🎁 Get the FREE AI Skills Starter Guide β€” Subscribe β†’
BytesAgainBytesAgain
BytesAgain β€Ί Skills β€Ί Spikecv Helper
πŸ¦€ ClawHub

Spikecv Helper

by @lhs183019

Help AI Agents answer questions and execute tasks for SpikeCV, an ultra-high-speed spike camera vision framework. Use when the user asks about spike cameras,...

Versionv1.0.2
Downloads365
Installs1
Stars⭐ 2
#legal#hr#productivity
TERMINAL
clawhub install spikecv-helper

πŸ“– About This Skill

name: spikecv-helper description: Help AI Agents answer questions and execute tasks for SpikeCV, an ultra-high-speed spike camera vision framework. Use when the user asks about spike cameras, SpikeCV repository, spike dataset download, running vision task like tracking, reconstruction through spike vision, etc.

SpikeCV Agent Skill

*last updated: 2026-04-28*

This document is designed to equip an AI Agent (or developer) with the necessary prior knowledge and instructions to answer questions and execute tasks within the SpikeCV repository.

Any command execution or conceptual question should be informed by the context in this document and the attached references.

> Before reading: If you're unfamiliar with spike cameras or SpikeCV's architecture, first read references/About_SpikeCV.md.

🧭 Quick Lookup

Use this table to jump to the right section. If it's not here, the answer isn't in this skill.

| You want... | Go to... | |---|---| | What is SpikeCV? | references/About_SpikeCV.md | | Install SpikeCV | Β§ Installation | | SpikeCV API docs | spikecv.readthedocs.io | | SpikeCV Project directory structure | Β§ Project Layout | | Run spikecv CLI (download, track, reconst) | Β§ CLI Reference | | Full publication list (up-to-date) | spikecv.github.io/publications.html | | Algorithm and it's theory | search for docs/source/ζ ΈεΏƒζ“δ½œ.rst πŸ‡¨πŸ‡³ or source code under SpikeCV/spkProc/ πŸ‡¬πŸ‡§ SpikeCV/examples πŸ‡¬πŸ‡§, you might get it wrong, so notify user to look up the details in publication for exact theory | | SpikeCV event, competition, Team contact, contribution, hardware | references/About_SpikeCV.md | | Dataset descriptions | references/About_SpikeCV.md | | Troubleshooting | Β§ Gotchas & Common Errors |

Not in this skill? β†’ Defer to the user or suggest SpikeCV website and SpikeCV team contact (spikecv@outlook.com).

πŸ“¦ Installation

Prerequisites:

  • Python β‰₯ 3.10
  • Python virtual environment (Conda recommended): see install_miniconda.md for a step-by-step setup guide from scratch.

    • git clone https://github.com/Zyj061/SpikeCV
cd SpikeCV
pip install .[cli]

    Optional extras: 

    pip install .[tracking]   # for SNNTracker/SpikeSORT

    Verify: 

    spikecv --help

    Quick health check (downloads ~40 MB and runs TFSTP reconstruction): 

    spikecv data download --dataset recVidarReal2019 --agent-used
cd datasets/
spikecv proc reconst --agent-used

    πŸ›  CLI Reference

    SpikeCV provides the spikecv command for wrapper interactions. After installation, you can use it to download datasets and run processing algorithms.

    All commands accept --agent-used to return structured JSON output. Always include this flag.

    > Note: Feel free to explore other CLI options and parameters as needed. The following examples only showcase partial subcommands and parameters, the CLI may support additional features or algorithms. Always refer to --help for the most up-to-date command options and usage instructions.

    spikecv data download

    Download a dataset from the OpenI platform:

    spikecv data download --dataset  --local-dir  --agent-used
    | Dataset | For Task | |---|---| | recVidarReal2019 | Reconstruction | | motVidarReal2020 | Tracking |

    ⚠️ Path gotcha: Data lands in //. Default local-dir is datasets/, so your dat files end up at datasets/recVidarReal2019/classA/car-100kmh.dat, NOT recVidarReal2019/classA/car-100kmh.dat.

    spikecv proc reconst

    Reconstruct visible images from a raw .dat spike stream. Default algorithm: TFSTP.

    # From the datasets/ directory:
cd datasets/
spikecv proc reconst --dat-file-path recVidarReal2019/classA/car-100kmh.dat --agent-used
    Or with an absolute/explicit path:
    
spikecv proc reconst --dat-file-path /path/to/recVidarReal2019/classA/car-100kmh.dat \
                     --yaml-file-path /path/to/recVidarReal2019/config.yaml \
                     --agent-used

    Key parameters:

  • --dat-file-path: Path to .dat spike stream file
  • --yaml-file-path: Path to config.yaml for the dataset (default: recVidarReal2019/config.yaml)
  • --begin-idx: Starting frame index (default: 500)
  • --block-len: How many spike frames to process (default: 1500)
  • --stp-d, --stp-F, --stp-f: STP model parameters

    • ⚠️ Path gotcha: The default yaml-file-path is recVidarReal2019/config.yaml (relative to cwd). If you download the dataset using the CLI, it lives under datasets/recVidarReal2019/. You must either cd datasets/ first or pass explicit paths.

    spikecv proc track

    Run multi-object tracking on spike data. Default algorithm: SNNTracker.

    spikecv proc track --scene-idx 0 --metrics --agent-used

    Key parameters:

  • --scene-idx: Scene index 0–6
  • --metrics: (Optional) Calculate MOTA/IDF1 metrics (requires ground truth labels)

    • ⚠️ Dataset: Tracking uses motVidarReal2020, not recVidarReal2019.

    πŸ“ Project Layout

    SpikeCV/
β”œβ”€β”€ SpikeCV/
β”‚   β”œβ”€β”€ cli/               # CLI command definitions (typer)
β”‚   β”œβ”€β”€ device/            # Hardware driver for spike cameras
β”‚   β”œβ”€β”€ examples/          # Standalone test scripts (NOT for agent use, use CLI instead)
β”‚   β”œβ”€β”€ metrics/           # Quantitative evaluation (PSNR, SSIM, MOTA, IDF1, AEPE)
β”‚   β”œβ”€β”€ spkData/           # Data loaders + config.yaml parsing
β”‚   β”‚   └── load_dat.py    # ParaDict generation, SpikeStream class
β”‚   β”œβ”€β”€ spkProc/           # ⭐ Core algorithms
β”‚   β”‚   β”œβ”€β”€ filters/       # STP filter (background removal)
β”‚   β”‚   β”œβ”€β”€ reconstruction/ # TFI, TFP, TFSTP, SSML
β”‚   β”‚   β”œβ”€β”€ tracking/      # SNNTracker, SpikeSORT
β”‚   β”‚   β”œβ”€β”€ detection/     # STDP, Motion-based detection
β”‚   β”‚   β”œβ”€β”€ recognition/   # RPSNet, SVM, VGG
β”‚   β”‚   β”œβ”€β”€ depth_estimation/ # SpikeT (Transformer)
β”‚   β”‚   β”œβ”€β”€ optical_flow/  # SCFlow
β”‚   β”‚   └── augment/       # Data augmentation
β”‚   β”œβ”€β”€ utils/             # Path helpers
β”‚   └── visualization/     # Video generation from spikes
β”œβ”€β”€ docs/
β”‚   β”œβ”€β”€ spike_algo.md      # deprecated
β”‚   β”œβ”€β”€ data_processing.md # deprecated
β”‚   β”œβ”€β”€ tools.md           # deprecated
β”‚   β”œβ”€β”€ examples.md        # deprecated
β”‚   └── source/            # πŸ‡¨πŸ‡³ Sphinx sources (readthedocs)
β”œβ”€β”€ Publications.md        # πŸ“„ Publication list (may be stale β€” use website instead)
β”œβ”€β”€ README.md / README_en.md
└── CONTRIBUTING.md / CONTRIBUTING_en.md

    🌐 Documentation by Language

    | File(s) | Language | Best for | |---|---|---| | docs/source/*.rst | πŸ‡¨πŸ‡³ Chinese | API, little Algorithm theory, code examples | | SpikeCV/spkProc/**/*.py (source code) | πŸ‡¬πŸ‡§ English | Algorithm math + implementation details | | README_en.md, CONTRIBUTING_en.md | πŸ‡¬πŸ‡§ English | Setup, contribution workflow | | Publications.md | πŸ‡¬πŸ‡§ English | Publication list (stale β€” see website) |

    🚨 Rules (SHOULD NOT DO)

    These are not suggestions β€” following them prevents errors and hallucinations:

    1. Use CLI, not example scripts β€” If a task has a spikecv CLI command, use it. Do NOT run SpikeCV/examples/test_snntracker.py or similar standalone scripts directly. 2. Always include --agent-used β€” Otherwise the CLI prints log text, not structured JSON. 3. Do not modify SpikeCV code β€” Suggest the user contact the team instead (spikecv@outlook.com). 4. Do not hallucinate external resources β€” For contacts, purchases, or contributions, only use info from references/About_SpikeCV.md. 5. For publication/paper queries β†’ always use the website β€” Publications.md in the repo may be outdated. Point to spikecv.github.io/publications.html as the canonical source.

    πŸ› Gotchas & Common Errors

    | Symptom | Cause | Fix | |---|---|---| | "Data path '...config.yaml' does not exist" | --yaml-file-path is relative but you're not in the right directory | cd datasets/ first, or pass full path | | spikecv proc track fails | Wrong dataset β€” using recVidarReal2019 instead of motVidarReal2020 | Download correct dataset first | | --scene-idx out of range | motVidarReal2020 only has scenes 0–6 | Use a value in [0, 6] | | --scene-idx in range but still broken | some of the scene data might not have uploaded by the developer, check carefully if the corresponding scene appear in the downloaded dataset | don't use the scene that's not downloaded | | spikecv not found | CLI not installed or not in PATH | Run pip install .[cli] from SpikeCV root | | --agent-used not working (no JSON output) | Using an older SpikeCV version | Update to latest, or check spikecv --help for flag name |