Processing LiDAR at the Speed of Light

作者：琳达·达菲（Linda Duffy）

LiDAR data can be too much of a good thing. The newest generation of airborne LiDAR sensors are capable of collecting very dense point clouds that contain critical information for many applications; however, processing and managing these enormous data sets is daunting for beginners and companies that lack the resources to invest in the required computing infrastructure. Long processing times can bog down the entire workflow and delay the most important step – analysing the data and delivering actionable intelligence to the customer to enable decision making.

Aerial LiDAR data

SolSpecis a geospatial data collection, processing and analytics company with unique expertise in remote sensing applications of earth science. This Denver-based company started out offering drone acquisition and processing services, primarily to the oil and gas industry, but soon pivoted to a scalable aerial strategy serving a broad range of customers.

2019年，Solspec购买了一对Leica Terrainmapper线性模式激光雷达传感器带有内置数码相机，可捕获4波段数据（RGB和NIR），并在短时间内覆盖比无人机更短的地面。飞机安装的系统的飞行速度更高，更快，有效地收集了更广阔的区域，并使其成为各种情况的可扩展工具。平均而言，每平方米20点（PPSM）的捕获一日捕获会产生1 TB的高度精确数据。

Solspec的销售和营销副总裁Seth Tribbey说：“通过使用TerrainMapper收集更高的密度，我们为客户提供更好的数据。”“这转化为更有效的分析，以支持所做出的决策。”

High-performance computing technology

After identifying the traditional processing workflow as an obstacle for expedited delivery of information based on aerial LiDAR data, SolSpec realised the cloud offered the opportunity to scale up multiple machines to process data in parallel. To harness the near-infinite computing power of the cloud, the innovative company built the SolSpec Engine on a high-performance computing and machine learning backbone.

Leica HxMap, a multi-sensor platform designed to leverage the benefits of the TerrainMapper data, has an open interface processing workflow that accommodates cloud processing, which is unique in the industry. HxMap can be installed from a single workstation to high end cluster environment with hundreds of nodes for high volume production. The workflow can be orchestrated in different engines using the many command line applications that can be scripted to fulfill various workflows to produce different output products.

当在Amazon Web Services（AWS）云中部署在SOLSPEC引擎顶部时，HXMAP在压缩时间范围内处理大量航空数据。HXMAP在Linux上的AWS云中的部署使SOLSPEC可以快速扩展数据处理能力。该公司将大型机载激光雷达数据集的处理速度提高了60倍，从而降低了后处理成本，并减少了向客户的数据传递时间。此外，通过在SOLSPEC发动机中构建决策分析，SOLSPEC大大缩短了使用LiDAR数据的“决定时间”。

“The flexibility that Hexagon has shown in embracing new technology and the willingness to work with us were main drivers for our partnership,” Tribbey says. “We’ve automated the proprietary TerrainMapper format, taken core libraries and adapted them to run on top of a cloud engine. This structure allows us to go from raw wave-form data to a point cloud to a terrain model in a fraction of the time compared to conventional providers.”

SolSpec Geohazard Analytic is built on machine-learning and trained on 15,000 historic landslides to identify landslide signatures in a digital terrain model even in areas covered by vegetation. Courtesy SolSpec.

Real-life applications

SolSpec的一种旗舰产品是通行权（ROW）完整性管理。管道操作员经常处理诸如滑坡和侵蚀等环境条件，这些环境有可能破裂管道和中断服务。如果有一个厚厚的树冠层掩盖了幻灯片活动，则很难识别出问题。TerrainMapper有效地穿透了树冠，以收集包含大量细节的高密度点云。在处理云中的数据之后，使用机器学习算法来通过顶篷识别危害，从而更快地提醒客户对潜在问题。

Similarly, SolSpec’s vegetation management solutions are highly dependent on rich, high density point clouds combined with the high resolution 4-band spectral data from the TerrainMapper. By leveraging spectral and structural data, SolSpec data scientists have developed algorithms that detect where vegetation is encroaching on powerlines, predict wildfire risk, identify wetlands, classify vegetation types for assessing reclamation activities, and many other applications.

“We have a perfect marriage between the data collection with the TerrainMapper and the processing with HxMap,” says Tribbey. “This allows us to leverage the nearly unlimited computing power on AWS and deliver information incredibly faster.”

SolSpec’s Surface Hydrology Analytic models hydrologic energy and surface flow across high-resolution digital terrain models to accurately identify erosion issues. Courtesy SolSpec.

Streamlining the LiDAR value chain

SolSpec’s ultimate goal is to transform aerial data into actionable risk analysis, decision support and predictive modelling. By combining aerial data and project-specific data with machine learning tools, SolSpec produces comprehensive reports about site conditions more quickly than other providers.

Approximately half of a LiDAR project’s cost is acquiring data, and the other half is processing. A conventional provider may take 30 hours to process 3 square miles of data (20 ppsm, QL1) in the office, while the SolSpec Engine does the same work in 20 minutes in the cloud. Processing with HxMap on the super-fast SolSpec Engine is a key competitive advantage to support time-sensitive decision making.

T亚搏苹果appribbey继续说道：“六边形是我们作为合作伙伴的明显选择，因为它在空中激光雷达行业中的声誉。”“它的传感器和软件非常可靠，并产生出色的结果。”

The combined time savings of processing in the cloud and automating analytics with machine-learning algorithms increases the value of LiDAR data and expands its usefulness to a variety of markets.

“SolSpec helps its customers identify, measure, prioritise and monitor the most common environmental threats to their infrastructure on a recurring basis,” explains Tribbey. “We streamline the entire LiDAR value chain by processing more quickly, managing the data, running the analytics, and providing the answers that customers need. This enables our customers to quickly make decisions about erosion, geohazards, vegetation, encroachment, structures, and more at scale.”