Edge AI Inspection to Enhance Crop Sorting Quality: Efficient Crop Sorting Solution

Efficient Crop Sorting Solution

Challenges of Visual Inspection

Traditional crop inspection methods, such as those for grains, beans or fruits, rely heavily on labors. Labors visually examine factors like color uniformity, cracks, size, shape and foreign objects. This process is time-consuming and susceptible to errors due to fatigue, leading to inconsistencies and unstable inspection quality and efficiency. 

 

Edge AI Inspection Solution for Crop Sorting

With advancements in agricultural technology, embedded edge AI systems now offer an efficient crop sorting solution to address the issues of time and error in visual inspection. These systems’ stability, low power consumption, and adaptability to various environments enhance inspection efficiency and ensure quality. In the application, when grains are poured into a hopper, a vibrating feeder moves the grains, and an industrial camera captures images of the grains under controlled lighting. These images are sent to the embedded system, where AI technology analyzes the features and determines quality. Based on this inference, a PLC directs an air pressure device to sort the grains by quality. 

 

Embedded System Designed for Edge AI Applications

The WEBS-21J0-ASL, equipped with the Hailo-8 AI module, delivers 26 TOPS of computational performance, suitable for real-time image inference with accurate results. The system is powered by the Intel Atom x7000RE series SoC, providing sufficient computing capability while operating at low power to suit limited-power agricultural environments. It is designed to operate in temperatures from -20°C to 60°C, withstands dust due to its fanless design, and maintains function in 5-95% relative humidity. The system’s I/O interfaces, including RS-485 for PLC and PCIe for image capture card connection, ensure connectivity with peripheral equipment. 

 

Portwell's Value-Added Services: DMS, PET, RPET

To support various application scenarios and customer needs, Portwell’s DMS (Design, Manufacturing and Services) offers comprehensive one-stop services to enhance customer value. Portwell’s PET provides an IoT solution with cross-platform APIs and applications for system monitoring and device control, simplifying IoT application integration. The PET-based RPET enables extensive remote management, including real-time firmware monitoring, power management, CPU load, memory usage, disk’s status and network load. It also supports firmware updates, ensuring stable and efficient system operation. 
WEBS-21J0-ASL

WEBS-21J0-ASL | Fanless Box PC | Embedded System

  • Support low power Intel Atom® X7000RE Series SoC
  • Up to 16GB DDR4 3200MT/s non-ECC SO-DIMM
  • Support one DP and one HDMI® display
  • Support one M.2 E Key, One M.2 B Key socket
  • SupportoneRS-232/422/485port ( selectable via BIOS)
  • One Antenna hole for WiFi module to usage
  • Support a wide -40°C to 60°C industrial temperature range
  • Optional preassemble HAILO 8 AE key module