Ir para o conteúdo
Atlas de IA

Segmentação de imagens

Rotular cada pixel com o objeto a que pertence

Compreensão visualIniciante #13
entradaImagemImagem

O texto completo é apresentado em inglês; o título e o resumo estão traduzidos.

O QUE ESTA CAPACIDADE SIGNIFICA

Takes an image and outputs a mask the size of the input, labelling each pixel with its class or its instance. It is finer than detection because it gives outlines rather than boxes. Semantic segmentation only distinguishes classes (all of them are people), while instance segmentation also separates individuals (A and B are different people); the two are often lumped together as segmentation.

Como é feita tecnicamente

The classic design is an encoder–decoder: the encoder downsamples to extract semantics, the decoder upsamples to restore resolution, and skip connections carry high-resolution detail from shallow layers, with U-Net and fully convolutional networks as landmarks. Instance segmentation often detects first and predicts a mask inside each box (the Mask R-CNN line), or uses a promptable segment-anything model cued by clicks or boxes to isolate arbitrary objects.

Produtos representativos

4

Organizações relacionadas

Usos típicos

  • Organ and lesion delineation in medical imaging
  • Land-cover classification in remote sensing
  • Drivable area and obstacles for driving
  • Selection masks for image editing

Como avaliar se funciona bem

IoU / mIoU
Intersection over union of masks, averaged over classes
Dice coefficient
Common in medical imaging, more sensitive than IoU for small targets
Boundary F-score
Judges only contour fit rather than large correct interiors

Limites e dificuldades

  • Thin structures and boundaries — hair, wires, vessel tips — break or lose their thinness
  • Adjacent or overlapping instances of the same class merge into one blob
  • Masks are inaccurate on transparent, reflective or low-contrast materials

Conceitos por trás