Version 36.1.84.16 – Patch Release

We are pleased to introduce VisionLidar v.36.1.84.16, a targeted patch release addressing critical bug fixes and introducing new automation capabilities. This update focuses on stability, compatibility improvements, and processing efficiency.

🛠 Classification by Corridor – Bug Fix

Resolved a critical issue where Classification by Corridor would fail to execute in both VisionLidar 1.2 and VisionLidar 2.0.
Root cause: a malformed PLY file generated during the classification workflow prevented the classification engine from processing the point cloud data.
This fix ensures reliable corridor-based classification results across both engine versions.

📂 E57 File Import – Compatibility Fix

Fixed an issue preventing the import of certain E57 point cloud files into VisionLidar.
The E57 library handling has been updated to better tolerate minor file validation warnings.
Files that were previously rejected can now be imported and processed correctly.

⚡ New: Automated Batch Processing

Introduced a new automated batch processing dialog allowing users to specify a source directory and process all LAS files within it.
Supported operations: Classify, Export LAS, and Update LAS – all without manual, file-by-file interaction.
Particularly beneficial for VisionLidar365 users and large organizations managing hundreds of point cloud files.

🔄 Classification Result Display – Bug Fix

Resolved an intermittent issue where the VCS (View Classification Synchronizer) updater would not refresh class labels in the viewer after a classification task completed.
Users can now reliably see updated classification results immediately after processing.

🖥 CUDA Memory Overflow – Stability Fix

Resolved a critical stability issue on Windows where exhausting CUDA memory during DNN training or classification caused the OS to fall back to Windows shared memory.
This fallback caused the program to stall for an extended period, ultimately either crashing with a memory error (if shared memory was also full) or continuing unreliably.
The fix blocks the shared memory fallback: the input point cloud is now randomly subsampled and retried (up to 100 iterations) until the data fits within available CUDA memory.

Version 36.1.69.10

Version 36.1 arrives like a toolbox upgrade for power users. Precision tightens. Control deepens. Automation becomes negotiable. Let's walk through what's new:

Utilities Analysis – Precision Meets Standards

Utility workflows now move from observation to actionable compliance.

⚡ High-Accuracy Vectorization

Automatic, high-precision vectorization of poles and powerlines
Interactive tools to manually adjust and refine extracted lines
Fully editable geometries

📐 Custom Engineering Standards

Users can now define their own compliance profiles:

Pole tilt threshold
Minimum line-to-ground clearance
Clash detection tolerances

Think of it as giving engineering standards a digital measuring tape.

📊 Pole Tilt Analysis

Flags poles exceeding defined tilt angle
Generates detailed reports including: Geographic location, Measured angle, Area map visualization

No more visual guessing. Every leaning pole is quantified.

📏 Line Clearance Analysis

Computes ground clearance per segment
Highlights non-compliant sections
Produces map-based report with flagged segments and precise locations

It transforms a long transmission corridor into a color-coded compliance dashboard.

🌲 Clash Detection (Vegetation Encroachment)

Detects conflict zones between vegetation and powerlines
Identifies areas requiring trimming
Generates detailed report with attached map

Maintenance planning now starts with data, not field surprises.

Training a New Model – Fine-tuning with VisionLidar 2.0

The "Training a New Model" feature now runs on the VisionLidar 2.0 engine. In this version, it's specifically designed for retraining existing models — letting you fine-tune a pre-trained model on your own labeled data rather than starting from scratch.

🧠 Model Retraining

Customers can:

Select a base model to retrain
Add their own labeled point cloud samples
Define which classes to include or remap

🎛 Flexible Class Management

Add new classes not in the original model
Merge or remap existing classes
Remove classes irrelevant to your workflow

Your model no longer dictates your workflow. Your workflow shapes the model.

New Feature: Line Detection

A new entry in the Analyze section: Line Detection.

Detect linear structures (e.g., road edges, curbs, rails) directly from point cloud data
Uses spatial analysis to identify and extract continuous line features
Outputs editable vector lines for further processing or export

Improvements

Improved performance of LAS/LAZ export
Fixed display issues in the classification panel
Minor UI refinements across several dialogs

Version 35.2

We are pleased to introduce VisionLidar V35.2, a feature-rich update that brings major improvements in design, methodology, and performance.

New Mesh Generation

A completely redesigned mesh generation feature, featuring both a new methodology and a modernized user interface. This update provides greater control, enhanced output quality, and a more intuitive workflow.

Redesigned "Road by Section" Tool

The Road by Section module has been fully revamped with a new UI and workflow, making road modeling more efficient and user-friendly.

Edge Detection Overhaul

Edge detection now benefits from a fresh UI and structural redesign, resulting in clearer results and easier workflow.

New Road Marking Detection Methodology (First Iteration)

This version introduces the first iteration of a new methodology for road marking detection, designed to deliver improved detection accuracy and adaptability to various environments.

Build System Modernization

The internal build system has been migrated to CMake and Qt6, streamlining development, improving maintainability, and simplifying future portability.

Version 35.1

We are excited to introduce VisionLidar V35.1, bringing new features, improvements, and enhanced stability.

LGSx Format: Full support for the LGSx format for both point clouds and spherical images.
Improvements in Automatic Catenary Detection and Vectorization: Refinements to the automatic catenary detection and vectorization features.
Bug Fixes in AI Models and DNN Feature: Several bugs have been fixed in the AI models and deep neural network (DNN) feature.
Redesigned Road Mark Detection: The road mark detection feature has been given a fresh design.
Improved performance and stability: Internal code improvements and optimizations.

Version 35.0

Welcome to VisionLidar365, 2025 R1, version 35.0.

Automatic Classification (Beta)
Creating Groups of the Classes
Informative pop-ups for features
Improved performance and stability

Release notes