controlnet_aux/open_pose/body.py

import math
from typing import List, NamedTuple, Union

import cv2
import numpy as np
import torch
from scipy.ndimage.filters import gaussian_filter

from . import util
from .model import bodypose_model


class Keypoint(NamedTuple):
    x: float
    y: float
    score: float = 1.0
    id: int = -1


class BodyResult(NamedTuple):
    # Note: Using `Union` instead of `|` operator as the ladder is a Python
    # 3.10 feature.
    # Annotator code should be Python 3.8 Compatible, as controlnet repo uses
    # Python 3.8 environment.
    # https://github.com/lllyasviel/ControlNet/blob/d3284fcd0972c510635a4f5abe2eeb71dc0de524/environment.yaml#L6
    keypoints: List[Union[Keypoint, None]]
    total_score: float
    total_parts: int


class Body(object):
    def __init__(self, model_path):
        self.model = bodypose_model()
        model_dict = util.transfer(self.model, torch.load(model_path))
        self.model.load_state_dict(model_dict)
        self.model.eval()

    def to(self, device):
        self.model.to(device)
        return self

    def __call__(self, oriImg):
        device = next(iter(self.model.parameters())).device
        # scale_search = [0.5, 1.0, 1.5, 2.0]
        scale_search = [0.5]
        boxsize = 368
        stride = 8
        padValue = 128
        thre1 = 0.1
        thre2 = 0.05
        multiplier = [x * boxsize / oriImg.shape[0] for x in scale_search]
        heatmap_avg = np.zeros((oriImg.shape[0], oriImg.shape[1], 19))
        paf_avg = np.zeros((oriImg.shape[0], oriImg.shape[1], 38))

        for m in range(len(multiplier)):
            scale = multiplier[m]
            imageToTest = util.smart_resize_k(oriImg, fx=scale, fy=scale)
            imageToTest_padded, pad = util.padRightDownCorner(imageToTest, stride, padValue)
            im = np.transpose(np.float32(imageToTest_padded[:, :, :, np.newaxis]), (3, 2, 0, 1)) / 256 - 0.5
            im = np.ascontiguousarray(im)

            data = torch.from_numpy(im).float()
            data = data.to(device)
            # data = data.permute([2, 0, 1]).unsqueeze(0).float()
            with torch.no_grad():
                Mconv7_stage6_L1, Mconv7_stage6_L2 = self.model(data)
            Mconv7_stage6_L1 = Mconv7_stage6_L1.cpu().numpy()
            Mconv7_stage6_L2 = Mconv7_stage6_L2.cpu().numpy()

            # extract outputs, resize, and remove padding
            # heatmap = np.transpose(np.squeeze(net.blobs[output_blobs.keys()[1]].data), (1, 2, 0))  # output 1 is heatmaps
            heatmap = np.transpose(np.squeeze(Mconv7_stage6_L2), (1, 2, 0))  # output 1 is heatmaps
            heatmap = util.smart_resize_k(heatmap, fx=stride, fy=stride)
            heatmap = heatmap[:imageToTest_padded.shape[0] - pad[2], :imageToTest_padded.shape[1] - pad[3], :]
            heatmap = util.smart_resize(heatmap, (oriImg.shape[0], oriImg.shape[1]))

            # paf = np.transpose(np.squeeze(net.blobs[output_blobs.keys()[0]].data), (1, 2, 0))  # output 0 is PAFs
            paf = np.transpose(np.squeeze(Mconv7_stage6_L1), (1, 2, 0))  # output 0 is PAFs
            paf = util.smart_resize_k(paf, fx=stride, fy=stride)
            paf = paf[:imageToTest_padded.shape[0] - pad[2], :imageToTest_padded.shape[1] - pad[3], :]
            paf = util.smart_resize(paf, (oriImg.shape[0], oriImg.shape[1]))

            heatmap_avg += heatmap_avg + heatmap / len(multiplier)
            paf_avg += + paf / len(multiplier)

        all_peaks = []
        peak_counter = 0

        for part in range(18):
            map_ori = heatmap_avg[:, :, part]
            one_heatmap = gaussian_filter(map_ori, sigma=3)

            map_left = np.zeros(one_heatmap.shape)
            map_left[1:, :] = one_heatmap[:-1, :]
            map_right = np.zeros(one_heatmap.shape)
            map_right[:-1, :] = one_heatmap[1:, :]
            map_up = np.zeros(one_heatmap.shape)
            map_up[:, 1:] = one_heatmap[:, :-1]
            map_down = np.zeros(one_heatmap.shape)
            map_down[:, :-1] = one_heatmap[:, 1:]

            peaks_binary = np.logical_and.reduce(
                (one_heatmap >= map_left, one_heatmap >= map_right, one_heatmap >= map_up, one_heatmap >= map_down, one_heatmap > thre1))
            peaks = list(zip(np.nonzero(peaks_binary)[1], np.nonzero(peaks_binary)[0]))  # note reverse
            peaks_with_score = [x + (map_ori[x[1], x[0]],) for x in peaks]
            peak_id = range(peak_counter, peak_counter + len(peaks))
            peaks_with_score_and_id = [peaks_with_score[i] + (peak_id[i],) for i in range(len(peak_id))]

            all_peaks.append(peaks_with_score_and_id)
            peak_counter += len(peaks)

        # find connection in the specified sequence, center 29 is in the position 15
        limbSeq = [[2, 3], [2, 6], [3, 4], [4, 5], [6, 7], [7, 8], [2, 9], [9, 10], \
                   [10, 11], [2, 12], [12, 13], [13, 14], [2, 1], [1, 15], [15, 17], \
                   [1, 16], [16, 18], [3, 17], [6, 18]]
        # the middle joints heatmap correpondence
        mapIdx = [[31, 32], [39, 40], [33, 34], [35, 36], [41, 42], [43, 44], [19, 20], [21, 22], \
                  [23, 24], [25, 26], [27, 28], [29, 30], [47, 48], [49, 50], [53, 54], [51, 52], \
                  [55, 56], [37, 38], [45, 46]]

        connection_all = []
        special_k = []
        mid_num = 10

        for k in range(len(mapIdx)):
            score_mid = paf_avg[:, :, [x - 19 for x in mapIdx[k]]]
            candA = all_peaks[limbSeq[k][0] - 1]
            candB = all_peaks[limbSeq[k][1] - 1]
            nA = len(candA)
            nB = len(candB)
            indexA, indexB = limbSeq[k]
            if (nA != 0 and nB != 0):
                connection_candidate = []
                for i in range(nA):
                    for j in range(nB):
                        vec = np.subtract(candB[j][:2], candA[i][:2])
                        norm = math.sqrt(vec[0] * vec[0] + vec[1] * vec[1])
                        norm = max(0.001, norm)
                        vec = np.divide(vec, norm)

                        startend = list(zip(np.linspace(candA[i][0], candB[j][0], num=mid_num), \
                                            np.linspace(candA[i][1], candB[j][1], num=mid_num)))

                        vec_x = np.array([score_mid[int(round(startend[I][1])), int(round(startend[I][0])), 0] \
                                          for I in range(len(startend))])
                        vec_y = np.array([score_mid[int(round(startend[I][1])), int(round(startend[I][0])), 1] \
                                          for I in range(len(startend))])

                        score_midpts = np.multiply(vec_x, vec[0]) + np.multiply(vec_y, vec[1])
                        score_with_dist_prior = sum(score_midpts) / len(score_midpts) + min(
                            0.5 * oriImg.shape[0] / norm - 1, 0)
                        criterion1 = len(np.nonzero(score_midpts > thre2)[0]) > 0.8 * len(score_midpts)
                        criterion2 = score_with_dist_prior > 0
                        if criterion1 and criterion2:
                            connection_candidate.append(
                                [i, j, score_with_dist_prior, score_with_dist_prior + candA[i][2] + candB[j][2]])

                connection_candidate = sorted(connection_candidate, key=lambda x: x[2], reverse=True)
                connection = np.zeros((0, 5))
                for c in range(len(connection_candidate)):
                    i, j, s = connection_candidate[c][0:3]
                    if (i not in connection[:, 3] and j not in connection[:, 4]):
                        connection = np.vstack([connection, [candA[i][3], candB[j][3], s, i, j]])
                        if (len(connection) >= min(nA, nB)):
                            break

                connection_all.append(connection)
            else:
                special_k.append(k)
                connection_all.append([])

        # last number in each row is the total parts number of that person
        # the second last number in each row is the score of the overall configuration
        subset = -1 * np.ones((0, 20))
        candidate = np.array([item for sublist in all_peaks for item in sublist])

        for k in range(len(mapIdx)):
            if k not in special_k:
                partAs = connection_all[k][:, 0]
                partBs = connection_all[k][:, 1]
                indexA, indexB = np.array(limbSeq[k]) - 1

                for i in range(len(connection_all[k])):  # = 1:size(temp,1)
                    found = 0
                    subset_idx = [-1, -1]
                    for j in range(len(subset)):  # 1:size(subset,1):
                        if subset[j][indexA] == partAs[i] or subset[j][indexB] == partBs[i]:
                            subset_idx[found] = j
                            found += 1

                    if found == 1:
                        j = subset_idx[0]
                        if subset[j][indexB] != partBs[i]:
                            subset[j][indexB] = partBs[i]
                            subset[j][-1] += 1
                            subset[j][-2] += candidate[partBs[i].astype(int), 2] + connection_all[k][i][2]
                    elif found == 2:  # if found 2 and disjoint, merge them
                        j1, j2 = subset_idx
                        membership = ((subset[j1] >= 0).astype(int) + (subset[j2] >= 0).astype(int))[:-2]
                        if len(np.nonzero(membership == 2)[0]) == 0:  # merge
                            subset[j1][:-2] += (subset[j2][:-2] + 1)
                            subset[j1][-2:] += subset[j2][-2:]
                            subset[j1][-2] += connection_all[k][i][2]
                            subset = np.delete(subset, j2, 0)
                        else:  # as like found == 1
                            subset[j1][indexB] = partBs[i]
                            subset[j1][-1] += 1
                            subset[j1][-2] += candidate[partBs[i].astype(int), 2] + connection_all[k][i][2]

                    # if find no partA in the subset, create a new subset
                    elif not found and k < 17:
                        row = -1 * np.ones(20)
                        row[indexA] = partAs[i]
                        row[indexB] = partBs[i]
                        row[-1] = 2
                        row[-2] = sum(candidate[connection_all[k][i, :2].astype(int), 2]) + connection_all[k][i][2]
                        subset = np.vstack([subset, row])
        # delete some rows of subset which has few parts occur
        deleteIdx = []
        for i in range(len(subset)):
            if subset[i][-1] < 4 or subset[i][-2] / subset[i][-1] < 0.4:
                deleteIdx.append(i)
        subset = np.delete(subset, deleteIdx, axis=0)

        # subset: n*20 array, 0-17 is the index in candidate, 18 is the total score, 19 is the total parts
        # candidate: x, y, score, id
        return candidate, subset
    
    @staticmethod
    def format_body_result(candidate: np.ndarray, subset: np.ndarray) -> List[BodyResult]:
        """
        Format the body results from the candidate and subset arrays into a list of BodyResult objects.
        
        Args:
            candidate (np.ndarray): An array of candidates containing the x, y coordinates, score, and id
                for each body part.
            subset (np.ndarray): An array of subsets containing indices to the candidate array for each
                person detected. The last two columns of each row hold the total score and total parts
                of the person.

        Returns:
            List[BodyResult]: A list of BodyResult objects, where each object represents a person with
                detected keypoints, total score, and total parts.
        """
        return [
            BodyResult(
                keypoints=[
                    Keypoint(
                        x=candidate[candidate_index][0],
                        y=candidate[candidate_index][1],
                        score=candidate[candidate_index][2],
                        id=candidate[candidate_index][3]
                    ) if candidate_index != -1 else None
                    for candidate_index in person[:18].astype(int)
                ],
                total_score=person[18],
                total_parts=person[19]
            )
            for person in subset
        ]