Object Segmentation

Overview

 

Instance segmentation in aerial images is an important topic and segmenting different instances of small objects accurately in densely populated areas is a current challenge. SkyDATA challenge aims to improve the efficiency of instance based segmentation algorithms in densely populated scenes to help with vision based algorithms.

 

METRICS:

 

This challenge uses the same input as the object detection challenge uses. Similar to the object detection task, here we also compute 17 metrics (calculated over the segmentation annotations).

 

Measure Perfect Description
AP 100% The average precision over all 10 IoU thresholds (i.e., [0.5:0.05:0.95]) of all object categories
AP IOU=0.50 100% The average precision over all object categories when the IoU overlap with ground truth is larger than 0.50
AP IOU=0.75 100% The average precision over all object categories when the IoU overlap with ground truth is larger than 0.75
AP micro 100% The average precision for micro objects.
AP tiny 100% The average precision for tiny objects.
AP small 100% The average precision for small objects.
AP medium 100% The average precision for medium objects.
AP large 100% The average precision for large objects.
AR max=1 100% The average recall given 1 detection per image
AR max=10 100% The average recall given 10 detections per image
AR max=100 100% The average recall given 100 detections per image
AR max=1000 100% The average recall given 1000 detections per image
AR micro 100% The average recall for micro objects.
AR tiny 100% The average recall for tiny objects.
AR small 100% The average recall for small objects.
AR medium 100% The average recall for medium objects.
AR large 100% The average recall for large objects.

 

 

SUBMISSON (RESULT) FORMAT FOR INSTANCE SEGMENTATION:

 

We accept submissions in a single JSON file similar to the COCO format for the entire detection task. During the submission, we require a single JSON file. Use the format below:

 

 [{           
    'image_id'      : int, 
    'category_id'   : int, 
    'segmentation'  : RLE,
    'score'         : float,
 }]  

 

A binary mask containing an instance’s segment should be encoded to RLE and you can use COCO libraries (the MaskApi function encode()) to compute that.

References:

[1] T. Lin, M. Maire, S. J. Belongie, J. Hays, P. Perona, D. Ramanan, P. Dollar, and C. L. Zitnick, “Microsoft COCO: common objects in context,” in Proceedings of European Conference on Computer Vision, 2014, pp. 740–755