Object detection
Skill a5c-ai/babysitter/library/specializations/robotics-simulation/skills/object-detection
Deep learning based object detection and segmentation for robotics applicationsFrom its SKILL.md
npx -y skills add a5c-ai/babysitter --skill object-detectionAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
SKILL.md
1.7 KB, 284 tokens by cl100k_base, as published. Nobody here has run it
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
Target Processes
- object-detection-pipeline.js
- synthetic-data-pipeline.js
- nn-model-optimization.js
- moveit-manipulation-planning.js
Dependencies
- YOLO (Ultralytics)
- Detectron2
- TensorRT
- ONNX Runtime
- vision_msgs
Usage Context
This skill is invoked when processes require object detection model deployment, instance segmentation, 3D detection, or multi-object tracking for robot perception.
Output Artifacts
- Detection model configurations
- TensorRT optimized models
- ROS detection node implementations
- Tracking pipeline configurations
- Multi-camera fusion setups
- Inference optimization scripts
What ships with it: 1 file
686 B alongside SKILL.md
- README.md686 B