Fresh-cut vegetables have a shelf life measured in hours; inspection must be fast, catch millimeter-scale targets, and keep data on premise. DaoAI moved the model to the line edge.
This prepared-vegetable plant produces salads and ready-to-eat fresh-cut vegetables, with only a few hours between cutting and dispatch, so any line stoppage to wait on cloud inference is unacceptable. Its biggest quality risk is small foreign objects — hairs, tiny insects, torn plastic-packaging fragments — that often occupy only a few dozen pixels in frame. Conventional machine vision and manual inspection miss them easily, and a single complaint hits the brand directly.
DaoAI optimized a lightweight deep-learning model for small-object detection and deployed it on an edge computing box at the line, achieving local real-time inference: images never leave the plant, latency stays in the millisecond range, and the line never slows to wait for a result. Data augmentation and hard-example mining sharpened the model's sensitivity to low-contrast, translucent contaminants; for newly appearing contaminant forms, APDT few-shot learning reinforces the model quickly, avoiding a full retrain every time packaging material changes.
Why It Has To Be at the Edge
- Fresh-cut products have a very short window; cloud round-trip latency would slow the takt, while edge inference enables real-time synchronized ejection
- Image data stays inside the plant, satisfying food-industry data-compliance and confidentiality needs
- The lightweight model runs on low-power hardware, keeping retrofit cost and footprint low
- APDT few-shot brings new contaminant types online within hours
A few-dozen-pixel hair, caught in milliseconds at the edge — speed and precision are no longer a choice of one.
After go-live, detection of millimeter-scale small foreign objects holds steadily above 98%, a marked gain over the prior manual spot-checks and conventional vision, and complaints from missed contaminants dropped sharply. A single line achieves full inspection with no added headcount, and edge deployment makes replicating the setup across multiple lines lightweight and fast.
FAQ
How does DaoAI solve the problem of detecting small target foreign objects in fresh-cut vegetables?
DaoAI optimizes a lightweight deep-learning model for small target detection and deploys it on the edge computing box of the production line. It enables local real-time inference, keeps images in the factory, has low latency, enhances sensitivity to foreign objects, and quickly supplements new forms with few samples.
Why is it necessary to conduct foreign object detection for fresh-cut vegetables at the edge?
Fresh - cut products have a short shelf-life. Cloud round-trip latency can slow down the production rhythm, while edge inference allows for real-time removal. Images stay in the factory for compliance and confidentiality. The lightweight model has low costs, and few-sample adaptation is fast, achieving both speed and accuracy.
What are the effects after the DaoAI system is launched?
After the launch, the detection rate of millimeter-level small target foreign objects is stably over 98%, significantly higher than manual sampling inspection and traditional vision. Customer complaints due to missed detections have dropped significantly. Single - line full inspection can be achieved without extra staff, and production line replication and expansion are lightweight and fast.