如何在滑动窗口对象检测中对真阴性进行分类? [英] How to categorize True Negatives in sliding window object detection?

问题描述

我正在收集图像检测器算法的结果.所以基本上我所做的是，从一组图像(大小为 320 x 480)中，我会通过它运行一个 64x128 的滑动窗口，并在一些预定义的比例下运行.

I'm gathering results from my image detector algorithm. So basically what I do is that, from a set of images (with the size of 320 x 480), I would run a sliding window of 64x128 thru it, and also under a number of predefined scales.

我明白:

• True Positives = 当我检测到的窗口与真实情况(带注释的边界框)重叠(在定义的交叉点大小/质心内)时
• 误报 = 当算法给我正窗口时，这超出了事实.
• False Negatives = 当我没有给出肯定窗口时，而基本事实注释表明存在一个对象.

但是真正的否定呢?这些真正的否定是我的分类器给我否定结果的所有窗口吗?这听起来很奇怪，因为我一次将一个小窗口 (64x128) 滑动 4 个像素，并且我在检测中使用了大约 8 种不同的比例.如果我这样做，那么每张图片都会有很多真正的底片.

But what about True Negatives ? Are these true negatives all the windows that my classifier gives me negative results ? That sounds weird, since I'm sliding a small window (64x128) by 4 pixels at a time, and I've around 8 different scales used in detection. If I were to do that, then I'd have lots of true negatives per image.

或者我是否准备了一组纯负图像(根本没有物体/人)，我只是滑过，如果每张图像中都有一个或多个正检测，我会将其计为假负，反之亦然?

Or do I prepare a set of pure negative images (no objects / human at all), where I just slide thru, and if there's one or more positive detections in each of these images, I'd count it as False Negative, and vice versa ?

这是一个示例图像(绿色矩形作为基本事实)

Here's an example image (with green rects as the ground truth)

推荐答案

我一直看到的四个术语如下:

I've always seen the four terms as the following:

• 假阴性；结果应该是肯定的，但结果是否定的.
• 误报；结果应该是负面的，但结果是正面的.
• 真阳性；结果应该是肯定的并且是肯定的.
• 真阴性；结果应该是否定的并且是否定的.

在您的情况下，如果我理解正确，您正在尝试检测图像中是否有物体.因此，假阴性意味着有一个对象(结果应该是肯定的)但算法没有检测到它(因此返回否定).真正的否定只是算法正确地表明它检查的区域确实不包含一个对象.

In your case, if I understand correctly, you are trying to detect if there are objects in your image. False negative would therefore mean that there was a object (result should be positive) but the algorithm did not detect it (and therefore returned negative). A true negative is simply the algorithm correctly stating that the area it checked does not hold an object.

您可以选择忽略负值，但这些可用于进一步训练您的算法(例如，使用同时查找两者的算法，而不是将所有无法识别的内容设置为 false).

You can choose to ignore negative values, but these could be used to further train your algorithm (Eg; using an algorithm that looks for both, instead of setting everything that is not recognised to false).

这篇关于如何在滑动窗口对象检测中对真阴性进行分类?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！