Waste_Object_Segmentation

Waste Object Segmentation with state of art algorithm YOVOv5 trained on Custom Dataset.

Here I address the problem of localizing waste objects from a color image and an optional depth image, which is a key perception component for robotic interaction with such objects. Specifically, our method integrates the intensity and depth information at multiple levels of spatial granularity. Firstly, a scene-level deep network produces an initial coarse segmentation, based on which we select a few potential object regions to zoom in and perform fine segmentation.

I have tranied multiple YOLOv5 model check the model validation states..

To evaluate object detection models like R-CNN and YOLO, the mean average precision (mAP) is used. which is around 95% with this perticular dataset..

Results from model-7

Due to less amount of data here i have trained yolov5 for only 8 class detection and confusion matrix for best model from tranied models so far look as below

-->Note: Pretrained weights are confidential. If you need then feel free to reach out for industrial use purpose..