Comprehensive computer vision and image processing using OpenCV WebAssembly.
使用此技能的场景:
openclaw-wasm-sandbox~/.openclaw/skills/opencv/files/opencv-component.wasm```bash
openclaw wasm-sandbox download \
"https://raw.githubusercontent.com/guyoung/wasm-sandbox-openclaw-skills/main/opencv/files/opencv-component.wasm" \
"~/.openclaw/skills/opencv/files/opencv-component.wasm"
```
Use wasm-sandbox-run tool with the WASM file:
wasm-sandbox-run({
wasmFile: "~/.openclaw/skills/opencv/files/opencv-component.wasm",
args: ["<operation>", ...args]
})
For file access, use workDir or mapDir to expose directories to the sandbox.
| Category | Operations |
|---|---|
| ---------- | ----------- |
| Image Process | resize, blur, threshold, morphology, sharpen, crop, stats |
| Detection | cascade, dnn (YOLO), hog, contour, circle, line |
| Features | orb, sift, akaze, match, homography, optflow, template |
| Stitching | panorama, stitch |
| Photo | denoise, inpaint, stylize, hdr, pencil, detail |
| Calibration | chessboard, undistort, corners, pose |
| ML | train-knn, train-svm, predict, kmeans |
| Batch | batch-process, batch-convert, batch-stats |
See references/operations.md for complete operation reference with arguments, examples, and sandbox notes.
共 1 个版本