@inproceedings{ErbacherHellerFruehwaldetal., author = {Erbacher, Dominik and Heller, Leon and Fr{\"u}hwald, Alexander and H{\"o}sch, Leonhard and Bachmeir, Christian}, title = {Analysis of Object Detection Datasets for Machine Learning with Small and Tiny Objects}, series = {Proceedings of the Eleventh International Conference on Engineering Computational Technology}, booktitle = {Proceedings of the Eleventh International Conference on Engineering Computational Technology}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:863-opus-24895}, abstract = {Deep Learning models are trained to detect humans, cars, and other large objects which are centered in the images. The same models struggle with detecting small and tiny objects because of architecture design decisions that reduce the entropy of small and tiny objects during training. These small and tiny objects are essential for damage identification and maintenance including inspection and documentation of aeroplanes, constructions, offshore structures, and forests. Our work defines the terms tiny and small in context of deep learning models to evaluate possible approaches to resolve the issue of low accuracy in detecting these objects. We analyse the currently applied common datasets Common Objects in Context, ImageNet and Tiny Object Detection Challenge dataset. In addition we compare these datasets and present the differences in terms of object instance size. The COCO dataset, ImageNet dataset and TinyObjects dataset are analysed regarding size categorization and relative object size. The results show the large differences between the size ratios of the three chosen datasets, with ImageNet having by far the largest object instances, COCO being in the middle and TinyObjects having the smallest objects as its name would indicate. Since the objects themselves are larger in terms of total pixel width and height, they therefore make up a bigger percentage on the superordinate picture. Looking at the size categories of the COCO dataset and our extension of the tiny and very small category, the results confirm the size hierarchy of the datasets. With ImageNet having most of its objects in the large category, COCO respectively in the medium category and TinyObjects in the very small category. By taking these results into account, the reader is able to choose a fitting dataset for their tasks.We expect our analysis to help and improve future research in the area of small and tiny object detection.}, language = {en} }