Simulation: Great Power Technology

Before that, Ye Zhou had also carefully read the documentation of the aes technology provided by the simulator. What he did not understand was why the image recognition part in the algorithm module was so huge and complicated. At first, he thought that It is to ensure image accuracy, but now it seems that it is not the case at all.

This part of the code exists only to solve the problem of neural self-correction.

There is an essential difference between a high-precision camera and the human eye. A very simple particle is that in the civilian field, no matter how advanced a camera is, it is impossible to dynamically adjust the gain in areas of different brightness like retinal ganglion cells. To achieve such a function, it is necessary to use the so-called sme-hdr algorithm.

The sme-hdr algorithm is implemented by the back-end processing system. In this process, a large number of redundant data sets will inevitably appear. These data sets will immediately activate the self-correction function of the human brain, so as to correct it to the correct one. visual signal.

But the problem is that these final versions of the visual signals will also be written back into the camera system to dynamically adjust the data of the sme-hdr algorithm.

Moreover, the dynamic gain of brightness is not the only problem facing the camera, the difference in central resolution, the difference in single-photon resolution, the too mapping algorithm, the difference in color and color gamut sensitivity... Various problems are superimposed together to make corrections. The difficulty of making mistakes increases exponentially.

Computers can handle this amount of computation, but what about the human brain?

Therefore, when the experiment was only halfway through, Yang Yijin could already see Yaoyao's discomfort----because she was really tired at that time.

Ye Zhou sighed deeply. He really didn't think that it was not the technology itself that limited the development of avs technology, but a factor that was almost ignored by everyone: the camera.

And, the problem is not that the camera is not advanced enough, but rather that its capabilities are too advanced for the human eye.

The resolution is too high, the color distortion is too small, the shape distortion is almost non-existent...

If you want to express it in plain language, the visual system of a normal person is a third-rate camera with a first-class processor, but under the avs system, it becomes a super-first-class camera with a second-rate processor, because according to the In the current scheme, the neural pathways established by the avs system cannot achieve the agility of the human body's original neural pathways.

Under the circumstances, problems arise naturally.

There are only two ways to solve this problem: Either custom-built cameras or invasive surgery to widen the nerve path.

However, the increased cost and decreased convenience brought by these two methods are extremely unsuitable for large-scale promotion.

So, the ultimate solution is to use algorithms to make up for the shortcomings of the device.

This obviously violates the principle of "the code should be as concise as possible" in computer science, so it actually has a negative impact.

Thinking of this, Ye Zhou shook his head slightly.

I have to say that the researchers on my timeline are lucky. This kind of luck is not because they directly acquired the avs technology, but after acquiring the technology, they selected a most typical, self-correcting one in the first experiment. The subjects with the strongest error ability.

Such luck has tested the most extreme situation once, and on another timeline, I am afraid that thousands of tests will not be enough to achieve such an effect.

After listening to Ye Zhou explain the cause of the problem, Chen Li's team was also surprised, especially Zhu Xuan. He had already discovered a lot of redundant code in the algorithm and analyzed its functionality, but he always wanted to No way, what problem are these codes used to deal with.

Now, all doubts are answered.

"So, if we want to continue to develop avs technology, we have to start by building cameras?"

Hearing Chen Li's question, Ye Zhou nodded slightly and replied:

"Either build a camera or do a craniotomy. The risk of the latter is too high, you can't just open a hole in the back of your head to connect a usb port like in those sci-fi movies, right? The risk of infection is not a joke. ."

"Okay... But this way, this experiment will be delayed. It is not difficult to build a camera with similar functions to the human eye, but the main difficulty is the debugging process. Can't get down."

Chen Li's expression was a little disappointed, his eyes seemed to inadvertently glanced at Yao Yao who was sitting quietly beside him, everyone could see what he was thinking.

The cruelest thing in this world is not to lose hope, but after regaining hope, it is taken away in a short period of time.

There is a saying, "I could have endured the darkness, if I hadn't seen the light", this seems a bit hypocritical sentence, but it is a true portrayal of Yaoyao.

She had seen the light, literally, but now, it was dark again.

Ye Zhou stepped forward and touched Yaoyao's hair. She raised her face in confusion, as if she didn't understand why she could see it just now, but now it's gray again.

"Uncle, is your computer out of power?"

Hearing her words, the expressions of everyone around were a little bitter, only Ye Zhou smiled and replied:

"It's not that there is no electricity, it's that your new eyes need rest."

After he finished speaking, he didn't look at Yaoyao's reaction, but turned to Chen Li and said:

"Don't make things so complicated."

"Developing a new camera is something that needs to be done, but that doesn't mean helping the blind to regain their sight is on hold."

"The problem now is very simple. The computing power of the nervous system is in conflict with the information instruction set density of the camera."

"In that case, it would be nice to subtract some information sets."

"The information set of color, depth of field is removed, and only shape and light and shade are preserved."

"Isn't it also a huge improvement to make blind people fully colorblind?"

…….

Two hours later, the avs system after removing the color and depth of field lens as requested by Ye Zhou completed the test, and the test results surprised everyone.

Before that, they generally believed that human judgment of depth of field came from binoculars, that is, dual cameras, but it turns out that the adaptability of the human brain is much stronger than they thought.

Threading a needle in one eye is difficult, but not impossible.

And Yaoyao obviously has amazing talent in this regard.

Just over an hour after the experiment began, she was able to walk around the room, go up and down steps, and avoid obstacles using visual cues from the avs system.

This seemed like a no-brainer to her, and even when Chu Ya helped her remove the interface electrodes, she seemed a little unwilling.

"Okay Yaoyao, sit and wait for a while. We'll assemble the equipment so you can take it away."

Yaoyao nodded obediently and squatted on the ground, while Yang Yijin walked over to pick her up and put her on the sofa outside the laboratory.

The assembly work was in charge of several junior researchers under Chen Li. He didn't need to do it himself, so he sat down with Ye Zhou and the others.

"What did you do in the first place was the mobile solution?"

Ye Zhou curiously looked at the avs equipment that was gradually assembled into a helmet-like shape, and asked.

"It must be a mobile plan, otherwise, if the experiment is successful, the subjects can't take it away, it's too nonsense... Moreover, the process of collecting information is not over yet, let her take it to the complex environment by herself. Further optimization of the algorithm is actually helpful for subsequent equipment improvements."

Ye Zhou nodded and did not ask any further, but turned to Yaoyao and asked:

"Yaoyao, new eyes, do you feel used to it?"

Yaoyao on the sofa frowned and thought for a moment, then replied:

"No color."

"Yeah, it will have color later."

"But I want to see color."

"But now there's no way, if you want to see the color, your head won't be able to take it."

"I can handle it!"

Ye Zhou laughed dumbly. She is still a child at heart. When she encounters what she really wants, she will still act like a spoiled child and cheat like her peers.

Thinking of this, Ye Zhou did not continue to entangle with her topic, but after a deliberate pause for a while, he continued to ask:

"I can see it later, what do you want to do?"

"Go to kindergarten."

Hearing this answer, everyone on the sofa laughed.

After laughing, I feel a little sad again.

The accident at home was actually when she had just finished kindergarten, so her influence on "going to school" probably only stayed at that time.

She can learn a lot from her mobile phone, but she can't learn the concepts of elementary school and junior high school after kindergarten.

"You are almost seven years old, you can't go to kindergarten, you should go to primary school."

"Then go to elementary school."

"What about after elementary school? When you grow up? What do you want to do?"

This is a classic question. It seems that all adults can't help but ask "what do you want to do when you grow up" when facing a child who has just started school, just like facing a child who has just learned to talk and walk, always Ask him "where are mom and dad".

Ye Zhou thought that she would give answers such as astronauts and scientists, and even wondered whether she would say that she wanted to be a lumberjack, because yesterday at her home, she saw the animation on her mobile phone The film is about lumberjacks.

But unexpectedly, her answer was different from what everyone guessed.

"I want to be a firefighter."

Ye Zhou was stunned for a moment, then asked:

"Do you know what firefighters do?"

"I know."

Yaoyao's face showed a serious look like a little adult. After a while, her head lowered, her fingers slowly intertwined, and then she said in a low voice:

"Firefighters are putting out ... fire ... is a bad thing."