Abstract
Advanced object detectors based on Convolutional Neural Networks (CNNs) offer high detection rates for many application scenarios but only within their respective training, validation and test data. Recent studies show that such methods provide a limited generalization ability for unknown data, even for small image modifications including a limited scale invariance. Reliable person detection with aerial robots (Unmanned Aerial Vehicles, UAVs) is an essential task to fulfill high security requirements or to support robot control, communication, and human-robot interaction. Particularly in an agricultural context, persons need to be detected from a long distance and a high altitude to allow the UAV an adequate and timely response. While UAVs are able to produce high resolution images that enable the detection of persons from a longer distance, typical CNN input layer sizes are comparably small. The inevitable scaling of images to match the input-layer size can lead to a further reduction in person sizes. We investigate the reliability of different YOLOv3 architectures for person detection in regard to those input-scaling effects. The popular VisDrone data set with its varying image resolutions and relatively small depiction of humans is used as well as high resolution UAV images from an agricultural data set. To overcome the scaling problem, an algorithm is presented for segmenting high resolution images in overlapping tiles that match the input-layer size. The number and overlap of the tiles are dynamically determined based on the image resolution. It is shown that the detection rate of very small persons in high resolution images can be improved using this tiling approach.
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
Redmon, J., Farhadi, A.: Yolov3: An incremental improvement. arXiv preprint arXiv:1804.02767 (2018)
Redmon, J.: Darknet framework for object detection. https://github.com/pjreddie/darknet. Accessed 23 Jul 2020
Bochkovskiy, A.: Improved darknet framework for object detection. https://github.com/AlexeyAB/darknet. Accessed 23 Jul 2020
Rosenfeld, A., Zemel, R.S., Tsotsos, J.K.: The elephant in the room. arXiv preprint arXiv:1808.03305 (2018)
Azulay, A., Weiss, Y.: Why do deep convolutional networks generalize so poorly to small image transformations? J. Mach. Learn. Res. 20(184), 1–25 (2019)
Pinckaers, H., Litjens, G.J.S.: Training convolutional neural networks with megapixel images. arXiv preprint arXiv:1804.05712 (2018)
Zhang, P., Zhong, Y., Li, X.: Slimyolov3: Narrower, faster and better for real-time UAV applications. In: The IEEE International Conference on Computer Vision (ICCV) Workshops (2019)
Steinmann, L., Sommer, L., Schumann, A., Beyerer, J.: Fast and lightweight person detector for unmanned aerial vehicles. In: EUSIPCO (2019)
Tayara, H., Chong, K.: Object detection in very high-resolution aerial images using one-stage densely connected feature pyramid network. Sensors 18(10), 3341 (2018)
Huang, Z., Wang, J.: DC-SPP-YOLO: dense connection and spatial pyramid pooling based YOLO for object detection. arXiv preprint arXiv:1903.08589 (2019)
Yang, F., Fan, H., Chu, P., Blasch, E., Ling, H.: Clustered object detection in aerial images. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 8311–8320 (2019)
Lu, Y., Javidi, T.: Efficient object detection for high resolution images. In: 2015 53rd Annual Allerton Conference on Communication, Control, and Computing (Allerton), pp. 1091–1098 (2015). https://doi.org/10.1109/ALLERTON.2015.7447130
Zhang, J., Huang, J., Chen, X., Zhang, D.: How to fully exploit the abilities of aerial image detectors. In: The IEEE International Conference on Computer Vision (ICCV) Workshops (2019)
Pang, J., Li, C., Shi, J., Xu, Z., Feng, H.: \(\cal{R}^2\) -CNN: Fast tiny object detection in large-scale remote sensing images. IEEE Trans. Geosci. Remote Sens. 57(8), 5512–5524 (2019). https://doi.org/10.1109/TGRS.2019.2899955
Růžička, V., Franchetti, F.: Fast and accurate object detection in high resolution 4k and 8k video using gpus. In: 2018 IEEE High Performance extreme Computing Conference (HPEC), pp. 1–7 (2018). https://doi.org/10.1109/HPEC.2018.8547574
Lin, T.-Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740–755. Springer, Cham (2014). https://doi.org/10.1007/978-3-319-10602-1_48
Zhu, P., Wen, L., Bian, X., Ling, H., Hu, Q.: Vision meets drones: A challenge. arXiv preprint arXiv:1804.07437 (2018)
Leipnitz, A.: Tile based object detection. http://www1.hft-leipzig.de/leipnitz/papers/TiledDetection-resources. Accessed 23 Jul 2020
Acknowledgements
The authors acknowledge the financial support by the Federal Ministry of Education and Research of Germany (BMBF) within the framework of the EU Era.Net RUS+ project HARMONIC (national project number 01DJ18011).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Leipnitz, A., Strutz, T., Jokisch, O. (2020). Spatial Resolution-Independent CNN-Based Person Detection in Agricultural Image Data. In: Ronzhin, A., Rigoll, G., Meshcheryakov, R. (eds) Interactive Collaborative Robotics. ICR 2020. Lecture Notes in Computer Science(), vol 12336. Springer, Cham. https://doi.org/10.1007/978-3-030-60337-3_19
Download citation
DOI: https://doi.org/10.1007/978-3-030-60337-3_19
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-60336-6
Online ISBN: 978-3-030-60337-3
eBook Packages: Computer ScienceComputer Science (R0)