Ewenwan/ORB_SLAM2_SSD_Semantic

Health v2 · maintenance only

Flags: no_releases no_license

Adoption not part of the score

1574 stars · 435 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

A C++ research project extending ORB_SLAM2 with dynamic object detection and semantic mapping. It combines SSD-based object detection (MobileNetV2-SSD-Lite), optical flow and multi-view geometry for dynamic point filtering, and OctoMap-based semantic 3D map construction with an object database.

Use cases

• build a semantic 3D map from RGB-D camera streams
• run SLAM in dynamic environments with moving people or objects
• detect and track objects in 3D during SLAM
• filter dynamic feature points using optical flow and multi-view geometry
• save and reload ORB-SLAM2 and OctoMap maps
• generate colored point cloud maps with object bounding boxes

When to choose

• you need a research baseline for dynamic semantic SLAM with RGB-D cameras
• you want to combine object detection with visual SLAM and OctoMap mapping
• you are studying how to filter dynamic features in SLAM

When to avoid

• you need a production-ready or well-maintained SLAM system
• you require a permissively licensed project (no license is provided)
• you need monocular-only or LiDAR-based SLAM support
• you want plug-and-play installation without ROS and CUDA setup

Facets

library · maturity maintenance

computer-vision image-processing machine-learning simulation robotics computer-vision autonomous-vehicles artificial-intelligence cpp slam semantic-slam dynamic-slam orb-slam2 object-detection ssd octomap point-cloud rgb-d robotics 3d-mapping research-code linux ros

Member repositories

For agents

markdown · JSON · MCP: product_card(name="Ewenwan/ORB_SLAM2_SSD_Semantic")