Abdalrahman
Ibrahim

Header-only C++ library for real-time YOLO inference — detection, segmentation, pose, OBB — no Python, no runtime bloat

• C++17
• ONNX Runtime
• OpenCV
• CUDA
• YOLOv5–v12
• Quantization (INT8/FP16)

Header-only C++ YOLO library for NVIDIA TensorRT — GPU preprocessing, CUDA Graph replay, sub-2ms latency, 530+ FPS

• C++17
• TensorRT ≥10
• CUDA ≥12
• OpenCV
• CUDA Graph

Production-grade ROS2 nodes for YOLO inference — detection, segmentation, pose, OBB, classification with lifecycle management

• C++17
• ROS2 (Humble / Jazzy)
• ONNX Runtime
• OpenCV
• vision_msgs
• sensor_msgs

10 SOTA multi-object trackers in modern C++17 — 10–100× faster than Python, unified API, ONNX ReID backend

• C++17
• ONNX Runtime
• OpenCV
• Eigen3
• ByteTrack
• BoostTrack
• GoogleTest

On-device Vision-Language Model for robotics — SmolVLM2 running via ONNX Runtime inside a ROS2 node for scene understanding and spatial reasoning

• C++17
• Python
• ROS2
• ONNX Runtime
• SmolVLM2
• Transformers

Header-only C++ monocular depth estimation — Depth Anything v2 via ONNX Runtime, real-time on CPU and GPU

• C++17
• ONNX Runtime
• OpenCV
• Depth Anything v2
• CUDA

Single-header C++ point cloud viewer — OpenGL 3.3 rendering, arcball camera, no PCL or Open3D required

• C++17
• OpenGL 3.3
• GLFW
• GLEW

ROS2 C++ package for real-time LiDAR point cloud interpolation — five methods from nearest-neighbour to spline, tested on Velodyne and Ouster

• C++17
• ROS2
• PCL
• Eigen3
• Point Cloud Processing

C++ ROS2 package that exports bag files to images, PCD, IMU, GPS, and CSV — YAML-configured, sqlite3 and MCAP support

• C++17
• ROS2
• rosbag2
• OpenCV
• PCL
• YAML-CPP

On-device text-to-speech in C++ — Kokoro TTS running via ONNX Runtime for low-latency voice synthesis on embedded and robot hardware

• C++17
• ONNX Runtime
• Kokoro TTS
• HiFi-GAN
• Audio Processing