Currently, the yolov5_ros packages uses YOLOv5 for real time object detection and publishes result on a ROS topic. It uses this branch of the yolov5 github repo to do object detection.
My question is, if I use the master branch which allows for image segmentation, what changes need to be made to the detect script to publish result of segmentation on a ros topic? What could be the message type in this case?
In the attachment, I have shown result of strawberry segmentation done with YOLO v5. In the next step, I want to use this result to extract point cloud of one of the segmented strawberries for robot picking.
Hello,
Currently, the yolov5_ros packages uses YOLOv5 for real time object detection and publishes result on a ROS topic. It uses this branch of the yolov5 github repo to do object detection.
My question is, if I use the master branch which allows for image segmentation, what changes need to be made to the detect script to publish result of segmentation on a ros topic? What could be the message type in this case?
In the attachment, I have shown result of strawberry segmentation done with YOLO v5. In the next step, I want to use this result to extract point cloud of one of the segmented strawberries for robot picking.
Thank you.