Top Student

After a pause, Ren Wendou continued:

Of course, pure high resolution is not the goal, but it is necessary to clearly see each ground target. Ultra-high directivity and ultra-high stability are what we must guarantee.

Then what is the maximum carrying capacity of our rocket? Can the lens be made very large?

As long as it can be achieved by our existing rocket capacity, there is no problem.

Teacher Ren, our Zhengtu No. 9 is still unavailable, right?

Zhengtu No. 9 is still under development, and it is expected to be put into use within a few years. But in the short term, it should not be possible.

After receiving a series of answers from Ren Wendou, Xu You probably understood the current situation.

Under the existing conditions, we will make every effort to develop satellites with higher resolution.

Even, paying more costs is not a problem.

It's just that some things can't be solved with money.

For example, the carrying capacity of the rocket.

If you want to solve this problem from the direction of improving the rocket's carrying capacity.

Then the problem will become more complicated.

Xu You thinks that it is better to think about how to achieve a higher resolution with the existing resources as much as possible.

Because of the limited carrying capacity of the rocket, it is definitely not a good choice to send a particularly huge lens at a time.

If you think about it from the perspective of mirror splicing or optical film assembly.

It is a feasible direction.

Just divide it several times, send the lenses or optical films into space, and then assemble them.

Of course, in this way, how to assemble these lenses in space is another key issue.

After finishing the communication with Ren Wendou, Xu You started the specific plan design.

So far, Xu You has three general directions.

The first direction is the optimization of the previous generation of high-scoring satellites.

Through research, Xu You found that the previous generation of high-resolution satellites still has a certain potential in terms of resolution, and the resolution can be further improved without changing the main hardware.

Although it won't increase by as much as several times, it is still very promising, and it will be within ten centimeters.

The second direction is to use multi-lens splicing technology.

This direction can essentially improve the resolution of satellites.

The problem is that the weight of the reconnaissance satellite will be relatively heavy, which is a huge test for the carrying capacity of the launch vehicle.

The third direction is to use diffractive optical film technology.

Use a very thin optical film to replace ordinary optical lenses.

Because the optical film is much lighter than the optical lens.

This scheme does not have such high requirements for the rocket's carrying capacity.

But the problem is that it also needs to be assembled, and the imaging technology is not as mature as traditional optical lenses.

It can be said that the three methods have their own advantages and disadvantages.

It is necessary to make a more reasonable choice according to different situations.

On this day, Wu Jing organized everyone and held a meeting.

At the meeting, the main communication was about the design plan of the new generation of high-resolution satellites.

Teacher Xu, please tell me about your design plan.

Xu You showed everyone his three plans, and introduced the pros and cons of each plan.

Listening to Xu You's explanation, everyone present expressed their admiration for Xu You's ideas.

They didn't expect that Xu You had not only been here for a few days, but he had not only completed the study of such a huge amount of knowledge, but also had his own ideas about the design of the satellite.

There are even some plans that those senior designers have never thought of.

Mr. Xu, according to what you said, there is still room for optimization of the previous generation of high-scoring satellites? Wu Jing asked.

Yes, there is indeed a certain room for optimization. If ideal, we hope to increase its resolution to about 50mm without changing the main hardware.

Everyone was shocked to hear this number.

Even with the use of larger optical lenses, they are not fully confident that the ground resolution of the satellite can be so fine.

In this case, the resolution is more than double that of the previous satellite with the highest resolution.

This solution should be the one with the lowest cost and the fastest speed, right?

Yes. Of course, there must be an upper limit to the improvement of this solution. No matter how hard we try, it will be difficult to increase the resolution to within 10mm.

This is like an ordinary person who can run 100 meters in 13 seconds. After professional training, he may be able to run in 12 seconds or even faster.

But no matter how much you train, it is difficult to break through 11 seconds.

This is the limitation of the hardware, which determines the upper limit of the ability.

If using the other two solutions, as long as Xu You is given enough time, it is not impossible to make the resolution within 10mm.

After some discussions, everyone felt that the first option could be given priority.

Xu You could also see that, if possible, everyone hoped that such a high-resolution satellite could be launched into space as soon as possible.

Since this is the case, let's start with Teacher Xu's first plan. If this plan doesn't work well, we will try other plans. Wu Jing said.

Anyway, the remaining two options will take longer to study.

Putting the priority in the back will not have much impact.

After finishing this meeting, Xu You began to study the first plan.

In fact, before the meeting, Xu You already had a basic plan for this plan.

According to Xu You's estimate, I am confident that after optimization, the resolution will be between 30mm and 50mm.

Because this is the theoretical resolution limit of the previous generation of high-resolution satellites.

Xu You returned to his office and started intense work.

The first thing Xu You needs to do is to optimize on the basis of the previous generation algorithm.

Xu You turned on the state of deep learning, and under the highly concentrated attention, he soon entered the state of flow.

Based on the knowledge he has learned recently, as well as a large amount of previous accumulation, Xu You determined the optimization direction of the algorithm.

Using the concept of depth-separable convolution, decoupling the convolution layer, and reducing the number of model parameters can achieve the purpose of improving detection efficiency.

Xu You analyzed the data of the previous generation of high-resolution satellites, and began to optimize the algorithm.

In the previous algorithm, it is impossible to locate and distinguish multiple types of targets at the same time, and it is susceptible to changes in the external environment such as lighting and shooting angles, which will affect the final observation results.

Therefore, only by reducing the resolution to 100mm can the ultra-high stability of satellite imaging be best guaranteed.

Yes! Turn this problem of target positioning and detection into a regression problem to deal with. In this way...