Options
All
  • Public
  • Public/Protected
  • All
Menu

Class Human

Human library main class

All methods and properties are available only as members of Human class

  • Configuration object definition: Config
  • Results object definition: Result
  • Possible inputs: Input
param

Config

Hierarchy

  • Human

Index

Constructors

Properties

Methods

Constructors

constructor

  • new Human(userConfig?: Config | Record<string, unknown>): Human

  • Creates instance of Human library that is futher used for all operations

    Parameters

    • Optional userConfig: Config | Record<string, unknown>

    Returns Human

Properties

classes

classes: { body: __module | __module | __module; centernet: __module; emotion: __module; facemesh: __module; faceres: __module; hand: __module; nanodet: __module }
internal:

Currently loaded classes

Type declaration

  • body: __module | __module | __module
  • centernet: __module
  • emotion: __module
  • facemesh: __module
  • faceres: __module
  • hand: __module
  • nanodet: __module

config

config: Config

Current configuration

draw

draw: { all: (inCanvas: HTMLCanvasElement, result: Result, drawOptions?: DrawOptions) => Promise<void>; body: (inCanvas: HTMLCanvasElement, result: Body[], drawOptions?: DrawOptions) => Promise<void>; canvas: (inCanvas: HTMLCanvasElement, outCanvas: HTMLCanvasElement) => Promise<void>; face: (inCanvas: HTMLCanvasElement, result: Face[], drawOptions?: DrawOptions) => Promise<void>; gesture: (inCanvas: HTMLCanvasElement, result: Gesture[], drawOptions?: DrawOptions) => Promise<void>; hand: (inCanvas: HTMLCanvasElement, result: Hand[], drawOptions?: DrawOptions) => Promise<void>; options: DrawOptions }

Draw helper classes that can draw detected objects on canvas using specified draw styles

  • options: global settings for all draw operations, can be overriden for each draw method, for details see DrawOptions
  • face: draw detected faces
  • body: draw detected people and body parts
  • hand: draw detected hands and hand parts
  • canvas: draw processed canvas which is a processed copy of the input
  • all: meta-function that performs: canvas, face, body, hand

Type declaration

  • all: (inCanvas: HTMLCanvasElement, result: Result, drawOptions?: DrawOptions) => Promise<void>
      • (inCanvas: HTMLCanvasElement, result: Result, drawOptions?: DrawOptions): Promise<void>

      • Parameters

        Returns Promise<void>

  • body: (inCanvas: HTMLCanvasElement, result: Body[], drawOptions?: DrawOptions) => Promise<void>
      • (inCanvas: HTMLCanvasElement, result: Body[], drawOptions?: DrawOptions): Promise<void>

      • Parameters

        • inCanvas: HTMLCanvasElement
        • result: Body[]
        • Optional drawOptions: DrawOptions

        Returns Promise<void>

  • canvas: (inCanvas: HTMLCanvasElement, outCanvas: HTMLCanvasElement) => Promise<void>
      • (inCanvas: HTMLCanvasElement, outCanvas: HTMLCanvasElement): Promise<void>

      • Parameters

        • inCanvas: HTMLCanvasElement
        • outCanvas: HTMLCanvasElement

        Returns Promise<void>

  • face: (inCanvas: HTMLCanvasElement, result: Face[], drawOptions?: DrawOptions) => Promise<void>
      • (inCanvas: HTMLCanvasElement, result: Face[], drawOptions?: DrawOptions): Promise<void>

      • Parameters

        • inCanvas: HTMLCanvasElement
        • result: Face[]
        • Optional drawOptions: DrawOptions

        Returns Promise<void>

  • gesture: (inCanvas: HTMLCanvasElement, result: Gesture[], drawOptions?: DrawOptions) => Promise<void>
      • (inCanvas: HTMLCanvasElement, result: Gesture[], drawOptions?: DrawOptions): Promise<void>

      • Parameters

        Returns Promise<void>

  • hand: (inCanvas: HTMLCanvasElement, result: Hand[], drawOptions?: DrawOptions) => Promise<void>
      • (inCanvas: HTMLCanvasElement, result: Hand[], drawOptions?: DrawOptions): Promise<void>

      • Parameters

        • inCanvas: HTMLCanvasElement
        • result: Hand[]
        • Optional drawOptions: DrawOptions

        Returns Promise<void>

  • options: DrawOptions

faceTriangulation

faceTriangulation: number[]

Reference face triangualtion array of 468 points, used for triangle references between points

faceUVMap

faceUVMap: number[][]

Refernce UV map of 468 values, used for 3D mapping of the face mesh

image

image: { canvas: null | HTMLCanvasElement | OffscreenCanvas; tensor: null | Tensor<Rank> }
internal:

Instance of current image being processed

Type declaration

  • canvas: null | HTMLCanvasElement | OffscreenCanvas
  • tensor: null | Tensor<Rank>

models

models: { age: unknown; blazepose: unknown; centernet: unknown; efficientpose: unknown; embedding: unknown; emotion: unknown; face: null | [unknown, unknown, unknown]; faceres: unknown; gender: unknown; handpose: null | [unknown, unknown]; movenet: unknown; nanodet: unknown; posenet: unknown }
internal:

Currently loaded models

Type declaration

  • age: unknown
  • blazepose: unknown
  • centernet: unknown
  • efficientpose: unknown
  • embedding: unknown
  • emotion: unknown
  • face: null | [unknown, unknown, unknown]
  • faceres: unknown
  • gender: unknown
  • handpose: null | [unknown, unknown]
  • movenet: unknown
  • nanodet: unknown
  • posenet: unknown

performance

performance: Record<string, number>

Performance object that contains values for all recently performed operations

result

result: Result

Last known result of detect run

  • Can be accessed anytime after initial detection

state

state: string

Current state of Human library

  • Can be polled to determine operations that are currently executed
  • Progresses through: 'config', 'check', 'backend', 'load', 'run:', 'idle'

sysinfo

sysinfo: { agent: string; platform: string }

Platform and agent information detected by Human

Type declaration

  • agent: string
  • platform: string

tf

tf: __module
internal:

Instance of TensorFlow/JS used by Human

  • Can be embedded or externally provided

version

version: string

Current version of Human library in semver format

Methods

detect

  • Main detection method

    • Analyze configuration: Config
    • Pre-process input: Input
    • Run inference for all configured models
    • Process and return result: Result

    Parameters

    • input: Input
    • Optional userConfig: Config | Record<string, unknown>

    Returns Promise<Error | Result>

    result: Result

enhance

  • enhance(input: Tensor<Rank>): null | Tensor<Rank>

  • Enhance method performs additional enhacements to face image previously detected for futher processing

    Parameters

    • input: Tensor<Rank>

    Returns null | Tensor<Rank>

    Tensor

load

  • load(userConfig?: Config | Record<string, unknown>): Promise<void>

  • Load method preloads all configured models on-demand

    • Not explicitly required as any required model is load implicitly on it's first run

    Parameters

    • Optional userConfig: Config | Record<string, unknown>

    Returns Promise<void>

match

  • match(faceEmbedding: number[], db: { embedding: number[]; name: string; source: string }[], threshold?: number): { embedding: number[]; name: string; similarity: number; source: string }

  • Math method find best match between provided face descriptor and predefined database of known descriptors

    Parameters

    • faceEmbedding: number[]
    • db: { embedding: number[]; name: string; source: string }[]
    • threshold: number = 0

    Returns { embedding: number[]; name: string; similarity: number; source: string }

    best match

    • embedding: number[]
    • name: string
    • similarity: number
    • source: string

next

  • Runs interpolation using last known result and returns smoothened result Interpolation is based on time since last known result so can be called independently

    Parameters

    Returns Result

    result: Result

similarity

  • similarity(embedding1: number[], embedding2: number[]): number

  • Simmilarity method calculates simmilarity between two provided face descriptors (face embeddings)

    • Calculation is based on normalized Minkowski distance between

    Parameters

    • embedding1: number[]
    • embedding2: number[]

    Returns number

    similarity: number

warmup

  • warmup(userConfig?: Config | Record<string, unknown>): Promise<Result | { error: any }>

  • Warmup metho pre-initializes all models for faster inference

    • can take significant time on startup
    • only used for webgl and humangl backends

    Parameters

    • Optional userConfig: Config | Record<string, unknown>

    Returns Promise<Result | { error: any }>