Vehicle Detection and Attribution from a Multi-Sensor Dataset Using a Rule-Based Approach Combined with Data Fusion.

Vehicle detection using data fusion techniques from overhead platforms (RGB/MSI imagery and LiDAR point clouds) with vector and shape data can be a powerful tool in a variety of fields, including, but not limited to, national security, disaster relief efforts, and traffic monitoring. Knowing the location and number of vehicles in a given area can provide insight into the surrounding activities and patterns of life, as well as support decision-making processes. While researchers have developed many approaches to tackling this problem, few have exploited the multi-data approach with a classical technique. In this paper, a primarily LiDAR-based method supported by RGB/MSI imagery and road network shapefiles has been developed to detect stationary vehicles. The addition of imagery and road networks, when available, offers an improved classification of points from LiDAR data and helps to reduce false positives. Furthermore, detected vehicles can be assigned various 3D, relational, and spectral attributes, as well as height profiles. This method was evaluated on the Houston, TX dataset provided by the IEEE 2018 GRSS Data Fusion Contest, which includes 1476 ground truth vehicles from LiDAR data. On this dataset, the algorithm achieved a 92% precision and 92% recall. It was also evaluated on the Vaihingen, Germany dataset provided by ISPRS, as well as data simulated using an image generation model called DIRSIG. Some known limitations of the algorithm include false positives caused by low vegetation and the inability to detect vehicles (1) in extremely close proximity with high precision and (2) from low-density point clouds.

Cloud shading and fog drip influence the metabolism of a coastal pine ecosystem.

Assessing the ecological importance of clouds has substantial implications for our basic understanding of ecosystems and for predicting how they will respond to a changing climate. This study was conducted in a coastal Bishop pine forest ecosystem that experiences regular cycles of stratus cloud cover and inundation in summer. Our objective was to understand how these clouds impact ecosystem metabolism by contrasting two sites along a gradient of summer stratus cover. The site that was under cloud cover ~15% more of the summer daytime hours had lower air temperatures and evaporation rates, higher soil moisture content, and received more frequent fog drip inputs than the site with less cloud cover. These cloud-driven differences in environmental conditions translated into large differences in plant and microbial activity. Pine trees at the site with greater cloud cover exhibited less water stress in summer, larger basal area growth, and greater rates of sap velocity. The difference in basal area growth between the two sites was largely due to summer growth. Microbial metabolism was highly responsive to fog drip, illustrated by an observed ~3-fold increase in microbial biomass C with increasing summer fog drip. In addition, the site with more cloud cover had greater total soil respiration and a larger fractional contribution from heterotrophic sources. We conclude that clouds are important to the ecological functioning of these coastal forests, providing summer shading and cooling that relieve pine and microbial drought stress as well as regular moisture inputs that elevate plant and microbial metabolism. These findings are important for understanding how these and other seasonally dry coastal ecosystems will respond to predicted changes in stratus cover, rainfall, and temperature.