Imou Multimodal Analysis
AI scene analysis for device channel snapshot URLs (or any image URL) under an Imou account: human detection, smoking detection, phone-using detection, workwear and absence detection (with pre-configured workwear repository), shelf detection, trash detection, heatmap statistics, and face analysis. Also manage detect repositories and targets (create/list/delete repository; add/list/delete targets).
Quick Start
Install dependency:
pip install requests
Set environment variables (required):
export IMOU_APP_ID="your_app_id"
export IMOU_APP_SECRET="your_app_secret"
export IMOU_BASE_URL="your_base_url"
API Base URL (IMOU_BASE_URL) (required; no default—must be set explicitly):
| Region | Data Center | Base URL |
|---|
| Mainland China | — | https://openapi.lechange.cn |
| Overseas | East Asia | https://openapi-sg.easy4ip.com:443 |
| Overseas | Central Europe | https://openapi-fk.easy4ip.com:443 |
| Overseas | Western America | https://openapi-or.easy4ip.com:443 |
Note: AI APIs are value-added; apply for access via Imou if needed.
Run analysis on an image URL (e.g. device channel snapshot from live coverUrl or any accessible URL):
# Human detection
python3 {baseDir}/scripts/multimodal_analysis.py analyze HUMAN "https://example.com/snapshot.jpg"
# Smoking detection
python3 {baseDir}/scripts/multimodal_analysis.py analyze SMOKING "https://example.com/snapshot.jpg"
# Phone-using detection
python3 {baseDir}/scripts/multimodal_analysis.py analyze PHONE "https://example.com/snapshot.jpg"
# Workwear detection (optional repositoryId and threshold)
python3 {baseDir}/scripts/multimodal_analysis.py analyze WEAR "https://example.com/snapshot.jpg" [--repository-id REPO_ID] [--threshold 0.8]
# Absence detection (requires workwear repositoryId)
python3 {baseDir}/scripts/multimodal_analysis.py analyze ABSENCE "https://example.com/snapshot.jpg" --repository-id REPO_ID [--threshold 0.8]
# Shelf detection
python3 {baseDir}/scripts/multimodal_analysis.py analyze SHELF "https://example.com/snapshot.jpg"
# Trash detection
python3 {baseDir}/scripts/multimodal_analysis.py analyze TRASH "https://example.com/snapshot.jpg"
# Heatmap (threshold required; optional exclude repository IDs)
python3 {baseDir}/scripts/multimodal_analysis.py analyze HEATMAP "https://example.com/snapshot.jpg" --threshold 0.8 [--exclude-repos ID1,ID2]
# Face analysis
python3 {baseDir}/scripts/multimodal_analysis.py analyze FACE "https://example.com/snapshot.jpg"
Repository and target management:
# Create detect repository (face | human for workwear)
python3 {baseDir}/scripts/multimodal_analysis.py repo create "MyWorkwearLib" human
# List repositories (paginated)
python3 {baseDir}/scripts/multimodal_analysis.py repo list [--page 1] [--page-size 20]
# Delete repository
python3 {baseDir}/scripts/multimodal_analysis.py repo delete REPOSITORY_ID
# Add target to repository (image URL or base64 type)
python3 {baseDir}/scripts/multimodal_analysis.py target add REPOSITORY_ID "TargetName" "https://image.url" [--type url]
python3 {baseDir}/scripts/multimodal_analysis.py target add REPOSITORY_ID "TargetName" "BASE64_DATA" --type base64
# List targets in repository
python3 {baseDir}/scripts/multimodal_analysis.py target list REPOSITORY_ID [--page 1] [--page-size 20]
# Delete target from repository
python3 {baseDir}/scripts/multimodal_analysis.py target delete REPOSITORY_ID TARGET_ID
Capabilities
- Human detection: Detect whether the image contains human figure(s).
- Smoking detection: Detect whether someone is smoking in the image.
- Phone-using detection: Detect whether someone is using a phone.
- Workwear detection: Detect whether personnel are in compliance with workwear (optional workwear repository and threshold).
- Absence detection: Detect absence from post (requires pre-configured workwear repository).
- Shelf detection: Detect shelf status (e.g. empty/full).
- Trash detection: Detect trash overflow.
- Heatmap: Get heatmap statistics for regions (threshold required; optional exclude repository IDs to filter by workwear).
- Face analysis: Face detection/analysis.
- Detect repository: Create (face/human), list by page, delete.
- Target in repository: Add (URL or Base64), list by page, delete.
Request Header
All requests to Imou Open API must include the header Client-Type: OpenClaw for platform identification.
API References
See references/imou-ai-api.md for request/response formats.
Tips
- Token: Fetched automatically per run; valid 3 days. Do not cache across runs unless you implement expiry handling.
- Image input: Use
type "0" for image URL, "1" for Base64. Snapshot URL can be device channel live cover URL (e.g. from imou-open-device-video skill liveList / bindDeviceLive streams[].coverUrl) or any accessible image URL.
- Workwear / Absence: Create a human-type repository first, add workwear target images, then pass
repositoryId to workwearDetect and absenceDetect.
- Heatmap:
threshold in (0,1]. Use excludeRepositoryIds to exclude matched workwear persons (e.g. staff) and count only valid customers.
- detectRegion: Optional; up to 3 regions, each 3–6 points (normalized 0–1). Omit to analyze full image.
Data Outflow
| Data | Sent to | Purpose |
|---|
| appId, appSecret | Imou Open API | Obtain accessToken |
| accessToken, image URL or Base64, repositoryId, threshold, etc. | Imou Open API | AI detection and repository/target management |
All requests go to the configured IMOU_BASE_URL. No other third parties.
