Abstract
Cities of the future will carefully manage their ecological environment, including parks and trees, as critical resources to balance the effects of climate change. As such, tree health has become an integral part of well-managed cities and urban areas, where tree censuses provide a critical source of ecological data. This data provides information to improve the ecological status of these areas; however, gathering this data is laborious and requires expert knowledge to accurately register each tree species included in the census. With recent advances in object-detection methods, automating this type of census is now possible. However, these approaches require training data to be gathered, labelled, and validated. This study merged data from a tree census in the Auckland region (New Zealand) with Google Street View image data and used a pre-trained model on specialised datasets released by prior authors to create a training dataset for pedestrian-view tree species detection. This approach can be used as the basis for wider data collection and labelling of New Zealand urban tree species, crucial for inventorying the state and health of its urban forests. Here, we demonstrated that training and deploying a fine-grained object detection model to an edge device for real-time inference on a video stream can achieve speeds of 25 frames per second (fps).
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Alphabet Inc: Google street view static API,. https://maps.googleapis.com/maps/api/streetview/. Accessed 25 Mar 2023
Beery, S., et al.: The auto arborist dataset: a large-scale benchmark for multiview urban forest monitoring under domain shift. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 21294–21307 (2022)
Braithwaite, J.M.: Chapter 17: challenges and payoffs of building a dataset from scratch, pp. 300–316. Edward Elgar Publishing, Cheltenham, UK (2022). https://doi.org/10.4337/9781839101014.00028
Cubuk, E.D., Zoph, B., Mané, D., Vasudevan, V., Le, Q.V.: Autoaugment: learning augmentation policies from data. CoRR (2018)
Fu-En, W.: Equirec2perspec. https://github.com/fuenwang/Equirec2Perspec. Accessed 9 Apr 2023
Heartex Inc: Label studio. https://labelstud.io/. Accessed 9 Apr 2023
Kin Yiu, W.: Yolov 7: implementation of paper (2022). https://github.com/WongKinYiu/yolov7. Accessed 9 Apr 2023
Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. Commun. ACM 60(6), 84–90 (2017). https://doi.org/10.1145/3065386
Lumnitz, S.: Mapping urban trees with deep learning and street-level imagery. Ph.D. thesis, University of British Columbia (2019). http://dx.doi.org/10.14288/1.0387513
NZ, S.: General electoral district 2014. https://datafinder.stats.govt.nz/layer/104062-general-electoral-district-2014/. Accessed 3 Apr 2023
Orlita, T.: Steet view download 360 (2016). https://svd360.istreetview.com/. Accessed 9 Apr 2023
Pias, M., Botelho, S., Drews, P.: Perfect storm: DSAs embrace deep learning for GPU-based computer vision. In: 2019 32nd SIBGRAPI Conference on Graphics, Patterns and Images Tutorials (SIBGRAPI-T), pp. 8–21 (2019). https://doi.org/10.1109/SIBGRAPI-T.2019.00007
Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: You only look once: unified, real-time object detection (2015). https://doi.org/10.48550/ARXIV.1506.02640
University of Auckland: Geodatahub. https://geodatahub.library.auckland.ac.nz/. Accessed 25 Mar 2023
Velasquez, L., Echeverria, L., Etxegarai, M., Anzaldi Varas, G., Miguel, S.D.: Mapping street trees using google street view and artificial intelligence (2022)
Wang, C.Y., Bochkovskiy, A., Liao, H.Y.M.: Yolov7: trainable bag-of-freebies sets new state-of-the-art for real-time object detectors (2022). https://doi.org/10.48550/ARXIV.2207.02696
Wang, C.Y., Liao, H.Y.M., Yeh, I.H.: Designing network design strategies through gradient path analysis (2022). https://doi.org/10.48550/ARXIV.2211.04800
Wang, Y., et al.: Utd dataset (2022). https://github.com/yz-wang/OD-UTDNet. Accessed 23 Oct 2022
Wegner, J.D., Branson, S., Hall, D., Schindler, K., Perona, P.: Cataloging public objects using aerial and street-level images - urban trees. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 6014–6023 (2016)
Zou, Z., Chen, K., Shi, Z., Guo, Y., Ye, J.: Object detection in 20 years: a survey. Proc. IEEE 111(3), 257–276 (2023). https://doi.org/10.1109/JPROC.2023.3238524
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Ooi, M., Valdez, D.A.S., Rogers, M., Ababou, R., Zhao, K., Delmas, P. (2023). Construction of a Novel Data Set for Pedestrian Tree Species Detection Using Google Street View Data. In: Blanc-Talon, J., Delmas, P., Philips, W., Scheunders, P. (eds) Advanced Concepts for Intelligent Vision Systems. ACIVS 2023. Lecture Notes in Computer Science, vol 14124. Springer, Cham. https://doi.org/10.1007/978-3-031-45382-3_28
Download citation
DOI: https://doi.org/10.1007/978-3-031-45382-3_28
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-45381-6
Online ISBN: 978-3-031-45382-3
eBook Packages: Computer ScienceComputer Science (R0)