Object detection (Images)
The two most common image-processing problems are image classification and object detection.
Image classification takes an image as an input and outputs what type of object is in the image. This technique works great, even on microcontrollers, as long as we only need to detect a single object in the image.
On the other hand, object detection takes an image and outputs information about the class and number of objects, position, (and, eventually, size) in the image.
Edge Impulse provides four different methods to perform object detection:
Using MobileNetV2 SSD FPN
Using FOMO
Using NVIDIA TAO
Labelling method
Bounding boxes
Bounding Boxes
Bounding boxes
Bounding boxes
Input size
320x320
Square (any size)
Flexible
Flexible
Image format
RGB
Greyscale & RGB
RGB
RGB
Output
Bounding boxes
Centroids
Bounding boxes
Bounding boxes
MCU
❌
✅
✅
✅
CPU/GPU
✅
✅
✅
✅
Limitations
- Works best with big objects - Models use high compute resources (in the edge computing world) - Image size is fixed
- Works best when objects have similar sizes & shapes - The size of the objects are not available - Objects should not be too close to each other
- Works best on high end MCU
- More compute intensive - Not suitable for all edge devices
Last updated