使用环境进行物体检测 [英] Object detection using environment

问题描述

我想问一个有关基于DNN的对象检测算法(例如Yolo，SSD或R-CNN)的一般问题.

I'd like to ask a general question about DNN based object detection algorithms such as Yolo, SSD or R-CNN.

假设我想在小图像上检测手机，因此-移动设备本身非常小，此外，仅查看出现在像素上的像素几乎不可能检测到它们.例如，查看300x300的图片，移动设备会显示在7x5的网格上，因此，只有查看7x5的图片，没人可以肯定地决定在那里可以看到什么.

Assume I'd like to detect mobile phones on small images, where - consequently - the mobile devices themselves are super small, moreover, it's nearly impossible to detect them by only looking at those pixels which they appear on. For instance, looking at a 300x300 image, the mobile shows up on a 7x5 grid, so only by looking at the 7x5 picture no one can surely decide what can be seen there.

另一方面，如果我们在图片上看到一个地铁车厢，一个人的手上有黑色的东西，我们(人类)几乎可以确定黑色的7x5黑色小网格代表移动设备

On the other hand, if we see a subway car on the picture, where a person has something black in her/his hand, we (human beings) are almost sure that the little, black 7x5 grid stands for a mobile device.

我的理解正确吗，当前最新的DNN算法无法像人类一样捕获环境，但是只能通过其在图像上的物理外观来检测物体?如果不是，您是否可以建议一种算法，该算法不一定只在黑色像素组上学习，而是能够捕捉到人的手中握有黑色物体(可能是电话)的黑色物体?

Is my understanding right that the current state-of-the-art DNN algorithms cannot capture the environment as humans do, but they only detect objects by their physical appearance on the image? If not, can you suggest an algorithm that does not necessarily learn on a black pixel group only, but is able to capture a human being holding a black thing in her/his hand that is likely to be a phone?

谢谢.

推荐答案

这可能与跟踪算法松散相关.通常，您可以将LSTM或其他算法与CNN结合使用，以预测人类在时序图像中的行为.

This may be loosely related to tracking algorithms. Typically, you would use a LSTM or other algorithm coupled with a CNN to predict a human's behavior in time series images.

我不明白为什么您无法使用电话的目标标签而不是CNN来预测类标签的电话设置目标数据集. R-CNN或Yolo不会像这样开箱即用，因此您需要为此应用程序自定义适合您的算法和训练集.

I don't see why you couldn't setup your dataset with target labels of phones vs no phones for the CNN to predict the class label. R-CNN or Yolo won't come out of the box like this so you would need to custom fit your algorithm and training set for this application.

了解人类行为是当前深度学习的重要且活跃的研究主题.预测此类任务的行为可能不会在通用库中广泛分布，因为这些任务可能是针对特定领域的任务，并且研究是新的，但这并不意味着不可能.

Understanding human behavior is an important and active research topic for deep learning right now. Predicting behavior for a task like this is probably not as widely distributed in common libraries since these could be more domain specific tasks and the research is new, but that doesn't mean it's not possible.

这是关于此主题的调查论文，可能与您的问题有关: https://arxiv. org/pdf/1806.11230.pdf .您可能还想研究一下对象跟踪正在进行的研究，因为它是一个类似的概念(但是，覆盖范围比仅仅检测某人所持有的东西要广.)

This is a survey paper on this topic that may relate to your question: https://arxiv.org/pdf/1806.11230.pdf. You may also want to look into the research going on with object tracking since it is a similar concept (but covers a wider scope than just detecting what someone is holding).

这篇关于使用环境进行物体检测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！