0000000000000000

Scheaven

已于 2023-03-10 15:32:26 修改

阅读量652

点赞数

分类专栏： test 文章标签： docker 深度学习神经网络

于 2021-01-07 10:08:48 首次发布

本文链接：https://blog.csdn.net/sinat_30584357/article/details/112303517

版权

test 专栏收录该内容

1 篇文章 0 订阅

订阅专栏

该博客介绍了计算机视觉中用于衡量两个边界框重叠程度的IoU（Intersection over Union）概念。它提供了一个名为`defiou`的函数，该函数接收一个边界框和一组候选边界框作为输入，返回每个候选框与给定边界框的IoU分数。IoU分数越高，表示给定边界框被候选框遮挡的比例越大，对于目标检测和语义分割任务至关重要。

摘要由CSDN通过智能技术生成

def iou(bbox, candidates):
“”"Computer intersection over union.

Parameters
----------
bbox : ndarray
    A bounding box in format `(top left x, top left y, width, height)`.
candidates : ndarray
    A matrix of candidate bounding boxes (one per row) in the same format
    as `bbox`.

Returns
-------
ndarray
    The intersection over union in [0, 1] between the `bbox` and each
    candidate. A higher score means a larger fraction of the `bbox` is
    occluded by the candidate.

"""
bbox_tl, bbox_br = bbox[:2], bbox[:2] + bbox[2:]
candidates_tl = candidates[:, :2]
candidates_br = candidates[:, :2] + candidates[:, 2:]

tl = np.c_[np.maximum(bbox_tl[0], candidates_tl[:, 0])[:, np.newaxis],
           np.maximum(bbox_tl[1], candidates_tl[:, 1])[:, np.newaxis]]
br = np.c_[np.minimum(bbox_br[0], candidates_br[:, 0])[:, np.newaxis],
           np.minimum(bbox_br[1], candidates_br[:, 1])[:, np.newaxis]]
wh = np.maximum(0., br - tl)

area_intersection = wh.prod(axis=1)
area_bbox = bbox[2:].prod()
area_candidates = candidates[:, 2:].prod(axis=1)
return area_intersection / (area_bbox + area_candidates - area_intersection)