The military-industrial scientific research system of the academic master.

No matter what the Indians think, China is actually not very concerned about the pace over there.

Especially in the aviation industry.

It is really achieved in reality that it is better to buy than to build, and it is better to rent than to buy——

If the Indian army really uses the money invested in the LCA project to buy ready-made aircraft, the threat it could pose might be even greater.

In short, after the first batch of pre-production J-10A entered service, Chang Haonan quickly forgot what he had said afterwards.

During this period, his main job was to improve the image processing system of the Ocean No. 1 satellite.

It's not just the satellite side, there's also the part that needs to be processed on the ground after the data is transmitted back.

And the result...

There are already some signs of progress.

1 month 14 day.

The first snow of 2002 did not seem to come later than in previous years.

Despite the mobilization of a large number of municipal workers and the general public, the heavy snow that lasted all night still caused considerable trouble to road traffic early in the morning due to insufficient equipment.

So much so that when Chang Haonan got out of the car, he almost stepped on empty air.

But there was no way, as he was the one who set the date of the achievement report meeting, and he couldn't blame anyone else.

In fact, this heavy snow even caused temporary power outages in many areas.

The original meeting place suffered as a result.

Fortunately, the Fifth Academy of Aerospace Science and Technology is a key power supply target, so it can continue to operate in another place.

The results report meeting was not a technical seminar, and most of the participants were leaders related to the Ocean No. 1 satellite project.

As a result, the location of the Torch Laboratory seems a bit remote.

And the Fifth Academy of Aerospace is just the right one.

What’s a bit bizarre is that the former has been working on this project for several months, but this is his first time here.

In addition, a heavy snowfall covered everything in white, and he was a little disoriented for a moment.

Fortunately, at this time, a familiar voice sounded from not far away:

"Mr. Chang, welcome, welcome."

Chang Haonan turned around and saw Lin Senming coming towards him with big strides:

"Mr. Lin?"

He stepped forward and shook hands with the other party:

"What a coincidence, you just arrived too?"

"Well... I saw your car coming in, and I realized that the comrade in charge of guiding the guests had not arrived yet, so I came down from the office."

Lin Senming replied:

"There was a snowstorm last night. I was worried that I wouldn't be able to make it today, so I didn't go home and stayed in the office all night..."

Obviously, this person is also a person who works so hard that he forgets to eat and sleep.

So, before they could even say two sentences, the topic between the two of them returned to today's report meeting:

"Boss Chang, I summarized the content I was responsible for last night, and I feel... it's hard to come up with a sufficiently intuitive presentation."

"Although there are a lot of data and charts, they can only be understood by experts. Today..."

He didn't go on here, but his meaning was very clear.

Most of the people here today are leaders. Although there are also people with a technical background, after all, different fields are like different worlds. What’s more, image recognition is an extremely abstract and novel field.

However, Chang Haonan looked relaxed and even patted Lin Senming on the shoulder:

"It's okay. I'm prepared. Just organize the report meeting according to the original plan."

The latter is still a little skeptical.

But after all, Chang Haonan, who made the final decision, said so, and there would be someone taller to hold up the sky if it collapsed, so he nodded in the end.

……

Perhaps due to weather reasons, the leaders who came to attend the meeting generally arrived a little late.

Fortunately, it did not affect the normal start of the report meeting.

For Chang Haonan, making reports in such a relatively closed setting is already a piece of cake.

However, Lin Senming was still somewhat nervous.

After a brief introduction, the general background of the satellite and an overview of the software programming were first introduced.

Logically speaking, these two parts are relatively bland.

But as he listened, Chang Haonan felt something was wrong.

Too scripted.

Especially the software design part.

Even most leaders with professional backgrounds do not know much about the computer field.

However, Lin Senming started with a CV model and an energy functional of the LBF model, followed by a curve evolution theory and variational level set method model, and finally ended with an active contour model improved by local binary fitting...

If it's a technical meeting within the project team, it's not a big deal, but for a report meeting... it still needs to be concise and easy to understand.

Taking advantage of the gap between the two paragraphs, Chang Haonan looked around and found that many people on both sides of the conference table were either frowning or drowsy.

Although Ocean No. 1 is a project under the ministry's name, it is unlikely to cause any serious consequences even if it fails today.

However, problems are bound to arise due to the degree of funding imbalance.

More importantly, Chang Haonan is also planning to extract funds from this project to continue developing the segmentation and tracking technology of multiphase diagrams.

So, after finally getting through the first two parts, as soon as Chang Haonan took the stage, he chose to start from the middle part of the PPT.

"Dear leaders and colleagues, Comrade Lin Senming has just introduced to you the theoretical basis of our target contour segmentation. Next, let me show you our research results over the past month."

In fact, it can’t be entirely blamed on Lin Senming for speaking in a boring way.

If you want to show the effect of satellite image processing, first of all, you must have enough satellite images.

However, Ocean No. 1 is China's first ocean remote sensing satellite...

Therefore, during previous testing, the project team used more abstract calculation methods to conduct the test.

But it is obviously less intuitive.

However, Chang Haonan thought of a remedy in time before the report meeting.

"Everyone, please look at these pictures."

He directly controlled the PPT to turn to the next page.

No formulas or numbers, just four pictures.

Slightly monotonous picture.

A gray background with a dark image composed of regular pentagons and ellipses.

"The color of the picture is what we paint for the visual effect. In the actual processing process, the background pixels will be simplified to a certain extent to reduce the pressure of information transmission..."

The participants, who had just been indoctrinated with excessive mathematical symbols, needed this intuitive and simple image to take a break.

Chang Haonan could clearly feel that many people had regained their spirits.

"Next, I will show the relationship between the evolution curve C and the target contour line C* under the piecewise constant condition."

As he spoke, Chang Haonan clicked the mouse, and a white circle appeared on the first picture:

"In Figure (a), when the evolution curve C surrounds the true target contour C*, the energy functional inside the curve C is greater than zero, while the external energy is close to zero; while in (b), when the true target contour C* surrounds the curve C, the energy functional inside the curve C is close to zero, and the external energy is greater than zero..."

"That is to say, for any part of the evolution curve, we only need to calculate the energy functional values ​​inside and outside it separately to determine its positional relationship with the true target contour."

"When the calculation results of its internal and external energy are close to 0, we can determine whether it coincides with the target outline..."

At this moment, the originally dead conference room suddenly became lively——

Except for some busy international shipping lanes, there are actually not that many ships in most areas of the ocean.

In other words, most photos taken by ocean surveillance satellites only have a sea background.

Therefore, even if we just separate the target area and the background area and exclude the data that only contains the background but not the target, we can greatly reduce the communication pressure of the ground-to-space link and shorten the response time of the entire space-based reconnaissance system.

This does not take into account the efficiency of secondary identification after the data is received on the ground.

Finding an aircraft carrier in 100 photos is different from finding an aircraft carrier in photos.

The difficulty is obviously not on the same level.

"Comrade Haonan."

The speaker was Wang Shuguang, head of the State Oceanic Administration.

He certainly had no direct connection to the Navy.

But in principle, Haiyang No. 1 is a satellite belonging to the State Oceanic Administration.

Naturally, he was also invited to attend today's meeting.

"I noticed that the four pictures you used all have backgrounds with uniform grayscale, but the actual ocean background may not be so ideal. Even in the deep sea, there is a high probability that the grayscale is heterogeneous."

“Can your algorithm distinguish the grayscale difference between the backgrounds in different areas, and between the target to be observed and the overall background?”

This question is indeed professional.

Even the navy found it difficult to figure out.

"of course can."

Chang Haonan smiled:

"In fact, all we need to do is replace the grayscale mean in the model with the fitting function corresponding to the evolution curve in the local energy term."

"In most cases, a picture captured by a photo will not involve too many complex grayscale heterogeneities. Combined with the weak performance of the onboard computer, we can basically handle most situations by selecting two fitting functions."

As he spoke, Chang Haonan continued to turn the pages.

This time, a picture that was obviously an aerial view of the port appeared on the PPT.

More importantly, although the clarity is very poor, it can still be seen that there is a ship with a full deck parked in the lower left corner of the picture.

"This is……"

Wang Shuguang frowned and found that things didn't seem simple.

"The environment feels somewhat familiar..."

"Wait a minute, isn't this the Jinmen Nanjiang Wharf?"

Soon someone recognized the location:

"So this ship is the Kiev?"

"Yes."

Chang Haonan replied:

"This is a photo taken by a 244-channel CCD optical reconnaissance camera. I applied to the Air Force and just got it a few days ago."

"In addition to the Kiev, there are several other large ships whose outlines can be barely seen."

"And after our processing."

He clicked the mouse again.

In an instant, except for the ground, the dock buildings and the few ships, all parts involving the water surface turned into a light gray background with a uniform grayscale.

"Even in shallow waters with complex hydrological conditions, we can still identify large surface targets!"

After saying this, Chang Haonan turned around again.

The meeting room fell silent again.

But anyone could see that this time, it wasn't due to lethargy.

Instead, he was so shocked that he couldn't speak for a moment.

"boom--"

Until a crisp sound broke the silence.

He was a naval leader who was holding a teacup and accidentally knocked the bottom of the cup onto the edge of the table.

Apparently, the technology doesn’t even have to be put into practical use.

If only a little bit of information leaked out, it would be enough to keep Americans awake at night...