AI-based autonomous forest stand generation
In recent years, the tech is moving towards a more automized and smarter software. To achieve smarter software the implementation of AI is a step towards that goal. The forest industry needs to become more automized and decrease the manual labor. Decreasing manual labor will both have a positive imp...
| Main Author: | |
|---|---|
| Format: | Others |
| Language: | English |
| Published: |
Mittuniversitetet, Institutionen för informationssystem och –teknologi
2021
|
| Subjects: | |
| Online Access: | http://urn.kb.se/resolve?urn=urn:nbn:se:miun:diva-43517 |
| Summary: | In recent years, the tech is moving towards a more automized and smarter software. To achieve smarter software the implementation of AI is a step towards that goal. The forest industry needs to become more automized and decrease the manual labor. Decreasing manual labor will both have a positive impact on both the cost and the environment. After doing a literature study the conclusion was to use Mask R-CNN to be able to make the AI learn about the pattern of the different stands. The different stands were extracted and masked for the Mask R-CNN. First there was a comparison between the usage of a computer versus Google Colab, and the results show that Google Colab did deliver the results a little faster than on the computer. Using a smaller area with fewer stands gave a better result and decreased the risk of the algorithm crashing. Using 42 areas with about 10 stands in each gave better results than using one big area with 3248 stands. Using 42 areas gave the result of an average IoU of 42%. Comparing this to 6 areas with about 10 stands each gave the result of 28% IoU. The result of increasing the data split to 70/30 did gave the best IoU with the value of 47%. |
|---|