Object Detection/Segmentation Skill

Overview

Expert skill for deploying and optimizing deep learning models for object detection, instance segmentation, and 3D object detection in robotics applications.

Capabilities

• Configure YOLO (v5, v8) for real-time detection
• Set up Detectron2 for instance segmentation
• Implement semantic segmentation models
• Configure TensorRT optimization for Jetson
• Set up ONNX runtime deployment
• Implement 3D object detection (PointPillars, VoxelNet)
• Configure depth-based object detection
• Set up ROS vision pipelines with image_pipeline
• Implement object tracking (SORT, DeepSORT, ByteTrack)
• Configure multi-camera detection fusion