Bringing AI to the Edge- Application Cases
Advantech AI Edge Solutions – MIC Jetson series, powered by full NVIDIA® Jetson™ platform, which gets all the performance of a GPU workstation in an embedded module.Featuring strict validation to ensure thermal, mechanical, and electrical compatibility, plus industrial-grade anti-vibration, high temperature operation capabilities, and modular, compact-sized design, Advantech’s MIC Jetson series are perfect hardware platforms for the surveillance, transportation, and manufacturing sectors.
Case 1 - Traffic Monitoring
MIC-720AI leverages AI inference technology to perform traffic monitoring on massive amounts of collected data; surpassing traditional vehicle recognition methods used for object tracking.
MIC-720AI fulfills deep learning computing requirements at the roadside, where metadata is packaged and transmitted to the central control room. It also provides multiple interfaces to integrate with other traffic equipment.Read the Full Case
Case 2 - Improving Wait Time at Major Intersections
Taipei’s traffic lights’ lengthy countdowns exist to provide fixed and enough time for pedestrians to safely cross wide roads. Such arrangements burdensome around midnight when fewer pedestrians and vehicles traverse Taipei’s streets.
After deploying this AI system, night wait times at red lights on arterial roads decreased by 35% and arterial roads green light periods increased by 7 ~ 79%. Also, it reduces carbon dioxide emissions by around 23 tons every year and results in an annual economic benefits of around TWD 1.83 million for each intersection.Read the Full Case
Case 3 - Tracking Healthy Bee Hive Populations with the Latest in Machine Vision Technology
In recent years, beekeepers have been reporting they are losing, on average, 30 percent of all honeybee colonies each winter. This is twice the loss considered economically tolerable. Similarly, wild bee populations are also in decline.
So, we must learn more about bee hive health, bee behavior, and queen failure in an effort to limit future bee hive loss. Now, to get a complete picture of the health of the bee hive, SAS had to be able to collect, visualize a variety of IoT data and use AI analyze from video and audio data.Read the Full Case
Case 4 - Quality Control in Cookies Factory
To maintain consistent quality for bakeries, MIC-720AI deploys various AI models to ensure that all cookies are well baked in the production line. Compared to traditional quality control procedures performed through visual inspection, AI inference detects subtle levels of difference in how individual cookies are baked, adjusts the oven to meet quality standards, and avoids under-baked or overbaked products.Read the Full Case
Case 5 - AI Defect Inspection for Textile
AI inference requires high computation and needs a GPU-based solution to accelerate the computation. MIC-730AI is powered by an NVIDIA® Jetson AGX Xavier™ GPU and is employed as the edge AI system. MIC-730AI's great processing power makes it possible to automatically inspect high-precision textile goods with better speed and accuracy.
Textile defect inspections using AI inference technology can efficiently identify the most subtle defects and ensure high quality products.Read the Full Case
Case 6 - Multiple-model AI Inspection for Heat Sink
MIC-730AI conducts AI image analysis to compare and identify heat sinks with appearance defects.This is made possible by feeding AI model training system with images of defective products that collected from clients, prior to the import of software and hardware. After AI model completes relevant training, the trained models are placed into the MIC-730AI.
AI visual inspection can then be conducted to evaluate the flatness and identify crushes, stains, scratches and other defects that are difficult to categorize through general physical rules.Read the Full Case
Case 7 - AI Analysis: Identifying Critical Production Bottlenecks
The Human Factor Information Datamation AI System uses cameras to record worker actions and then analyze images and video through AI inference. This system assists foundries in identifying bottlenecks and improving production efficiency.
Five major electronic manufacturing service foundries adopt this systems. With the aid of AI deep-learning software, factories increased their Unit Per Hour (UPH) by 5% within only two months.Read the Full Case
Case 8 - Edge AI Security System Based on Standard IP Video Cameras
By using Edge AI, video streams from regular cameras can be analyzed in real time at the network edge and used to make critical security decisions. They can detect if triggered events are true intrusions or just false alarms, and they can instantly send notifications directly to your mobile phone with recorded video and pictures. Best of all, there is no additional cost on a security system, no expensive installation of sensors, and no high maintenance costs, this is the perfect solution for using your pre-installed security cameras to keep your family and assets safe.Read the Full Case
Case 9 - AI Empowered Indoor & Outdoor Facility Safety
Modern construction sites utilize real-time visual detection systems that analyze 20 to 30 live streams simultaneously. In these systems, visual AI increases the visibility of on-site workers and equipment to improve responsiveness to potentially dangerous situations — such as an employee carelessly approaching moving machinery. Real-time video feeds are available via the cloud to any device with a screen. To avoid tragedies or accidents, real-time alerts are sent to screens; and via methods including SMS and email.Read the Full Case
Case 10 - “Screen Data Extractor (SDE)” Aimed at AI Smart Factory Transformation
GoodLinker and Advantech designed the Screen Data Extractor (SDE) to address data collection issues by integrating software and hardware. Advantech’s MIC-710AIX industrial-grade edge AI computer leverages the GoodLinker OCR recognition, yielding an excellent SDE solution. This system exploits VGA/HMI data output to ocular-recognize and record data presented on screen. SDE is an external device; as such, data collection can be completed with minimal impact on the production plan and production line.Read the Full Case