API Reference — People Analytics

Manajemen Pipeline

Endpoint untuk membuat, memantau, dan menghapus pipeline People Analytics. Setiap pipeline diidentifikasi oleh kombinasi node_num, stream_id, dan analytic_id.

Gunakan NFV4-MPA untuk analitik counting/dwelling/density tanpa atribut, atau NFV4-MPAA untuk menambahkan attribute classification (usia, gender, masker, kacamata, penutup kepala, warna pakaian).

curl -X POST "http://localhost:4004/pipeline/0/stream_001/NFV4-MPA" \  -H "Content-Type: application/json" \  -d '{    "object_confidence_threshold": 0.53,    "sub_analytics": [      {        "name": "counting",        "is_active": true,        "dumping_sampling_time": 500,        "lines": [          {            "id": "entrance",            "name": "Main Entrance",            "points": [              [                0.2,                0.5              ],              [                0.8,                0.5              ]            ],            "direction": "both"          }        ]      },      {        "name": "roi_counting",        "is_active": false      },      {        "name": "dwelling",        "is_active": false      },      {        "name": "density",        "is_active": false      }    ]  }'

{  "code": 200,  "message": "Pipeline created successfully",  "data": {    "pipeline_id": "NFV4-MPA",    "stream_id": "stream_001",    "status": "running"  }}

{  "code": 400,  "message": "Invalid configuration: lines array is required for counting"}

curl -X GET "http://localhost:4004/pipeline/0/stream_001/NFV4-MPA"

{  "code": 200,  "data": {    "analytic_id": "NFV4-MPA",    "stream_id": "stream_001",    "status": "running",    "uptime_seconds": 3600,    "processed_frames": 25200  }}

{  "code": 404,  "message": "Pipeline not found"}

curl -X DELETE "http://localhost:4004/pipeline/0/stream_001/NFV4-MPA"

{  "code": 200,  "message": "Pipeline deleted successfully"}

{  "code": 404,  "message": "Pipeline not found"}

Konfigurasi Pipeline

Endpoint untuk memperbarui parameter pipeline yang sedang berjalan tanpa perlu me-restart. Berguna untuk menyesuaikan threshold, mengaktifkan/menonaktifkan sub-analytics, atau mengubah posisi garis dan zona secara dinamis.

curl -X PUT "http://localhost:4004/pipeline/0/stream_001/NFV4-MPA/config" \  -H "Content-Type: application/json" \  -d '{    "object_confidence_threshold": 0.6,    "sub_analytics": [      {        "name": "counting",        "is_active": true,        "object_confidence_threshold": 0.6      }    ]  }'

{  "code": 200,  "message": "Configuration updated successfully"}

{  "code": 400,  "message": "Cannot update configuration: invalid parameter value"}

Visual Output

Endpoint untuk mendapatkan output visual dari pipeline yang berjalan — berguna untuk verifikasi konfigurasi garis counting dan polygon ROI.

curl -X GET "http://localhost:4004/pipeline/0/stream_001/NFV4-MPA/mjpeg"

"string"

curl -X GET "http://localhost:4004/pipeline/0/stream_001/NFV4-MPA/snapshot"

"string"

Event Streaming (WebSocket)

Visionaire4 mengirim setiap event hasil deteksi/inferensi melalui WebSocket. Untuk berlangganan event yang dihasilkan oleh pipeline People Analytics pada stream tertentu, buka koneksi WebSocket ke endpoint berikut:

ws://<host>:4004/event_channel/{node_num}/{stream_id}/NFV4-MPA

Setelah koneksi terbuka, server akan langsung mendorong (push) setiap event ke client tanpa perlu handshake atau pesan subscribe. Tutup koneksi untuk berhenti menerima event.

Parameter Path

Query Parameter (Opsional)

Format Pesan

Setiap event yang diterima berbentuk JSON dengan struktur berikut:

{
  "event_id": "evt_123456",
  "stream_id": "<stream_id>",
  "analytic_id": "NFV4-MPA",
  "node_num": 0,
  "timestamp_ms": 1674123456789,
  "primary_text": "5 people detected",
  "secondary_text": "Zone A",
  "pipeline_data": {
    /* field spesifik module — lihat "Output yang Dihasilkan" pada index.mdx */
  },
  "image_jpeg": "base64-encoded JPEG..."
}

Detail field pipeline_data untuk People Analytics dijelaskan pada Output yang Dihasilkan di halaman utama.

Contoh Koneksi

const ws = new WebSocket(
  'ws://localhost:4004/event_channel/0/<stream_id>/NFV4-MPA'
);

ws.onmessage = (msg) => {
  const event = JSON.parse(msg.data);
  console.log(event.primary_text, event.pipeline_data);
};

ws.onerror = (err) => console.error('WebSocket error', err);
ws.onclose = () => console.log('Disconnected');

import asyncio
import json
import websockets

async def listen():
    url = "ws://localhost:4004/event_channel/0/<stream_id>/NFV4-MPA"
    async with websockets.connect(url) as ws:
        async for msg in ws:
            event = json.loads(msg)
            print(event["primary_text"], event["pipeline_data"])

asyncio.run(listen())

Filter Berdasarkan Logic

Jika pipeline menjalankan beberapa logic rule (misalnya line-counting, ROI density), Anda dapat memfilter event hanya untuk satu logic dengan menambahkan query parameter:

ws://<host>:4004/event_channel/{node_num}/{stream_id}/NFV4-MPA?logic=<logic_name>

Endpoint Channel Lainnya

Untuk mendengarkan event yang lebih luas (lintas analitik atau lintas stream), gunakan endpoint berikut yang dijelaskan pada Developer Guide: