Deep fruit detection in orchards
Open accessAbstract
An accurate and reliable image based fruit detection system is critical for supporting higher level agriculture tasks such as yield mapping and robotic harvesting. This paper presents the use of a state-of-the-art object detection framework, Faster R-CNN, in the context of fruit detection in orchards, including mangoes, almonds and apples. Ablation studies are presented to better understand the practical deployment of the detection network, including how much training data is required to capture variability in the dataset. Data augmentation techniques are shown to yield significant performance gains, resulting in a greater than two-fold reduction in the number of training images required. In contrast, transferring knowledge between orchards contributed to negligible performance gain over initialising the Deep Convolutional Neural Network directly from ImageNet features. Finally, to operate over orchard data containing between 100-1000 fruit per image, a tiling approach is introduced for the Faster R-CNN framework. The study has resulted in the best yet detection performance for these orchards relative to previous works, with an F1-score of > 0.9 achieved for apples and mangoes.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In real-world AIoT systems, there are always many related tasks involved, e.g., object detection and tracking, and semantic segmentation in video surveillance. Therefore, finding transfer learning dependencies across these tasks and leveraging such prior knowledge to learn better models are of practical value for AIoT [199], [200], [201], [202].
“In real-world AIoT systems, there are always many related tasks involved, e.g., object detection and tracking, and semantic segmentation in video surveillance. Therefore, finding the transfer learning dependencies across these tasks and leveraging such prior knowledge to learn better models, are of practical value for AIoT [199], [200], [201], [202].”
From Empowering things with intelligence: a survey of the progress, challenges, and opportunities in artificial intelligence of things (2021) · cites this paper as [201]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
Ren, S., He, K., Girshick, R., & Sun, J. (2015) · arXiv · doi:10.48550/arxiv.1506.01497 · Cited by 70,812 · see citing works
The pascal visual object classes (VOC) challenge
Everingham, M., Van Gool, L., Williams, C. K. I., Winn, J., & Zisserman, A. (2010) · International Journal of Computer Vision · doi:10.1007/s11263-009-0275-4 · Cited by 19,599 · see citing works
How transferable are features in deep neural networks?
Yosinski, J., Clune, J., Bengio, Y., & Lipson, H. (2014) · arXiv · doi:10.48550/arxiv.1411.1792 · Cited by 6,061 · see citing works
Selective Search for Object Recognition
Uijlings, J. R. R., van de Sande, K. E. A., Gevers, T., & Smeulders, A. W. M. (2013) · International Journal of Computer Vision · doi:10.1007/s11263-013-0620-5 · Cited by 5,980 · see citing works
R-FCN: Object Detection via Region-based Fully Convolutional NetworksPreprint
Dai, J., Li, Y., He, K., & Sun, J. Z. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1605.06409 · Cited by 5,135 · see citing works
Region-based convolutional networks for accurate object detection and segmentation
Girshick, R., Donahue, J., Darrell, T., & Malik, J. (2016) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2015.2437384 · Cited by 2,912 · see citing works
DeepFruits: A Fruit Detection System Using Deep Neural Networks
Sa, I., Ge, Z., Dayoub, F., Upcroft, B., Pérez, T., & McCool, C. (2016) · Sensors · doi:10.3390/s16081222 · Cited by 1,121 · see citing works
Is Faster R-CNN Doing Well for Pedestrian Detection?
Zhang, L., Lin, L., Liang, X., & He, K. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46475-6_28 · Cited by 852 · see citing works
What makes ImageNet good for transfer learning?Preprint
Huh, M., Agrawal, P., & Efros, A. A. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1608.08614 · Cited by 591 · see citing works
Image Based Mango Fruit Detection, Localisation and Yield Estimation Using Multiple View Geometry
Stein, M., Bargoti, S., & Underwood, J. (2016) · Sensors · doi:10.3390/s16111915 · Cited by 286 · see citing works
Self-citationAutomated Crop Yield Estimation for Apple Orchards
Wang, Q., Nuske, S. T., Bergerman, M., & Singh, S. (2013) · Springer tracts in advanced robotics · doi:10.1007/978-3-319-00065-7_50 · Cited by 233 · see citing works
Automated Visual Yield Estimation in Vineyards
Nuske, S. T., Wilshusen, K., Achar, S., Yoder, L., Narasimhan, S. G., & Singh, S. (2014) · Journal of Field Robotics · doi:10.1002/rob.21541 · Cited by 229 · see citing works
Computer vision for fruit harvesting robots – state of the art and challenges ahead
Kapach, K., Barnea, E., Mairon, R., Edan, Y., & Ben‐Shahar, O. (2012) · International Journal of Computational Vision and Robotics · doi:10.1504/ijcvr.2012.046419 · Cited by 222 · see citing works
Sengupta, S., & Lee, W. S. (2013) · Biosystems Engineering · doi:10.1016/j.biosystemseng.2013.07.007 · Cited by 182 · see citing works
Payne, A. B., Walsh, K. B., Subedi, P. P., et al. (2013) · Computers and Electronics in Agriculture · doi:10.1016/j.compag.2013.11.011 · Cited by 125 · see citing works
Orchard fruit segmentation using multi-spectral feature learning
Hung, C., Nieto, J. I., Taylor, Z., et al. (2013) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2013.6697125 · Cited by 97 · see citing works
A Feature Learning Based Approach for Automated Fruit Yield Estimation
Hung, C., Underwood, J., Nieto, J. I., et al. (2014) · Springer tracts in advanced robotics · doi:10.1007/978-3-319-07488-7_33 · Cited by 62 · see citing works
Self-citationEnd-to-End Instance Segmentation and Counting with Recurrent Attention.Preprint
Ren, M., & Zemel, R. S. (2016) · arXiv (Cornell University) · Cited by 50 · see citing works
Image classification with orchard metadata
Bargoti, S., & Underwood, J. (2016) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2016.7487721 · Cited by 18 · see citing works
Self-citationEnd-to-End Instance Segmentation with Recurrent AttentionPreprint
Ren, M., & Zemel, R. S. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1605.09410 · Cited by 11 · see citing works
Is Faster R-CNN Doing Well for Pedestrian Detection?Preprint
Zhang, L., Lin, L., Liang, X., et al. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1607.07032 · Cited by 7 · see citing works
Flagged first, then by citations
Research works printed but not linked: 2
- S. Bargoti and J. Underwood, "Image Segmentation for Fruit Detection and Yield Estimation in Apple Orchards," Journal of Field Robotics (accepted, under revision), 2016.
- A. Krizhevsky, I. Sutskever, and G. E. Hinton, "Imagenet classification with deep convolutional neural networks," in Advances in neural information processing systems, 2012, pp. 1097-1105.
Cited by
Sorted by citations
Zhang, J., & Tao, D. (2021) · IEEE Internet of Things Journal · doi:10.1109/jiot.2020.3039359 · Cited by 774 · see citing works
A detection algorithm for cherry fruits based on the improved YOLO-v4 model
Gai, R., Chen, N., & Yuan, H. (2023) · Neural Computing and Applications · doi:10.1007/s00521-021-06029-z · Cited by 388 · see citing works
Mazzia, V., Khaliq, A., Salvetti, F., & Chiaberge, M. (2020) · IEEE Access · doi:10.1109/access.2020.2964608 · Cited by 212 · see citing works
Gené-Mola, J., Vilaplana, V., Rosell-Polo, J. R., Morros, J.-R., Ruiz-Hidalgo, J., & Gregorio, E. (2019) · Computers and Electronics in Agriculture · doi:10.1016/j.compag.2019.05.016 · Cited by 169 · see citing works
Robust Fruit Counting: Combining Deep Learning, Tracking, and Structure from Motion
Liu, X., Chen, S. W., Aditya, S., Sivakumar, N., Dcunha, S., Qu, C., Taylor, C. J., Das, J., & Kumar, V. (2018) · 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2018.8594239 · Cited by 135 · see citing works
- Authors
- Bargoti, S., & Underwood, J.
- Affiliations
- The University of Sydney (AU)
- ORCID
- Underwood, James
- Venue
- 2017 IEEE International Conference on Robotics and Automation (ICRA)
- Publisher
- IEEE
- Published
- 2017-05
- Pages
- 3626-3633
- ISSN
- 1050-4729 (ISSN-L)
- OpenAlex
- W2537458488
- Cited by
- 607
- References
- 21
- Citations by year
- 2026: 42 · 2025: 53 · 2024: 64 · 2023: 80 · 2022: 81 · 2021: 94 · 2020: 96 · 2019: 62 · 2018: 32 · 2017: 3
- FWCI
- 154.97
- Type
- conference paper
- Language
- en
- Open access
- green
- arxiv.org
- Locations
- Proceedings - IEEE International Conference on Robotics and Automation/Proceedings (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Funders
- Australian Government
- University of Sydney
- Australian Centre for Field Robotics
- Department of Agriculture and Water Resources, Australian Government
- Topics
- Life Sciences › Agricultural and Biological Sciences › Plant Science › Smart Agriculture and AI
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Physical Sciences › Engineering › Industrial and Manufacturing Engineering › Industrial Vision Systems and Defect Detection
- Keywords
- fruit detection, orchards, Faster R-CNN, object detection, mango, almond, apple, data augmentation, transfer learning, tiling, training data requirements, robotic harvesting, yield mapping
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
