated, including anchor-based (one and two-stage) and anchor-free state-of-the-art deep-learning methods. We used two orthoimages divided into 220 non-overlapping patches of 512 × 512 pixels with a ground sample distance (GSD) of 10 cm. The orthoimages were manually annotated, and 3382 single tree crowns were identified as the ground-truth. Our findings show that the anchor-free detectors achieved the best average performance with an AP50 of 0.686. We observed that the two-stage anchor-based and anchor-free methods showed better performance for this task, emphasizing the FSAF, Double Heads, CARAFE, ATSS, and FoveaBox models. RetinaNet, which is currently commonly applied in remote sensing, did not show satisfactory performance, and Faster R-CNN had lower results than the best methods but with no statistically significant difference. Our findings contribute to a better understanding of the performance of novel deep-learning methods in remote sensing applications and could be used as an indicator of the most suitable methods in such applications.