Real-time instance segmentation on video
This solution is a real-time tool for object instance segmentation that detects 80 different classes on a live video stream.
__background person bicycle car motorcycle airplane bus train truck boat traffic light fire hydrant stop sign parking meter bench bird cat dog horse sheep cow elephant bear zebra giraffe backpack umbrella handbag tie suitcase frisbee skis snowboard sports ball kite baseball bat baseball glove skateboard surfboard tennis racket bottle wine glass cup fork knife spoon bowl banana apple sandwich orange broccoli carrot hot dog pizza donut cake chair couch potted plant bed dining table toilet tv laptop mouse remote keyboard cell phone microwave oven toaster sink refrigerator book clock vase scissors teddy bear hair drier toothbrush
The demo shows real-time processing of streaming video on the example of various live video streams. This demo is launched on a typical mining farm (CPU: Intel Celeron G3900, 6 GPU Nvidia GTX 1080).
The use of crypto miners resources allows us to reduce the cost of model training and inference up to 20 times compared to services by Amazon, Microsoft and other companies.
The source code for the solution is a paid feature. Please contact the solution provider.
The solution is based on Mask R-CNN. Mask R-CNN is a state-of-the-art framework for image segmentation.
The model used to build this solution:
|Accuracy:||mAP of 0.36 & 0.33|
|Format:||ONNX 1.5, Opset ver. 10|
Reference: Mask R-CNN