vitis::ai::MultiTaskv38UC3 - 1.4.1 English

Vitis AI Library User Guide (UG1354)

Document ID
UG1354
Release Date
2021-12-11
Version
1.4.1 English
Base class for ADAS MuiltTask8UC3 from an image (cv::Mat).

Input is an image (cv::Mat).

Output is struct MultiTaskv3Result include segmentation results, detection results and vehicle orientation; The result cv::Mat type is CV_8UC3(except depth estimation)

Sample code:

auto det = vitis::ai::MultiTaskv38UC3::create(vitis::ai::MULITASK);
auto image = cv::imread("sample_multitaskv3.jpg");
auto result = det->run(image);
cv::imwrite("res.jpg",result.segmentation);

Quick Function Reference

The following table lists all the functions defined in the vitis::ai::MultiTaskv38UC3 class:

Table 1. Quick Function Reference
Type Name Arguments
std::unique_ptr< MultiTaskv38UC3 > create
  • const std::string & model_name
  • bool need_preprocess
int getInputWidth
  • void
int getInputHeight
  • void
size_t get_input_batch
  • void
MultiTaskv3Result run
  • const cv::Mat & image
std::vector< MultiTaskv3Result > run
  • const std::vector< cv::Mat > & images