Welcome to Edge Impulse, the largest community of edge AI developers!
This is a public Edge Impulse project, use the navigation bar to see all data and models in this project; or clone to retrain or deploy to any edge device.
This is a public Edge Impulse project, use the navigation bar to see all data and models in this project; or clone to retrain or deploy to any edge device.
Visual Anomaly Detection - DHT11
About this project
This dataset has been collected by Edge Impulse teams and contains a single DHT11 sensor, centered in the frame, with a similar size and a uniform background.
The training dataset only contains "nominal" (no anomaly) images whereas the testing dataset contains both nominal and anomalous images.
The DHT11 have been used to teach IoT classes in the past and have been manipulated by students extensively. When not wiring the pins properly, it can cause an overheat which often lead to the plastic melting. Some other anomalous images are missing wiring pins.
Compatible Blocks
- Feature extraction: Image
- Learning block: Visual Anomaly Detection (FOMO-AD)
Not sure what to choose? Try out this dataset with the EON Tuner.
This project has no trained model yet.
Dataset summary
Data collected
195 itemsLabels
no anomalyProject info
| Project ID | 497422 |
| Project version | 4 |
| License | BSD 3-Clause Clear |
| No. of views | 19,644 |
| No. of clones | 11 |
