vitis::ai::VehicleResult - 1.2 English

Vitis AI Library User Guide (UG1354)

Document ID
UG1354
Release Date
2020-07-21
Version
1.2 English
A struct to define detection result of MultiTask.

Declaration

typedef struct
{
  int label,
  float score,
  float x,
  float y,
  float width,
  float height,
  float angle
} vitis::ai::VehicleResult;
Table 1. Structure vitis::ai::VehicleResult member description
Member Description
label

number of classes

  • 0 : "background"
  • 1 : "person"
  • 2 : "car"
  • 3 : "truck"
  • 4 : "bus"
  • 5 : "bike"
  • 6 : "sign"
  • 7 : "light"
score confidence of this target
x

x-coordinate, x is normalized relative to the input image cols ,the value range from 0 to 1.

y

y-coordinate ,y is normalized relative to the input image rows ,the value range from 0 to 1.

width

width, width is normalized relative to the input image cols ,the value range from 0 to 1.

height

height, height is normalized relative to the input image rows ,the value range from 0 to 1.

angle the angle between the target vehicle and ourself.