Support Circle shape in labelme2coco.py JSON generation

[stephanj]

The current labelme2coco.py doesn't support the circle shape.

[stephanj]

You can achieve this by adding following logic to /examples/instance_segmentation/labelme2coco.py:

        # ...
            if label in masks:
                masks[label] = masks[label] | mask
            else:
                masks[label] = mask

            # Support for circle shape by Stephan Janssen ([email protected])
            if shape_type == "circle":
                
                # Create polygon shaped based on connecting lines from/to following degress
                bearing_angles = [0, 15, 30, 45, 60, 75, 90, 105, 120, 135, 150, 165, 
                180, 195, 210, 225, 240, 255, 270, 285, 300, 315, 330, 345, 360]
                            
                orig_x1 = points[0][0] 
                orig_y1 = points[0][1] 

                orig_x2 = points[1][0]
                orig_y2 = points[1][1]

                # Calculate radius of circle
                cx = (orig_x2 - orig_x1)**2
                cy = (orig_y2 - orig_y1)**2
                radius = math.sqrt(cx + cy)

                circle_polygon = []
            
                for i in range(0, len(bearing_angles) - 1):
                    ad1 = math.radians(bearing_angles[i])
                    x1 = radius * math.cos(ad1)
                    y1 = radius * math.sin(ad1)
                    circle_polygon.append( (orig_x1 + x1, orig_y1 + y1) )

                    ad2 = math.radians(bearing_angles[i+1])
                    x2 = radius * math.cos(ad2)  
                    y2 = radius * math.sin(ad2)
                    circle_polygon.append( (orig_x1 + x2, orig_y1 + y2) )

                points = circle_polygon

            else:
                points = np.asarray(points).flatten().tolist()
            
            segmentations[label].append(points)                

        for label, mask in masks.items():
        # ...

[pieterblok]

@stephanj thank you for this good addition!!! I would recommend to add one additional line of code at the end of the circle procedure, as this line will flatten the array in such a way that it corresponds to the visualization method of the cocoapi. Again, thank you for this addition.

You can achieve this by adding following logic to /examples/instance_segmentation/labelme2coco.py:

        # ...
            if label in masks:
                masks[label] = masks[label] | mask
            else:
                masks[label] = mask

            # Support for circle shape by Stephan Janssen ([email protected])
            if shape_type == "circle":
                
                # Create polygon shaped based on connecting lines from/to following degress
                bearing_angles = [0, 15, 30, 45, 60, 75, 90, 105, 120, 135, 150, 165, 
                180, 195, 210, 225, 240, 255, 270, 285, 300, 315, 330, 345, 360]
                            
                orig_x1 = points[0][0] 
                orig_y1 = points[0][1] 

                orig_x2 = points[1][0]
                orig_y2 = points[1][1]

                # Calculate radius of circle
                cx = (orig_x2 - orig_x1)**2
                cy = (orig_y2 - orig_y1)**2
                radius = math.sqrt(cx + cy)

                circle_polygon = []
            
                for i in range(0, len(bearing_angles) - 1):
                    ad1 = math.radians(bearing_angles[i])
                    x1 = radius * math.cos(ad1)
                    y1 = radius * math.sin(ad1)
                    circle_polygon.append( (orig_x1 + x1, orig_y1 + y1) )

                    ad2 = math.radians(bearing_angles[i+1])
                    x2 = radius * math.cos(ad2)  
                    y2 = radius * math.sin(ad2)
                    circle_polygon.append( (orig_x1 + x2, orig_y1 + y2) )

                points = circle_polygon
                points = np.asarray(points).flatten().tolist()

            else:
                points = np.asarray(points).flatten().tolist()
            
            segmentations[label].append(points)                

        for label, mask in masks.items():
        # ...

[xingkongliang]

You can achieve this by adding following logic to /examples/instance_segmentation/labelme2coco.py:

        # ...
            if label in masks:
                masks[label] = masks[label] | mask
            else:
                masks[label] = mask

            # Support for circle shape by Stephan Janssen ([email protected])
            if shape_type == "circle":
                
                # Create polygon shaped based on connecting lines from/to following degress
                bearing_angles = [0, 15, 30, 45, 60, 75, 90, 105, 120, 135, 150, 165, 
                180, 195, 210, 225, 240, 255, 270, 285, 300, 315, 330, 345, 360]
                            
                orig_x1 = points[0][0] 
                orig_y1 = points[0][1] 

                orig_x2 = points[1][0]
                orig_y2 = points[1][1]

                # Calculate radius of circle
                cx = (orig_x2 - orig_x1)**2
                cy = (orig_y2 - orig_y1)**2
                radius = math.sqrt(cx + cy)

                circle_polygon = []
            
                for i in range(0, len(bearing_angles) - 1):
                    ad1 = math.radians(bearing_angles[i])
                    x1 = radius * math.cos(ad1)
                    y1 = radius * math.sin(ad1)
                    circle_polygon.append( (orig_x1 + x1, orig_y1 + y1) )

                    ad2 = math.radians(bearing_angles[i+1])
                    x2 = radius * math.cos(ad2)  
                    y2 = radius * math.sin(ad2)
                    circle_polygon.append( (orig_x1 + x2, orig_y1 + y2) )

                points = circle_polygon

            else:
                points = np.asarray(points).flatten().tolist()
            
            segmentations[label].append(points)                

        for label, mask in masks.items():
        # ...

                ...
                points = circle_polygon
                points = np.asarray(points).flatten().tolist()
                ...

[fanweiya]

@stephanj Why are the segmentations points the same after use circle transformation? Can You upload the full script？this is my datasets