Min
Max
Min
Max
Min
Max
Min
Max
Top Fence Computer Vision Models
The models below have been fine-tuned for various fence detection tasks. You can try out each model in your browser, or test an edge deployment solution (i.e. to an NVIDIA Jetson). You can use the datasets associated with the models below as a starting point for building your own fence detection model.
At the bottom of this page, we have guides on how to count fences in images and videos.
211 images 13 classes 1 model
143 images 18 classes 1 model
243 images 9 classes 1 model
252 images 67 classes 1 model
130 images 53 classes 2 models
605 images 12 classes 4 models
400 images 5 classes 4 models
27 images 127 classes 2 models
260 images 7 classes 1 model
1k images 25 classes 1 model
773 images 13 classes 1 model
703 images 23 classes 1 model
161 images 9 classes 1 model
81 images 21 classes 1 model
47 images 45 classes 1 model
3.3k images 23 classes 1 model
4.5k images 29 classes 1 model
40 images 13 classes 1 model
9.1k images 12 classes 1 model
Broken fence Broken/unguarded windows Damaged building facade Messy/loose wires/pipes/air conditioners Mixed entrance for pedestrians and cars No barrier-free facilities at the entrance No space for physical activity Non-existent/broken/obstructed door Non-standard parking phenomenon Stacked and discarded garbage Unauthorized construction on the building facade Unhardened/damaged road
1.7k images 13 classes 1 model