![](https://csdnimg.cn/release/download_crawler_static/87500519/bg3.jpg)
中文摘要
目标检测对于人类来说极为简单,经过上万年的进化,人类天生具有复杂的感
知与视觉系统,这是机器无可比拟的,我们可以只对图片看一眼,即分辨出物体
的种类和它相应的位置。但是对于计算机来说,一张图片只是具有无数 RGB 像
素点的矩阵,它本身并不知道猫狗动物,大小形状的概念,如果再给它一张具有
复杂自然场景背景的图片,想要检测出物体更是难上加难。面对这样的计算机难
题,很多研究学者蜂拥而至,从此目标检测领域变成了非常热门的研究方向。
YOLO 为一种新的目标检测方法,该方法的特点是实现快速检测的同时还达到较
高的准确率。
ABSTRACT
Target detection is extremely simple for humans. After tens of
thousands of years of evolution, humans are born with a complex
perception and vision system, which is unmatched by machines. We
can only look at the picture, that is, distinguish the type of object and
its corresponding position. But for a computer, a picture is just a
matrix with countless RGB pixels. It does not know the concept of
size and shape of cats and dogs. If it is given another picture with a
complex natural scene background, it is even more difficult to detect
objects. In the face of such computer problems, many researchers
swarmed in, and since then the field of target detection has become a
very popular research direction. YOLO is a new target detection
method, which is characterized by fast detection and high accuracy.