Refine
Has Fulltext
- yes (2)
Document Type
Language
- English (2)
Is part of the Bibliography
- yes (2)
Keywords
- damage identification (1)
- dataset (1)
- inspection (1)
- machine learning (1)
- maintenance (1)
- object detection (1)
- small objects (1)
- tiny obejcts (1)
Institute
Forest management relies on the analysis of satellite
imagery and time intensive physical on-site inspections. Both
methods are costly and time consuming. Satellite based images
are often not updated in a sufficient frequency to react to
infestations or other occurring problems.
Forest management benefits greatly from accurate and recent
information about the local forest areas. In order to react
appropriately and in time to incidents such as areas damaged by
storms, areas infested by bark beetles and decaying ground water
level, this information can be extracted from high resolution
imagery.
In this work, we propose UAVs to meet this demand and
demonstrate that they are fully capable of gathering this information
in a cost efficient way. Our work focuses on the cartography
of trees to optimize forest-operation. We apply deep learning for
image processing as a method to identify and isolate individual trees for GPS tagging and add some additional information such as height and diameter.
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.
