Agent Skills
› SharpAI/DeepCamera
› depth-estimation
depth-estimation
GitHub基于Depth Anything v2实现实时单目深度估计，支持macOS CoreML与PyTorch后端。提供隐私匿名化（隐藏身份保留布局）、深度叠加及3D场景理解功能，适用于安防监控等视觉处理场景。
Trigger Scenarios
需要实时视频流深度图生成
启用摄像头隐私匿名化模式
进行3D空间布局分析
Install
npx skills add SharpAI/DeepCamera --skill depth-estimation -g -y
SKILL.md
Frontmatter
{
"name": "depth-estimation",
"version": "1.2.0",
"category": "privacy",
"parameters": [
{
"name": "model",
"type": "select",
"group": "Model",
"label": "Depth Model",
"default": "depth-anything-v2-small",
"options": [
"depth-anything-v2-small",
"depth-anything-v2-base",
"depth-anything-v2-large"
]
},
{
"name": "variant",
"type": "select",
"group": "Model",
"label": "CoreML Variant (macOS)",
"default": "DepthAnythingV2SmallF16",
"options": [
"DepthAnythingV2SmallF16",
"DepthAnythingV2SmallF16INT8",
"DepthAnythingV2SmallF32"
]
},
{
"name": "blend_mode",
"type": "select",
"group": "Display",
"label": "Display Mode",
"default": "depth_only",
"options": [
"depth_only",
"overlay",
"side_by_side"
]
},
{
"max": 1,
"min": 0,
"name": "opacity",
"type": "number",
"group": "Display",
"label": "Overlay Opacity",
"default": 0.5
},
{
"name": "colormap",
"type": "select",
"group": "Display",
"label": "Depth Colormap",
"default": "viridis",
"options": [
"inferno",
"viridis",
"plasma",
"magma",
"jet",
"turbo",
"hot",
"cool"
]
},
{
"name": "device",
"type": "select",
"group": "Performance",
"label": "Device",
"default": "auto",
"options": [
"auto",
"cpu",
"cuda",
"mps"
]
}
],
"description": "Real-time depth map privacy transforms using Depth Anything v2 (CoreML + PyTorch)",
"capabilities": {
"live_transform": {
"script": "scripts\/transform.py",
"description": "Real-time depth estimation overlay on live feed"
}
}
}
Depth Estimation (Privacy)
Real-time monocular depth estimation using Depth Anything v2. Transforms camera feeds with colorized depth maps — near objects appear warm, far objects appear cool.
When used for privacy mode, the depth_only blend mode fully anonymizes the scene while preserving spatial layout and activity, enabling security monitoring without revealing identities.
Hardware Backends
| Platform | Backend | Runtime | Model |
|---|---|---|---|
| macOS | CoreML | Apple Neural Engine | apple/coreml-depth-anything-v2-small (.mlpackage) |
| Linux/Windows | PyTorch | CUDA / CPU | depth-anything/Depth-Anything-V2-Small (.pth) |
On macOS, CoreML runs on the Neural Engine, leaving the GPU free for other tasks. The model is auto-downloaded from HuggingFace and stored at ~/.aegis-ai/models/feature-extraction/.
What You Get
- Privacy anonymization — depth-only mode hides all visual identity
- Depth overlays on live camera feeds
- 3D scene understanding — spatial layout of the scene
- CoreML acceleration — Neural Engine on Apple Silicon (3-5x faster than MPS)
Interface: TransformSkillBase
This skill implements the TransformSkillBase interface. Any new privacy skill can be created by subclassing TransformSkillBase and implementing two methods:
from transform_base import TransformSkillBase
class MyPrivacySkill(TransformSkillBase):
def load_model(self, config):
# Load your model, return {"model": "...", "device": "..."}
...
def transform_frame(self, image, metadata):
# Transform BGR image, return BGR image
...
Protocol
Aegis → Skill (stdin)
{"event": "frame", "frame_id": "cam1_1710001", "camera_id": "front_door", "frame_path": "/tmp/frame.jpg", "timestamp": "..."}
{"command": "config-update", "config": {"opacity": 0.8, "blend_mode": "overlay"}}
{"command": "stop"}
Skill → Aegis (stdout)
{"event": "ready", "model": "coreml-DepthAnythingV2SmallF16", "device": "neural_engine", "backend": "coreml"}
{"event": "transform", "frame_id": "cam1_1710001", "camera_id": "front_door", "transform_data": "<base64 JPEG>"}
{"event": "perf_stats", "total_frames": 50, "timings_ms": {"transform": {"avg": 12.5, ...}}}
Setup
python3 -m venv .venv && source .venv/bin/activate
pip install -r requirements.txt
Version History
- 2264fcb Current 2026-08-20 16:01
