:::

【2021 Application Example】 AI Analysis Cloud Service Platform for Remote Sensing Big Data Enables the Smooth Application of Satellite Remote Sensing Images

Although satellite remote sensing images can make all surface objects visible, it still requires a lot of time and manpower to be truly applied to the industry. In order to effectively solve the problems that customers face in digesting huge amounts of image data and eliminate technical obstacles for cross-domain users to process satellite remote sensing images, ThinkTron has developed an "AI Analysis Cloud Service Platform for Remote Sensing Big Data" as a new beginning for cross-domain AI applications for spatial information.

In recent years, in response to the impact of industrial globalization, Taiwan's agriculture has continued to transition towards technology-based and higher quality, improving the yield and quality of crops by solving problems, such as microclimate impacts and pest and disease control. The demand of agriculture on images has expanded endlessly to accurately grasp the growing environment of crops. In the early years when UAVs (unmanned aerial vehicles) were not yet popular, manual field surveys were the most basic but most labor-intensive work. With the emergence of UAV drones, aerial photography operations might not be difficult, but the range that can be photographed is limited. Furthermore, surveying expertise is required to accurately capture spatial information. At this time, the use of satellite remote sensing data may break away from the past imagination of using image data.

Taiwan Space Agency (TASA) ODC data warehouse services

▲ Taiwan Space Agency (TASA) ODC data warehouse services

In the past ten years, with the breakthrough of modern satellite remote sensing application technology, Digital Earth has become a new trend in global data collection. Countries have developed data cube image storage technology, and the development of smart agriculture has become one of the largest image users. Determining planting distribution is the first step in understanding crop yields. Free satellite remote sensing images, powerful data warehousing support, and the team's robust image recognition technology are important supports for accelerating agricultural transformation.

Using satellite remote sensing image data can accelerate the development of smart agriculture.

However, in the past, it was difficult to extract large-area crop distribution through satellite remote sensing images, not to mention the cost. If you wanted to use free information, you had to visit all websites of international space agencies, look through the wide variety of satellite specifications, and carefully evaluate the sensor specifications, image resolution, and revisit cycle. After finding suitable images, you had to look at them one by one to filter the ones you need. Next is downloading dozens of images that are often several hundreds of Megabytes (MB) each, which might exceed the capacity of your computer.

Also, after overcoming image access and preparing data, you must then start to confirm the downloaded image products and which bands you want, because the image you see is not just an image file (.jpg or .png), but rather complex multi-spectral information, attribute fields and coordinate information. It takes a lot of effort just to confirm the correct information. Facing GIS software packages with complex functions is the start of another trouble. The complex image pre-processing process and the inflexible machine learning package greatly reduce the efficiency of analyzing data. After finally getting the results of crop identification, you might find that the best time for using map information may have already passed. The above-mentioned complex and time-consuming satellite image processing problems are precisely the pain points of the market. ThinkTron expanded from traditional machine learning to modern deep learning applications, and developed an "AI Analysis Cloud Service Platform for Remote Sensing Big Data" under the GeoAI framework, breaking through the constraints of details in the spatial information for customers.

Differences between the process before and after introducing the AI analysis cloud service platform

▲Differences between the process before and after introducing the AI analysis cloud service platform

ThinkTron said that Taiwan's ODC (Open Data Cube) system has been completed and began providing services after years of efforts from the Taiwan Space Agency (TASA), formally becoming aligned with international trends. The powerful warehousing technology allows users to easily capture and use image data of a specific time and spatial range according to their needs. The warehouse stores multiple satellite image resources from international space agencies, including the ESA's Sentinel-1 (one image every 6 days), Sentinel-2 (one image every 6 days), USGS's Landsat-7 (one image every 16 days), Landsat-8 (one image every 16 days), and the domestic Formosat-2 (one image every day) and Formosat-5 (one image every 2 days).

ThinkTron develops satellite image recognition tools based on Python

Breaking free from the limitations of GIS (Geographic Information System) software packages, ThinkTron integrated GDAL (Geospatial Data Abstraction Library) based on Python, and considered computing efficiency and parallel processing when developing all tools required for satellite image processing and image recognition modeling, including coordinate system and data format conversion, grid and vector data interaction, and data intra-difference and normalization. All of the tools are designed with AI applications in mind, and some commonly used tools are packaged into an open source package under the name TronGisPy to benefit the technical community. ThinkTron utilized the team's understanding of satellite remote sensing images and the collected tagged data (crop distribution maps) to preset the image recognition modeling process, the required training data specifications, and dataset definitions. This is imported into the machine learning (LightGBM) or deep learning (CNN) framework that was completed in advance, and the entire training process to be performed in the Web GIS interface, providing users with partial flexibility to freely filter images, confirm spatial and temporal ranges, select models, and adjust hyperparameters. In addition to the operation of training models, it also provides historical models to output identification results, and finally displays the identification results of crop distribution on the Web GIS map.

In fact, agriculture is not the only industry that needs satellite remote sensing applications. AI applications of spatial information have also appeared in various fields as companies in different industries aim to enhance their global competitiveness. For example, surveying and mapping companies that have a large amount of map data can use the AI analysis cloud service platform to store map data while also accelerating the efficiency of digital mapping. Under the severe global climate change and the risk of strong earthquakes, there is a wide variety industrial insurance, agricultural insurance, financial insurance, or disaster insurance are all inseparable from spatial information. The use of remote sensing image recognition to understand insurance targets has long been an international trend.

▲ AI Analysis Cloud Service Architecture for Remote Sensing Big Data

Recommend Cases

【解決方案】連聯合國都買單 悠由數據應用運用農業數據搶攻全球商機
Even the United Nations is on board! Yoyo Data Application captures global business opportunities with agricultural data

Nearly 2,000 days in the fields have made Yoyo Data Application a top player in Taiwan’s agricultural data sector Their comprehensive grasp of crop yields, production periods, and prices has enabled them to collaborate with the United Nations The service area for agricultural land skyrocketed from 24 hectares to over 6,000 hectares in less than three years—a 250-fold increase For Wu Junxiao, founder and CEO of Yoyo Data Application, aligning with global environmental trends and becoming a data company at the intersection of climate technology and the green economy to serve the global market is his ultimate entrepreneurial goal Wu Junxiao, originally an engineer, joined the Industrial Technology Research Institute in 2010, where he honed his profound technical and data science analytic skills 'At that time, I was working in data analysis engineering, and almost all data-related materials would be directed to me Additionally, I worked on indoor cultivation boxes, planting vegetables and mushrooms, hence planting the seed of entrepreneurship by integrating agriculture with data analysis,' Wu recalls Since 2016, Wu Junxiao has been frequently visiting farms to 'embed' himself among farmers and agricultural researchers, chatting and sharing information systematically, which quickly established his agricultural know-how Solid data analysis capabilities have even convinced the United Nations In 2017, he left the Institute to start his own business and founded Yoyo Data Application in 2019 Today, many agricultural businesses are his clients, with service areas rapidly climbing from 24 hectares to over 6,000 hectares, expected to surpass 7,000 hectares in 2022 His clientele includes markets in Japan, Central America, and even entities under the United Nations like the World Farmers Organization, which utilizes the 'Yoyo Crop Algorithm System' supported by Yoyo Data How exactly does Yoyo Data Application manage to impress even UN agencies The 'Yoyo Crop Algorithm System' developed by Yoyo Data Application accurately predicts the production period, yield, and prices Firstly, due to Wu Junxiao's precise mastery over agricultural data, Yoyo Data Application's clients don't necessarily need sensors or other hardware devices 'Sensors are expensive and if you buy cheap devices, you just collect a lot of noise or flawed data, which is useless,' Wu explains He continues, 'Collecting data doesn't necessarily require sensors our data solutions can solve problems more directly and effectively' For instance, one of Yoyo Data Application's products, the Yoyo Money Report Agri-price Linebot, developed in collaboration with LINE in 2020, gathers data on origin, wholesale, and terminal prices spanning over 10 years, driven by Yoyo Data’s proprietary AI algorithms This enables the system to autonomously learn about agricultural product trading prices, using big data and AI to perform price prediction analysis, thereby helping buyers reduce transaction risks and expanding the data application to the entire agricultural supply chain Regarding banana prices, the accuracy of price predictions increased from the original 70 to 998 Wu Junxiao notes that both buyers and farmers are very sensitive to prices Now, through the Yoyo Money Report service, both buyers and farmers can precisely understand the fluctuations in agricultural product prices Yoyo Data can also provide customers with optimal decision-making advice based on predictive models for crop growth, yield, and price estimations Currently, price predictions cover 28 types of crops Precise estimates of production periods and price fluctuations allow Yoyo Data to provide differentiated services based on data analysis The 'Yoyo Crop Algorithm System' provided by Yoyo Data Application incorporates a 'Parameter Bank', usually collecting 200-300 parameters, not just straightforward data like temperature and humidity, but also data divided according to the physiological characteristics of the crops Through effective dynamic data algorithms, it can accurately calculate when crops will flower and when they can be harvested, what the yield will be, and so forth For instance, the prediction accuracy of the broccoli production period is 0-4 days, with the flowering period predicted this year to be precisely 0 days, perfectly matching the actual flowering time in the field In these dynamic calculations, a 7-day range is considered reasonable, and the average error value of Yoyo Data's predictions typically ranges from 2-4 days, with most crop production period accuracies above 80 Through effective dynamic data algorithms, over 120 global crops can have their production periods and yields accurately estimated Using these effective dynamic data algorithms can set estimates for production quantities, helping adjust at the production end Yoyo Data Application's clientele primarily includes exporters of fruit crops like pineapples, bananas, guavas, mangos, pomelos, sugar apples, Taiwan's agricultural production is highly homogenized, often leading to a rush to plant the same crops and resulting in price crashes Yoyo Data Application helps clients differentiate their offerings Thus, Wu Junxiao positions his company as a boutique digital consultant, carefully selecting clients for quality over quantity He notes that Taiwanese agricultural clients focus on how to improve yield rates, even categorizing yield rates by quality, aiming for high-quality, specialized export markets whereas international clients prioritize maximizing per-unit yields, showing different operational approaches in domestic and international markets In addition to agricultural fruit, Yoyo Data Application has also extended its services to the fisheries sector, including species like milkfish, sea bass, and white shrimp, all using the same system to establish various parameters related to the growth of fish and shrimp, such as when to feed and when to harvest, and the anticipated yield, timing, and prices Yoyo Data Application harnesses the power of data to create miracles in smart agriculture In response to the company's rapid development, Yoyo Data Application introduced venture capital funds in 2021 to expand its staff and promote its business Wu Junxiao states that in response to the global trend towards net zero carbon emissions by 2050, he plans to help clients plant carbon in the soil, effectively retaining carbon in the land while also connecting clients to carbon trading platforms, creating environmental business opportunities together Wu Junxiao says that from the start of his entrepreneurial journey, he positioned the company as a global entity, thus continuous international collaborations are planned As a data company serving a global clientele and focused on climate technology and the green economy, this represents Wu’s expectations for himself and his company's long-term goals Yoyo Data Application founder and CEO Wu Junxiao「Translated content is generated by ChatGPT and is for reference only Translation date:2024-05-19」

這是一張圖片。 This is a picture.
Testing Seat Contact Components AI Intelligent Flaw Detection

With rapid development in 5G, AIOT, automotive electronics, and other downstream sectors, the entire supply chain is expected to benefit from this consumer market As product demand momentum gradually increases, increasing production efficiency and reducing operational costs become the most important issues In order to meet the needs of customers for various packaging types, Yingwei Technology has been committed to developing highly customized test seats However, a resulting pain point is the inability to mass-produce and fully automate operations with machines some tasks still rely on manual execution In this project, the probe part of the test seat was outsourced in 2021, and under current and future large-scale demands, work hours, costs, supply, and quality are issues Yingwei faces The company achieves a defect detection rate of 9995, which seems high, but with an average inspector able to inspect 10,000 needles per day, there would still be 5 defective needles On a test seat that is only 3 cm wide with approximately 1,000 needles, just one defective needle could potentially lead to faulty testing at the customer end As the current operational mode relies on manual visual inspection, external factors such as fatigue or oversight of personnel, and subjective judgment by inspectors may lead to the outflow of defective products, which necessitates strict quality control of contact components We once sought to utilize optical inspections Rule-based for controlling the quality of appearances, but the metallic material of the contact components leads to light scattering, background noise interference, background scratches, and material issues that could result in misjudgments Therefore, we decided to look for AI technology service providers to solve our detection difficulties Developments of Dedicated AOI Line Scan Equipment To meet the needs for inspecting thousands to tens of thousands of probes within our company's IC test seats, traditional surface imaging and individual needle imaging would be too slow to achieve rapid inspection and labor-saving goals In response, the service provider proposed a trial with an AOI dedicated line scan module solution Utilizing a width of 63mm on the X-axis for reciprocal scanning of all probes on the test seat, the tests allowed for the simultaneous scanning of 8-9 probes, significantly enhancing the future detection efficiency of AOI machines This project will proceed with the aforementioned innovative Proof of Concept POC, focusing on the development of the line scanning equipment and performing imaging, learning, and training on both normal and abnormal probes provided by our company, with initial AI model training aimed at preliminary approval This project's customized line-scan imaging module Ideal future imaging result illustration A Single AI Technology Solution for MeasurementDetection Needs Unified use of AI DL CNN learning methods, instead of the current Rule-based system which necessitates defining each defect individually, to meet the needs for abrasion measurement and appearance defect detection of malfunctionsforeign objects When the same machine uses both measurement and detection technologies, not only does it increase costs, but it also affects the detection speed Hence, the service provider recommends the use of a line scan device for imaging Its resolution is sufficient for AI to simultaneously determine appearance defects and assess the condition of needle tip abrasion, as detailed below Line scan pixel imaging displaying needle tip abrasion conditions This AI detection technology meets both measurement and inspection needs for Yingwei, not only bringing more benefits to future probe testing but also introducing an innovative axis in AI technology Change the method of human inspection, enhance work efficiency and product quality After combining both hardware line scan and software AI model training approaches, we successfully ventured into new AOI detection applications Following the AI implementation POC, including the development and validation of a customized line scan module and an initial AI model, the plan is to officially develop the AOI machine next year and integrate it into the IC test seat production line Future Prospects Probe manufacturers upstream and downstream IC factory users both have needs for the AOI inspection machine upstream can ensure probe quality before leaving the factory, while downstream users can use this machine to regularly inspect the condition of numerous IC test seats in hand Given the future demands, the AOI machine is poised to have a significant positive impact on the IC testing industry in the foreseeable future 「Translated content is generated by ChatGPT and is for reference only Translation date:2024-12-12」

這是一張圖片。 This is a picture.
CCTV Intelligent Video Search System

Search for a specific person, find someone with a suitcase entering the factory in Gao'an area Color features of the person and the object confirmed, person in blue and black top, suitcase in black color, throughCCTV the intelligent video search system, by setting object and color retrieval conditions, it can successfully locate three video clips containing the target subject This greatly aids operational staff in finding the target items, and through this system, search speed can far surpass manual effort6fold Pain Points The CSE-Kaohsiung Plant is densely equippedCCTVto monitor every corner of the plant area, but when an incidenthappens, it's impossible within a limited time throughCCTVvideo playback to find the incident, the implications and risks behind this are self-evident Many areas that are usually unmanned can easily become security blind spots Thus, how to monitor a vast plant area more intelligently and effectively is one of the crucial aspects of building a smart plant for the semiconductor industry The AES Plant in Kaohsiung covers a vast area, with many important sites requiring monitoring of personnel movements to ensure corporate secrets and employee safety 1 Automated production lines and warehouses In semiconductor enterprises’ automated production lines and warehouses, oftenAGV(Automated Guided VehicleAGVs automated guided vehicles travel at high speeds if plant personnel inadvertently enterAGVthe moving area and cannot issue a warning to the person, then the regrettable accidents that occur will be too late to reverse 2 Material and product storage areas Materials used in semiconductor-related processes are costly if areas storing materials or products are breached, there is a risk of loss of high-value materialsproducts 3 High-security areas Trade secrets relate to the core technological competitiveness of semiconductor-related enterprises if someone breaches the high-security areas, there is a risk of corporate secrets being leaked The safety of trade secrets has always been one of the most critical issues for semiconductor enterprises 4 Loading docks At AESLButthe dock area often has loading vehicles coming and going if someone intrudes into the dock area, there is a risk of vehicle collisions and accidents Additionally, goods awaiting shipment at the dock area could be stolen or potentially damaged from collisions, thus causing significant reputation and financial losses for the company, further leading to production and shipping inconvenience When an abnormal event occurs, how to quickly search for the relevant key footage from massive data Many important locations within the AES Kaohsiung Plant need to be equippedCCTVfor safety checks, butCCTVWith thousands to tens of thousands of cameras, manually searching through footage for an event requires laborious frame-by-frame review which is time-consuming and inefficient In light of advancements in computer vision, it's beneficial to utilizeAIto replace manual playback and searching Problem Scenario Object Detection The data source for object detection comprises two parts Open-source datasetsOIDv4and AES Kaohsiung PlantCCTVImage files For these files, search for usable data, specificallyOIDv4image files For these files, extract the defined nine major categories of objects for training data among them, two object categories, knives and gasoline barrels, were not found inOIDv4found usable data for knives and gasoline barrels, while the remaining seven categories of objects are available fromOIDv4useful training data found for the remaining seven categories of objects, all marked Regarding the Kaohsiung PlantCCTVimage files, select some frames Frame of the footage, and manually annotate the objects to be_detected for training and testing data Nine Major Objects Color Recognition The data source for color recognition is divided into two partsInternet image screenshots, and Kaohsiung PlantCCTVimage files Currently, no publicly available open-source datasets specifically for color recognition applications have been found, so images are collected from the web Search the web for images of the defined nine major object categories, save the images after separating the objects from the background, keeping only the object sections, and mark the images according to color Additionally, for the Kaohsiung PlantCCTVimage files, use the already-markedbounding boxextractCCTVimage files from variousFramesections of objects identified by color, and finally, visually identifiable images are marked according to color Each object category has its specific color definition, depending on the usual colors seen in these objects in real life Dynamic Ignore during Training FromOIDv4during the training of the object detection pilot model, since each image in this dataset is only marked for a single category, but the image may contain other desired detection categories unmarked For such cases, dynamic ignore techniques will be employed during training to avoid confusion Next, use the extracted training data from the Kaohsiung Plant toFine-Tuneenhance the detection rate of the object in specific designated areas Finally, select the model that computes the lowest loss value in the test set during the training process as the main object_detection model Dynamic Ignoring AIHelp You View CCTV The intelligent video search system primarily serves as an assistive system for searching surveillance footage, capable of speeding up the process of finding target events by setting search conditions for objects By simply defining the search conditions, you can quickly produce thumbnails of critical objects and playback for review, shortening the time required for manual case retrieval of the past The search time is quickly6doubled, allowing the front-end security unit to use this platform to strengthen the first line of risk management supervision and take timely preventive measures 「Translated content is generated by ChatGPT and is for reference only Translation date:2024-12-12」