Zvinyorwa zvinyorwa

I indoor mepu system

Yakazara tekinoroji referensi yeSee U yemukati yekumisikidza system: architecture, sensors, algorithms, APIs, uye gwara rekushandisa.

Dhaunirodha yakazara PDF

← Kudzokera kumepu

Kufamba nekukurumidza

Muhtasari Usanifu Sensorer Ama-algorithms I-API Utekelezaji

Muhtasari

Nhanganyaya kuhurongwa hwemepu

Chii chinonzi See U indoor mepu system?

Iyo See U indoor system ipuratifomu yakavharika yekumisikidza iyo inosanganisa matanhatu masensa tekinoroji layer ine advanced fusion kuti ibudise nzvimbo chaiyo iyo GPS isingawanikwe.

Kusiyana neWi‑Fi- kana zvigadzirwa zveBluetooth-chete, isu tinoshandisa multimodal stack inosanganisira:

Magnetic geolocation: Yakasarudzika magineti "fingerprint" yechivakwa chese
Wi‑Fi RTT: Nguva-yendege inotangira nhambwe chaidzo
Bluetooth LE: Mabhekoni ezvibatiso nenzvimbo dzekufarira
Inertial sensors: Kufa kuverenga neIMU yepamusoro-soro
Kuona kwekombuta: SLAM uye mamakisi ekuona
GNSS: Smooth indoor-outdoor shanduko

99%

Kururama kwenzvimbo

1–2 m kurongeka mu99% yemakesi ekutsvaga nzira yakachengeteka

<100ms

Kunonoka

Real-time inogadziridza ine pasi pe100 ms end-to-end latency

Tabaka za sensor

Kusanganisa matekinoroji mazhinji ekuvimbika uye nemazvo

Usanifu wa mfumo

Chimiro uye zvikamu zvikuru

Zvivakwa zvekuvaka zvivakwa

1. Data yekuunganidza layer

Inoburitsa data raw kubva kune ese ma sensors emudziyo munguva chaiyo.

• Vatyairi vemunyika (iOS / Android)
• Udhibiti wa kiwango cha sampuli
• Data buffering ye batch fusion
• Kuwiriranisa kwechitambi chenguva

2. Safu ya usindikaji

Mafirita, anojairisa, uye anogadzirira data yekubatanidza.

• Vichujio vya pasi ya chini na pasi ya juu
• Urekebishaji otomatiki
• Kuonekwa uye kubvisa kunze
• Kugadzirisa uye kuwedzera

3. Safu ya fusion ya sensor

Inosanganisa akawanda masosi neazvino nzira dzekusanganisa.

• Kichujio cha chembe (uwezekano)
• Yakawedzerwa Kalman yekutsvedzerera
• Uzani unaobadilika kwa kila sensor
• Kuonekwa kwemukati / kunze kwemamiriro ezvinhu

4. Kuweka safu

Inoverengera yekupedzisira pamepu mushandisi chinzvimbo.

• Kuenderana nemepu
• Nyora kuzvikamu zvenzira zvinoshanda
• Floor / level yekuona
• Kusaruramisa

5. Safu ya urambazaji

Kuronga nzira uye kutendeuka-ne-kutendeuka kuraira.

• A* ine uremu hwekusvikika
• Audio murayiridzo chizvarwa
• Uelekezaji upya wa nguvu
• chenjedzo dzekuva pedyo kune POIs

6. Safu ya interface

MaAPI uye maSDK ekubatanidzwa kweapp.

• REST yewebhu nemasevha
• SDK Asilia (iOS na Android)
• Masasisho ya moja kwa moja ya WebSocket
• Webhooks for chinzvimbo zviitiko

Tabaka za sensor

Zvetekinoroji pachikamu

Tabaka la 1

Jiografia ya sumaku

I-magnetometer ye-3-eksisiUsahihi: 1-2 m

Mepu Earth munda uye chivakwa-chinokonzeresa anomalies. Chimiro chega chega chine yakasarudzika magineti zvigunwe.

Zvido zvehunyanzvi:

Muenzaniso chiyero: 50-100 Hz
Kugadzirisa: 0.01 µT
Urekebishaji otomatiki unaoendelea
Kupindira muripo

Tabaka la 2

I-Wi-Fi RTT

IEEE 802.11mcUsahihi: 1-3 m

Nguva-yekubhururuka Wi-Fi inotangira kusvika kunzvimbo dzekuwana. Inoda mudziyo uye zvivakwa RTT rutsigiro.

Zvido zvehunyanzvi:

Itifaki: IEEE 802.11mc (Wi-Fi RTT)
Mabhendi: 2.4 uye 5 GHz
Latency: <100 ms
Kanenge 3 APs ye triangulation

Tabaka la 3

Nishati ya Chini ya Bluetooth (BLE)

BLE 5.0+ mabhekoniUsahihi: 2-5 m

Mabhekoni ekuswedera, kutungamira, POIs, uye waypoints.

Zvido zvehunyanzvi:

Itifaki: BLE 5.0+
RSSI (yakagamuchira simba rechiratidzo)
Bhatiri: 2-5 makore
Range: kusvika ku100 m

Tabaka la 4

Kitengo cha kipimo cha inertial (IMU)

I-Accelerometer + gyro + barometerUsahihi: Kuverenga kwakafa

IMU inovhara mafambiro, kutenderera, uye urefu hwekuvharisa maburi pakati pemareferensi.

Zvido zvehunyanzvi:

Accelerometer: ± 16 g, 400 Hz
I-Gyro: ±2000°/s, 400 Hz
Baro: 0.5 m pasi kureba
Ukudibanisa: Kalman

Tabaka la 5

Maono ya Kompyuta (CV)

Kamera + AI/MLUsahihi: Visual kugadzirisa

Inooneka inowana maficha, mamaki eAR, QR, uye zvinyorwa zvekugadzirisa chinzvimbo uye SLAM.

Zvido zvehunyanzvi:

SLAM: panguva imwe chete yenzvimbo & mepu
Kuonekwa kwezvinhu: ORB, SIFT
AR mamaki: ArUco, QR
Nguva yekumhanya: TensorFlow Lite

Tabaka la 6

GNSS / GPS (kunze)

I-GPS + GLONASS + GalileoUsahihi: 5-10 m

Satellite chinzvimbo chekunze uye chemukati-kunze handover uye drift control.

Zvido zvehunyanzvi:

I-Multi-GNSS: GPS, GLONASS, Galileo, BeiDou
A-GPS yekukurumidza TTFF
Otomatiki mukati / kunze
Yakasanganiswa nemamwe maseru

Ama-algorithms

Processing uye njere

Mchanganyiko wa Multisensor

Particle sefa (Monte Carlo)

Mazhinji akaremerwa zvimedu anoteedzera anonyanya kushandiswa mushandisi kubva kune akawanda ane ruzha sensors.

Kulainisha trajectory

Yakawedzerwa Kalman sefa

Recursively inofungidzira a dynamic system ine ruzha rwekupinda; inoshandiswa kuita nzira dzakatsetseka uye kufanotaura kwenguva pfupi.

Kuelekeza

A * kutsvaga nzira

Inowana nzira ipfupi ine zvipingaidzo, kuwanikwa, uye zvido zvevashandisi sehuremu.

Kuona mepu

I-SLAM

Inovaka mepu uye inoteedzera chishandiso chiri mairi nezvinooneka.

Adaptive kudzidza

Kudzidza kwemichina (neural network)

Mamodheru akadzidziswa kurongedza nharaunda, denoise data, uye kugadzirisa huchokwadi nekufamba kwenguva.

Urambazaji usio na mawimbi

Kuverenga kwakafa

Paridza pose kubva pakugadzirisa kwekupedzisira uchishandisa velocity uye musoro kana redhiyo inogadzirisa inodonha.

Processing kuyerera

Kukamata data

Masensa anoburitsa zviyero zvakabikwa munguva chaiyo

Inachakata mapema

Kusefa, kuenzanisa, uye normalization

Mchanganyiko wa sensor

Particle sefa inosanganisa masosi ese

Kalman sefa

Inotsvedza uye inofanotaura mafambiro

Mepu inoenderana

Projekti pamepu inogona kuchinjika

Pozi la pato

Yakafumurwa kuapp pamusoro peAPI

I-REST API

Endpoints uye kubatanidzwa

URL ya msingi

https://api.seeu.app/v1

GET

/api/v1/positioning

Inodzosa chimiro chazvino chemudziyo

Vigezo:

device_idvenue_idfloor

POST

/api/v1/navigation/route

Ronga nzira pakati pemapoinzi maviri

Vigezo:

origindestinationaccessibility_mode

GET

/api/v1/venues/{id}/map

Tora mataira emepu yenzvimbo

Vigezo:

venue_idfloorformat

GET

/api/v1/pois

Nyora nzvimbo dzaunofarira dziri pedyo

Vigezo:

latlngradiuscategory

POST

/api/v1/tracking/update

Tumira sensor batch ye server-side fusion

Vigezo:

sensor_datatimestampdevice_id

Muenzaniso chikumbiro

curl -X POST https://api.seeu.app/v1/navigation/route \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "origin": {
      "lat": -23.550520,
      "lng": -46.633308,
      "floor": 1
    },
    "destination": {
      "lat": -23.551234,
      "lng": -46.634567,
      "floor": 2
    },
    "accessibility_mode": true
  }'

Mwongozo wa utekelezaji

Nzira yekubatanidza stack

1. System zvinodiwa

iOS

• iOS 14.0+
• Mwepesi 5.5+
• I-CoreLocation
• I-CoreMotion
• ARKit (hiari)

Android

• I-Android 8.0+ (API 26)
• Kotlin 1.7+
• Masevhisi eGoogle Play
• API ya kihisi cha Android
• ARCore (si lazima)

2. SDK kuisa

iOS (CocoaPods)

pod 'SeeUMapping', '~> 1.0'

I-Android (Gradle)

implementation 'app.seeu:mapping:1.0.0'

3. Kutanga

// Swift
import SeeUMapping

let mapping = SeeUMapping(apiKey: "YOUR_API_KEY")
mapping.configure(
    venueId: "shopping-center-xyz",
    enableMagneticPositioning: true,
    enableWiFiRTT: true,
    enableBLE: true
)

mapping.startPositioning { result in
    switch result {
    case .success(let position):
        print("Lat: \(position.lat), Lng: \(position.lng)")
    case .failure(let error):
        print("Error: \(error)")
    }
}

4. Urambazaji

mapping.calculateRoute(
    from: currentPosition,
    to: destination,
    accessibilityMode: true
) { route in
    mapping.startNavigation(route: route) { instruction in
        // turn-by-turn instructions
        print(instruction.text)
        speakInstruction(instruction.audio)
    }
}

Unoda rumwe ruzivo?

Chikwata chedu cheinjiniya chinogona kubatsira nekubatanidza, kuburitsa-kunze, uye netsigiro yakazvipira.

curl -X POST https://api.seeu.app/v1/navigation/route \ -H "Authorization: Bearer YOUR_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "origin": { "lat": -23.550520, "lng": -46.633308, "floor": 1 }, "destination": { "lat": -23.551234, "lng": -46.634567, "floor": 2 }, "accessibility_mode": true }'

// Swift import SeeUMapping let mapping = SeeUMapping(apiKey: "YOUR_API_KEY") mapping.configure( venueId: "shopping-center-xyz", enableMagneticPositioning: true, enableWiFiRTT: true, enableBLE: true ) mapping.startPositioning { result in switch result { case .success(let position): print("Lat: \(position.lat), Lng: \(position.lng)") case .failure(let error): print("Error: \(error)") } }

mapping.calculateRoute( from: currentPosition, to: destination, accessibilityMode: true ) { route in mapping.startNavigation(route: route) { instruction in // turn-by-turn instructions print(instruction.text) speakInstruction(instruction.audio) } }

I indoor mepu system

Kufamba nekukurumidza

Muhtasari

Chii chinonzi See U indoor mepu system?

Usanifu wa mfumo

Zvivakwa zvekuvaka zvivakwa

1. Data yekuunganidza layer

2. Safu ya usindikaji

3. Safu ya fusion ya sensor

4. Kuweka safu

5. Safu ya urambazaji

6. Safu ya interface

Tabaka za sensor

Jiografia ya sumaku

Zvido zvehunyanzvi:

I-Wi-Fi RTT

Zvido zvehunyanzvi:

Nishati ya Chini ya Bluetooth (BLE)

Zvido zvehunyanzvi:

Kitengo cha kipimo cha inertial (IMU)

Zvido zvehunyanzvi:

Maono ya Kompyuta (CV)

Zvido zvehunyanzvi:

GNSS / GPS (kunze)

Zvido zvehunyanzvi:

Ama-algorithms

Particle sefa (Monte Carlo)

Yakawedzerwa Kalman sefa

A * kutsvaga nzira

I-SLAM

Kudzidza kwemichina (neural network)

Kuverenga kwakafa

Processing kuyerera

I-REST API

URL ya msingi

Muenzaniso chikumbiro

Mwongozo wa utekelezaji

1. System zvinodiwa

iOS

Android

2. SDK kuisa

iOS (CocoaPods)

I-Android (Gradle)

3. Kutanga

4. Urambazaji

Unoda rumwe ruzivo?

Loading...

I indoor mepu system

Kufamba nekukurumidza

Muhtasari

Chii chinonzi See U indoor mepu system?

Usanifu wa mfumo

Zvivakwa zvekuvaka zvivakwa

1. Data yekuunganidza layer

2. Safu ya usindikaji

3. Safu ya fusion ya sensor

4. Kuweka safu

5. Safu ya urambazaji

6. Safu ya interface

Tabaka za sensor

Jiografia ya sumaku

Zvido zvehunyanzvi:

I-Wi-Fi RTT

Zvido zvehunyanzvi:

Nishati ya Chini ya Bluetooth (BLE)

Zvido zvehunyanzvi:

Kitengo cha kipimo cha inertial (IMU)

Zvido zvehunyanzvi:

Maono ya Kompyuta (CV)

Zvido zvehunyanzvi:

GNSS / GPS (kunze)

Zvido zvehunyanzvi:

Ama-algorithms

Particle sefa (Monte Carlo)

Yakawedzerwa Kalman sefa

A * kutsvaga nzira

I-SLAM

Kudzidza kwemichina (neural network)

Kuverenga kwakafa

Processing kuyerera