How AI and LiDAR are transforming control points in construction projects.

Today marks a significant milestone in the evolution of total station #technology.   Leica Geosystems part of Hexagon is introducing the Leica TS20 #robotic total station, powered by advanced edge #AI, to progress #automation in #surveying.    Based on decades of #innovation and industry-leading expertise, the Leica TS20 was designed and engineered with a deep understanding of the modern surveyor’s workflow. It accelerates fieldwork, simplifies daily tasks, streamlines repetitive work, prevents costly errors, and can withstand some of the harshest weather conditions without jeopardising productivity.   Our newly added AI capabilities, combined with Leica’s unmatched quality, will set a new standard unlike anything the industry has seen before. It will enable the Leica TS20 to optimise workflows autonomously, identify potential mistakes before they happen, and ensure reliable #measurements while safeguarding #data privacy – all of which are essential to achieving operational efficiency with #precision and accuracy.    The Leica TS20 has been created with our customers at its core. With insights gained directly from surveying practitioners, we’re ensuring that every element of this product meets real-world needs.   Having studied surveying, this launch is deeply personal because it serves as a reminder of where my journey began and how far the #industry has progressed.   Discover more: https://lnkd.in/dB2ipqfP Hexagon Geosystems, Hexagon AB

Leica TS20 robotic total station with edge AI. 👉 Accurate, precise, reliable: Decades expertise in measurement technologies delivering precision and accuracy surveyors can trust, even in demanding conditions. 👉 AI-powered automation: Advanced edge AI minimises errors, speeds up work, and safeguards data privacy. 👉 Seamless connectivity & enhanced security: Integrated cloud access for collaboration plus effective theft deterrence technology. #BeReady #LeicaGeosystemspartofHexagon #topgeocart Learn more: https://hxgn.biz/3ViDPam

A SHORT COURSE on INTELLIGENT FLIGHT CONTROL, Part 8 Least-Squares Estimation -------------------------------------------- Optimization methods presented previously assume that the state, control, and disturbance are known precisely. Measurements of an actual system used for feedback control may be incomplete or contain error. We take a 3-step approach to presenting the optimal state estimator for a linear, time-invariant (LTI) dynamic system before moving toward nonlinear estimation and its effect on intelligent control. A least-squares estimate (LSE) of a constant vector processes redundant measurements to compute the corresponding mean vector and standard-deviation matrix. The LSE assumes that there is no prior information about a vector's probability distribution. The estimate may assume that the uncertainty of each data point is equal or that some measurements are better than others. A batch process analyzes all points in a single calculation. The method can be used to interpolate between known points on a function, a process called Wiener–Kolmogorov Interpolation or "Kriging." New data can be added by recursive estimation, which introduces optimal estimation of a dynamic state vector. With constant estimation error matrix, R, the error covariance decreases at each step. Each new sample has smaller effect on the average than the sample before. Consequently, the estimator gain matrix, K-sub-k, approaches zero as the number of samples increases. When the varying state of a dynamic system is considered, K-sub-k does not go to zero, as presented next. ----- Reference . https://lnkd.in/eGSesEED . Section 4.1, Least-Squares Estimates of Constant Vectors, https://lnkd.in/enHjaWtp. . Google AI Overview of Recent Advances in Least-Squares Estimation (see addendum below the graphic) . Parts 1 to 7 can be found in previous LinkedIn posts =====

Intergeo Day 1 takeaways for field efficiency: • Mobility: compact, collapsible accessories reduce travel cost & setup time • Simplicity: emerging network-only rovers (like Juniper Spire) streamline training and rollouts • Automation: LiDAR auto-classification is maturing toward production use • Optionality: exploring non-DJI drone ecosystems to broaden procurement choices Follow for days 2 & 3. Happy to share deeper notes—DM us. https://lnkd.in/gFMgfxaN #Geospatial #Surveying #AEC #RealityCapture #FieldOps #Intergeo

📢 📢 📢  Dynamic Multiple Object Segmentation with Spatio-Temporal Filtering 🧑🔬 Wenguang Yang, Kan Ren, Minjie Wan, Xiaofang Kong, and Weixian Qian 🏫 Nanjing University of Science and Technology 💥 This article primarily focuses on the localization and extraction of multiple moving objects in images taken from a moving camera platform, such as image sequences captured by drones. The positions of moving objects in the images are influenced by both the camera’s motion and the movement of the objects themselves, while the background position in the images is related to the camera’s motion. The main objective of this article was to extract all moving objects from the background in an image. We first constructed a motion feature space containing motion distance and direction, to map the trajectories of feature points. Subsequently, we employed a clustering algorithm based on trajectory distinctiveness to differentiate between moving objects and the background, as well as feature points corresponding to different moving objects. The pixels between the feature points were then designated as source points. Within local regions, complete moving objects were segmented by identifying these pixels. We validated the algorithm on some sequences in the Video Verification of Identity (VIVID) program database and compared it with relevant algorithms. The experimental results demonstrated that, in the test sequences when the feature point trajectories exceed 10 frames, there was a significant difference in the feature space between the feature points on the moving objects and those on the background. Correctly classified frames with feature points accounted for 67% of the total frames.The positions of the moving objects in the images were accurately localized, with an average IOU value of 0.76 and an average contour accuracy of 0.57. This indicated that our algorithm effectively localized and segmented the moving objects in images captured by moving cameras. https://lnkd.in/gtrahRgx

It's incredible to see how quickly technology is changing the way we manage the intersection of nature and infrastructure. For anyone responsible for critical assets like power lines, railways, or roads, the challenge is constant: how do you effectively monitor thousands of kilometers of corridors where vegetation is always growing? The traditional approach of manual inspections is not only time-consuming and expensive but can also be hazardous for the teams on the ground. We often talk about a bird's-eye view, but now we can truly have it, and with an intelligence that was unimaginable just a few years ago. The combination of high-resolution drone imagery and advanced AI is fundamentally shifting this entire process from being reactive to proactive. Instead of just finding problems, we can now predict them. This isn't just about spotting a tree that's too close to a power line. It's about analyzing the health of entire stretches of vegetation, identifying at-risk trees before they fall, and creating data-driven maintenance plans that optimize resources and drastically improve safety and reliability. This shift gives asset managers the precise insights they need to act strategically, ensuring the lights stay on and our infrastructure remains secure. It’s a powerful example of how we can work smarter, not harder, by leveraging technology to understand and manage our environment. How is your organization using new data sources to get ahead of maintenance and risk? #VegetationManagement #Infrastructure #AI #DroneTech #GeospatialData #Utilities #RiskManagement #Innovation #Arboair

🌊 AI Meets the Ocean: Transforming the Marine Industry with Data 🌊 From autonomous ships to ocean floor mapping, AI is revolutionizing the marine industry — but it all begins with one thing: data. At Dserve AI, we help marine technology companies access high-quality, domain-specific datasets that power applications like: ⚓ Ship detection and tracking using satellite imagery 🐋 Marine life monitoring through computer vision 🌍 Oceanographic data analysis for environmental studies 🚢 Predictive maintenance for vessels and offshore equipment With our custom dataset creation, annotation, and validation services, we ensure your AI models navigate smoothly — no rough seas of data noise. Let’s build smarter oceans together 🌐 🔗 Explore our datasets: www.dserveai.com/datasets 📩 Get in touch: info@dserveai.com #DserveAI #MarineAI #ComputerVision #DataAnnotation #AIDatasets #machinelearning #datasets

Learning to Generate 4D LiDAR Sequences https://lnkd.in/eUZ3Y_Jn While generative world models have advanced video and occupancy-based data synthesis, LiDAR generation remains underexplored despite its importance for accurate 3D perception. Extending generation to 4D LiDAR data introduces challenges in controllability, temporal stability, and evaluation. We present LiDARCrafter, a unified framework that converts free-form language into editable LiDAR sequences. Instructions are parsed into ego-centric scene graphs, which a tri-branch diffusion model transforms into object layouts, trajectories, and shapes. A range-image diffusion model generates the initial scan, and an autoregressive module extends it into a temporally coherent sequence. The explicit layout design further supports object-level editing, such as insertion or relocation. To enable fair assessment, we provide EvalSuite, a benchmark spanning scene-, object-, and sequence-level metrics. On nuScenes, LiDARCrafter achieves state-of-the-art fidelity, controllability, and temporal consistency, offering a foundation for LiDAR-based simulation and data augmentation. --- Newsletter https://lnkd.in/emCkRuA More story https://lnkd.in/enY7VpM LinkedIn https://lnkd.in/ehrfPYQ6 #AINewsClips #AI #ML #ArtificialIntelligence #MachineLearning #ComputerVision

The next generation of schedulers will use AI, BIM, and drone data to predict progress before it happens. If you’re in construction, it’s time to level up. Learn more: https://lnkd.in/gJGJjkj4 #ConstructionTech #DigitalConstruction #SchedulerLife #ProjectControls #FutureOfConstruction #BoomAndBucket #TrustInIron #ConstructionInnovation #EngineeringLeaders #ConstructionTrends

"AI is becoming the quiet co-pilot on the bridge, helping crews navigate smarter and cleaner." AI is beginning to transform navigation; not by replacing crews, but by empowering them with real-time insights, smarter routing, and predictive foresight. From reducing human error to cutting fuel costs and supporting climate goals, the potential is huge. With our ESA-supported feasibility study project AURAN, we’re putting this vision into practice: an AI-powered navigation co-pilot designed to reduce stress on crews while enabling safer, cleaner, and more compliant voyages. Check out our latest article, where we explore how AI-powered navigation can help the industry move toward safer, cleaner, and more resilient operations; step by step, with humans firmly in the loop. https://lnkd.in/d85JGSHC