Now, let's move from single-person pose detection to multi-person pose detection. With single-person pose detection, we saw that the code will take an image of a single person and generate pose estimation with all the joints labeled. We will now learn a more advanced model called ArtTrack, which will allow us to count the number of people, find people, and estimate their poses.
Let's look at the code for multi-person pose detection, which is shown in the following example:
import os
import sys
import numpy as np
import cv2 I
from imageio import imread, imsave
from config import load_config
from dataset.factory import create as create_dataset
from nnet import predict
from dataset.pose_dataset import data_to_input
from multiperson.detections import extract_detections
from multiperson.predict import SpatialModel, eval_graph, get_person_conf_mu1ticut
#...
