评论
打印
Computer vision is a real-time representation, digital representation, of the world and the interactions within it.
计算机视觉就是对环境的实时呈现，对于这个世界和其内部交互的数字呈现。
It has benefited from leaps and bounds of advancements thanks to computer, sensors, machine learning and software innovation.
计算机视觉技术收益于现代科技突飞猛进的发展，尤其是计算机、传感器、机器学习和软件创新的发展。
At the core of computer vision are camera systems.
计算机视觉技术的核心是摄像系统。
Cameras basically help you see agents such as cars, their locations and their actions, pedestrians, their locations, their actions and their gestures.
摄像机可以帮你查看周遭环境，像汽车以及它们的位置和行动，行人，他们的位置和手势。
In addition, there's also been a lot of advancements.
除此之外，还有其他很多进步的地方。
So one example is our vehicle can see the skeleton framework to show you the direction of travel;
比如，车上可以看到代码框架，告诉你行驶的方向；
also to give you details, like, are you dealing with a construction worker in a construction zone
还能告诉你其他一些细节信息， 比如，告诉你是否会在施工区域遇到建筑工人，
or are you dealing with a pedestrian that's probably distracted because they are looking on their phone?
或者你是否碰到了在查看手机而分心的行人？
Now the reality, though — and this is where it gets interesting —
然而现在的实际情况也是它变得有趣的地方
is that the camera and the algorithms that help us really cannot yet match the human brain's ability to understand and interpret the environment.
就是辅助人类的摄像机和算法，尚无法和人类大脑的能力相提并论，无法像人那样理解和解释环境。
They just can't.
机器做不到。
Even though they provide you really high-resolution imaging that really gives you continuous coverage,
即使它们可以给你提供高分辨率的成像，真正为你提供连续的实况图像，
that doesn't get fatigued, impaired or, you know, drunk or anything like that,
不会疲劳、受损、醉酒，或其他类似的情况，
at the end of the day, there are still things that they can't see and they can't measure.
到头来，仍然有一些它们看不到无法测量的情况。
So if we want autonomous-driving robotaxis soon, we have to supplement cameras.
因此，如果我们想要尽快实现无人驾驶出租车，我们必须要有足够多的摄像机。
Let me walk through some examples.
我们来看一些例子。
So radar gives you the direction of travel and measures the agent's movement within centimeters per second.
雷达告诉你行驶的方向，还测量物体的运动，精确到厘米每秒的范围。
Lidar gives you objects and shapes in the real world using depth perception as well as long-range and the all-important night vision.
激光雷达用深度感知远距离和夜视功能来为你提供现实世界中的物体和其形状的信息。
And let me tell you about this, because this is important to me personally and people who look like me.
让我再告诉你，因为这对我个人和跟我相似的人来说很重要。
Then you have, also, long-wave infrared where you are able to see agents that are emitting heat, such as animals and humans.
就是还有长波红外线，你可以靠这个看到周围散发热量的物体，像动物和人类。
And that's again, especially at night, super important.
一样的道理，这个功能在晚上格外重要。
Now, every one of these sensors is very powerful by itself, but when you put them together is when the magic happens.
每一个传感器各自的功能都非常强大，结合在一起，就是见证魔法的时刻。
If you see with this vehicle, for example, you have these multiple sensor modalities at all top four corners of the vehicle
如果你看到这样一辆车，在车身四个角上装有这些不同传感器，
that basically provide you a 360-degree field of vision, continuously, in a redundant manner, so that we don't miss anything.
它们基本上可以为你提供360度的视野，持续不断地，以绝不放过任何细节的态度来提供信息，这样我们就不会错过任何信息。
And this is that same thing with all of the different outputs fused together.
其实原理都是一样的，只是把不同输出的信息汇集在一起。
And looking at this, basically, and looking at what we see and how we are able to process the data,
这样看，基本上就是收集我们看到的信息数据，然后看如何处理这些数据，
then learn, then continue to improve our driving, is what tells us that we have confidence, this is the right approach and this time it's actually coming.
再学习，然后继续改进自动驾驶的技术，这让我们更有信心，这是正确的方法，这次真的要实现了。
Now, this is not, by the way, a brand new concept, OK?
顺便一提，这不是全新的概念吧？
Humans have been basically using vision systems to assist them for a long time.
人类使用视觉系统来辅助他们的生活已经有很长一段时间了。
