计算边界框重叠的百分比，以进行图像检测器评估 [英] Calculating percentage of Bounding box overlap, for image detector evaluation

问题描述

在测试大图像中的对象检测算法时，我们将检测到的边界框与为地面真实矩形指定的坐标进行比较。

In testing an object detection algorithm in large images, we check our detected bounding boxes against the coordinates given for the ground truth rectangles.

根据Pascal VOC的挑战，是这样的：

According to the Pascal VOC challenges, there's this:

如果预测的边界框与地面约束力的边界重叠超过50％的
，则认为该边界框是正确的框，否则将边界框
视为误报。多次检测将被罚款
。如果系统预测与单个地面真实边界框重叠
的多个边界框，则只有一个预测是
被认为是正确的，其他预测被认为是误报。

A predicted bounding box is considered correct if it overlaps more than 50% with a ground-truth bounding box, otherwise the bounding box is considered a false positive detection. Multiple detections are penalized. If a system predicts several bounding boxes that overlap with a single ground-truth bounding box, only one prediction is considered correct, the others are considered false positives.

这意味着我们需要计算重叠百分比。这是否意味着地面真相框被检测到的边界框覆盖了50％？还是50％的边界框被地面真值框吸收了？

This means that we need to calculate the percentage of overlap. Does this mean that the ground truth box is 50% covered by the detected boundary box? Or that 50% of the bounding box is absorbed by the ground truth box?

我已经搜索过，但是还没有找到标准的算法-令人惊讶因为我会认为这在计算机视觉中很常见。 （我是新来的）。我错过了吗？有人知道这种类型的问题的标准算法是什么吗？

I've searched but I haven't found a standard algorithm for this - which is surprising because I would have thought that this is something pretty common in computer vision. (I'm new to it). Have I missed it? Does anyone know what the standard algorithm is for this type of problem?

推荐答案

我发现概念答案在这里：
http：//pascallin.ecs。 soton.ac.uk/challenges/VOC/voc2012/htmldoc/devkit_doc.html#SECTION00054000000000000000

I found that the conceptual answer is here: http://pascallin.ecs.soton.ac.uk/challenges/VOC/voc2012/htmldoc/devkit_doc.html#SECTION00054000000000000000

来自此线程：
将两个边界框相互比较Matlab

我应该能够在python中编写代码！

I should be able to code this in python!

这篇关于计算边界框重叠的百分比，以进行图像检测器评估的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！