ieemoo-ai-detecttracking/tracking/trackers/utils/matching.py

# Ultralytics YOLO 🚀, AGPL-3.0 license

import numpy as np
import math
import torch
import scipy
from scipy.spatial.distance import cdist

# from ultralytics.utils.metrics import bbox_ioa

try:
    import lap  # for linear_assignment

    assert lap.__version__  # verify package is not directory
except (ImportError, AssertionError, AttributeError):
    from ultralytics.utils.checks import check_requirements

    check_requirements('lapx>=0.5.2')  # update to lap package from https://github.com/rathaROG/lapx
    import lap


def bbox_iou(box1, box2, GIoU=False, DIoU=False, CIoU=False, eps=1e-7):
    '''由根目录下 utils.metrics.metrics.bbox_iou 更改而来'''
    # Returns Intersection over Union (IoU) of box1(1,4) to box2(n,4)

    # Get the coordinates of bounding boxes
    # x1, y1, x2, y2 = box1
    # box1 = torch.tensor(box1)
    # box2 = torch.tensor(box2)
    
    b1_x1, b1_y1, b1_x2, b1_y2 = box1.T
    b2_x1, b2_y1, b2_x2, b2_y2 = box2.T
    w1, h1 = b1_x2 - b1_x1, (b1_y2 - b1_y1).clip(eps)
    w2, h2 = b2_x2 - b2_x1, (b2_y2 - b2_y1).clip(eps)

    # Intersection area
    # inter = (b1_x2.minimum(b2_x2) - b1_x1.maximum(b2_x1)).clamp(0) * \
    #         (b1_y2.minimum(b2_y2) - b1_y1.maximum(b2_y1)).clamp(0)
            
    inter = (np.minimum(b1_x2[:, None], b2_x2) - np.maximum(b1_x1[:, None], b2_x1)).clip(0) * \
                 (np.minimum(b1_y2[:, None], b2_y2) - np.maximum(b1_y1[:, None], b2_y1)).clip(0)

    # Union Area
    box1_area = w1 * h1
    box2_area = w2 * h2
    
    union = box1_area[:, None] + box2_area - inter + eps

    # IoU
    iou = inter / union
    if CIoU or DIoU or GIoU:
        cw = np.maximum(b1_x2[:, None], b2_x2) - np.minimum(b1_x1[:, None], b2_x1)  # convex (smallest enclosing box) width
        ch = np.maximum(b1_y2[:, None], b2_y2) - np.minimum(b1_y1[:, None], b2_y1)  # convex height
        if CIoU or DIoU:  # Distance or Complete IoU https://arxiv.org/abs/1911.08287v1
            c2 = cw ** 2 + ch ** 2 + eps  # convex diagonal squared
            '''center dist ** 2''' 
            rho2 = ((b1_x1[:, None] + b1_x2[:, None] - b2_x1 - b2_x2) ** 2 + \
                    (b1_y1[:, None] + b1_y2[:, None] - b2_y1 - b2_y2) ** 2) / 4 
            if CIoU:  # https://github.com/Zzh-tju/DIoU-SSD-pytorch/blob/master/utils/box/box_utils.py#L47
                v = (4 / math.pi ** 2) * (np.arctan(w1 / h1)[:, None] - np.arctan(w2 / h2))**2
                with torch.no_grad():
                    alpha = v / (v - iou + (1 + eps))
                return iou - (rho2 / c2 + v * alpha)  # CIoU
            return iou - rho2 / c2  # DIoU
        c_area = cw * ch + eps  # convex area
        return iou - (c_area - union) / c_area  # GIoU https://arxiv.org/pdf/1902.09630.pdf
    return iou  # IoU


def bbox_ioa(box1, box2, iou=False, eps=1e-7):
    """
    Calculate the intersection over box2 area given box1 and box2. Boxes are in x1y1x2y2 format.

    Args:
        box1 (np.array): A numpy array of shape (n, 4) representing n bounding boxes.
        box2 (np.array): A numpy array of shape (m, 4) representing m bounding boxes.
        iou (bool): Calculate the standard iou if True else return inter_area/box2_area.
        eps (float, optional): A small value to avoid division by zero. Defaults to 1e-7.

    Returns:
        (np.array): A numpy array of shape (n, m) representing the intersection over box2 area.
    """

    # Get the coordinates of bounding boxes
    b1_x1, b1_y1, b1_x2, b1_y2 = box1.T
    b2_x1, b2_y1, b2_x2, b2_y2 = box2.T

    # Intersection area
    inter_area = (np.minimum(b1_x2[:, None], b2_x2) - np.maximum(b1_x1[:, None], b2_x1)).clip(0) * \
                 (np.minimum(b1_y2[:, None], b2_y2) - np.maximum(b1_y1[:, None], b2_y1)).clip(0)

    # box2 area
    area = (b2_x2 - b2_x1) * (b2_y2 - b2_y1)
    if iou:
        box1_area = (b1_x2 - b1_x1) * (b1_y2 - b1_y1)
        area = area + box1_area[:, None] - inter_area

    # Intersection over box2 area
    return inter_area / (area + eps)


# def linear_assignment(cost_matrix, thresh, use_lap=True):
def linear_assignment(cost_matrix: np.ndarray, thresh: float, use_lap: bool = True) -> tuple:
    """
    Perform linear assignment using scipy or lap.lapjv.

    Args:
        cost_matrix (np.ndarray): The matrix containing cost values for assignments.
        thresh (float): Threshold for considering an assignment valid.
        use_lap (bool, optional): Whether to use lap.lapjv. Defaults to True.

    Returns:
        (tuple): Tuple containing matched indices, unmatched indices from 'a', and unmatched indices from 'b'.
    """

    if cost_matrix.size == 0:
        return np.empty((0, 2), dtype=int), tuple(range(cost_matrix.shape[0])), tuple(range(cost_matrix.shape[1]))

    if use_lap:
        # https://github.com/gatagat/lap
        _, x, y = lap.lapjv(cost_matrix, extend_cost=True, cost_limit=thresh)
        matches = [[ix, mx] for ix, mx in enumerate(x) if mx >= 0]
        unmatched_a = np.where(x < 0)[0]
        unmatched_b = np.where(y < 0)[0]
    else:
        # https://docs.scipy.org/doc/scipy/reference/generated/scipy.optimize.linear_sum_assignment.html
        x, y = scipy.optimize.linear_sum_assignment(cost_matrix)  # row x, col y
        matches = np.asarray([[x[i], y[i]] for i in range(len(x)) if cost_matrix[x[i], y[i]] <= thresh])
        if len(matches) == 0:
            unmatched_a = list(np.arange(cost_matrix.shape[0]))
            unmatched_b = list(np.arange(cost_matrix.shape[1]))
        else:
            unmatched_a = list(set(np.arange(cost_matrix.shape[0])) - set(matches[:, 0]))
            unmatched_b = list(set(np.arange(cost_matrix.shape[1])) - set(matches[:, 1]))

    return matches, unmatched_a, unmatched_b


# def iou_distance(atracks, btracks):
def iou_distance(atracks: list, btracks: list) -> np.ndarray:
    """
    Compute cost based on Intersection over Union (IoU) between tracks.

    Args:
        atracks (list[STrack] | list[np.ndarray]): List of tracks 'a' or bounding boxes.
        btracks (list[STrack] | list[np.ndarray]): List of tracks 'b' or bounding boxes.

    Returns:
        (np.ndarray): Cost matrix computed based on IoU.
    """

    if (len(atracks) > 0 and isinstance(atracks[0], np.ndarray)) \
            or (len(btracks) > 0 and isinstance(btracks[0], np.ndarray)):
        atlbrs = atracks
        btlbrs = btracks
    else:
        atlbrs = [track.tlbr for track in atracks]
        btlbrs = [track.tlbr for track in btracks]

    ious = np.zeros((len(atlbrs), len(btlbrs)), dtype=np.float32)
    if len(atlbrs) and len(btlbrs):
        box1 = np.ascontiguousarray(atlbrs, dtype=np.float32)
        box2 = np.ascontiguousarray(btlbrs, dtype=np.float32)
        
        ious = bbox_ioa(box1, box2, iou=True)
        ious_g = bbox_iou(box1, box2, GIoU=True).clip(-1.0, 1.0)
        ious_d = bbox_iou(box1, box2, DIoU=True).clip(-1.0, 1.0)
        ious_c = bbox_iou(box1, box2, CIoU=True).clip(-1.0, 1.0)
        
    return 1 - ious  # cost matrix


def embedding_distance(tracks, detections, metric='cosine'):
    """
    Compute distance between tracks and detections based on embeddings.

    Args:
        tracks (list[STrack]): List of tracks.
        detections (list[BaseTrack]): List of detections.
        metric (str, optional): Metric for distance computation. Defaults to 'cosine'.

    Returns:
        (np.ndarray): Cost matrix computed based on embeddings.
    """

    cost_matrix = np.zeros((len(tracks), len(detections)), dtype=np.float32)
    if cost_matrix.size == 0:
        return cost_matrix
    det_features = np.asarray([track.curr_feat for track in detections], dtype=np.float32)
    # for i, track in enumerate(tracks):
    # cost_matrix[i, :] = np.maximum(0.0, cdist(track.smooth_feat.reshape(1,-1), det_features, metric))
    track_features = np.asarray([track.smooth_feat for track in tracks], dtype=np.float32)
    cost_matrix = np.maximum(0.0, cdist(track_features, det_features, metric))  # Normalized features
    return cost_matrix


def fuse_score(cost_matrix, detections):
    """
    Fuses cost matrix with detection scores to produce a single similarity matrix.

    Args:
        cost_matrix (np.ndarray): The matrix containing cost values for assignments.
        detections (list[BaseTrack]): List of detections with scores.

    Returns:
        (np.ndarray): Fused similarity matrix.
    """

    if cost_matrix.size == 0:
        return cost_matrix
    iou_sim = 1 - cost_matrix
    det_scores = np.array([det.score for det in detections])
    det_scores = np.expand_dims(det_scores, axis=0).repeat(cost_matrix.shape[0], axis=0)
    fuse_sim = iou_sim * det_scores
    return 1 - fuse_sim  # fuse_cost