Explicitly Incorporating Spatial Information to Recurrent Networks for Agriculture

Smitt, Claus; Halstead, Michael; Ahmadi, Alireza; McCool, Chris

doi:10.1109/lra.2022.3188105

Cited by 5 publications

(4 citation statements)

References 35 publications

(44 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In all of these approaches, researchers concentrated on single images; however, in agricultural robotics, there are platforms that scan the plants in a sequence. In an effort to use this temporal information, Smitt et al (2022) included the predicted movement of the platform (wheel odometry and depth images) into their segmentation network. They were able to improve segmentation scores considerably by using this technique.…”

Section: Prior Workmentioning

confidence: 99%

A cross-domain challenge with panoptic segmentation in agriculture

Halstead,

Zimmer,

McCool

2024

The International Journal of Robotics Research

Self Cite

View full text Add to dashboard Cite

Automation in agriculture is a growing area of research with fundamental societal importance as farmers are expected to produce more and better crop with fewer resources. A key enabling factor is robotic vision techniques allowing us to sense and then interact with the environment. A limiting factor for these robotic vision systems is their cross-domain performance, that is, their ability to operate in a large range of environments. In this paper, we propose the use of auxiliary tasks to enhance cross-domain performance without the need for extra data. We perform experiments using four datasets (two in a glasshouse and two in arable farmland) for four cross-domain evaluations. These experiments demonstrate the effectiveness of our auxiliary tasks to improve network generalisability. In glasshouse experiments, our approach improves the panoptic quality of things from 10.4 to 18.5 and in arable farmland from 16.0 to 27.5; where a score of 100 is the best. To further evaluate the generalisability of our approach, we perform an ablation study using the large Crop and Weed dataset (CAW) where we improve cross-domain performance (panoptic quality of things) from 12.8 to 30.6 for the CAW dataset to our novel WeedAI dataset, and 21.2 to 36.0 from CAW to the other arable farmland dataset. Although our proposed approaches considerably improve cross-domain performance we still do not generally outperform in-domain trained systems. This highlights the potential room for improvement in this area and the importance of cross-domain research for robotic vision systems.

show abstract

Section: Prior Workmentioning

confidence: 99%

A cross-domain challenge with panoptic segmentation in agriculture

Halstead,

Zimmer,

McCool

2024

The International Journal of Robotics Research

Self Cite

View full text Add to dashboard Cite

show abstract

“…For all experiments we use two datasets that we refer to as SB20 [2], [25], [10] (sugar beet 2020) and CN20 [1] (corn 2020). Both datasets contain instance-level manually annotated data for both training and inference and contain varying weed species, sizes, and densities (see Figure 4).…”

Section: A Datasetsmentioning

confidence: 99%

“…We train from scratch for 1500 epochs, which we empirically found was the convergence point. To tackle class imbalances in our datasets, we use a class weighted cross entropy loss similarly to [23], [25], that gives a higher loss to classes with fewer samples. We determine class weights w c as,…”

Section: Implementation and Metricsmentioning

confidence: 99%

Panoptic One-Click Segmentation: Applied to Agricultural Data

Zimmer

Halstead

McCool

2023

IEEE Robot. Autom. Lett.

Self Cite

View full text Add to dashboard Cite

In weed control, precision agriculture can help to greatly reduce the use of herbicides, resulting in both economical and ecological benefits. A key element here is the ability to locate and segment all the plants (crop & weed) from image data. Modern instance segmentation techniques can achieve this, however, training such systems requires large amounts of handlabelled data which is expensive and laborious to obtain. Weakly supervised training can help to greatly reduce labelling efforts and costs.In this paper we propose panoptic one-click segmentation, an efficient and accurate offline tool to produce pseudo-labels from click inputs and thereby reduce labelling effort when creating novel datasets. Our approach jointly estimates the pixel-wise location of all N objects in the scene, compared to traditional approaches which iterate independently through all N objects. This results in a highly efficient technique with greatly reduced training times. Using just 10% of the data to train our panoptic one-click segmentation approach yields 68.1% and 68.8% mean object intersection over union (IoU) on challenging sugar beet and corn image data respectively, providing comparable performance to traditional one-click approaches while being approximately 12 times (an order of magnitude) faster to train. We demonstrate the practical applicability of our system by generating pseudo-labels from click annotations for the remaining 90% of the data. These pseudo-labels are then used to train Mask R-CNN, in a semisupervised manner, improving the absolute performance (of mean foreground IoU) by 9.4 and 7.9 points for sugar beet and corn data respectively, demonstrating the potential of our approach to rapidly annotate challenging data. Finally, we show that our panoptic one-click segmentation technique is able to recover missed clicks during annotation outlining a further benefit over traditional approaches.

show abstract

“…Clearly, these approaches rely on the underlying perception or agricultural monitoring approaches which have gained significant research attention in recent years, including in glasshouses [14], [15], orchards [16], and fields (for weed intervention) [17].…”

Section: Related Workmentioning

confidence: 99%

BonnBot-I: A Precise Weed Management and Crop Monitoring Platform

Ahmadi

Halstead

McCool

2022

2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

Self Cite

View full text Add to dashboard Cite

Cultivation and weeding are two of the primary tasks performed by farmers today. A recent challenge for weeding is the desire to reduce herbicide and pesticide treatments while maintaining crop quality and quantity. In this paper we introduce BonnBot-I a precise weed management platform which can also performs field monitoring. Driven by crop monitoring approaches which can accurately locate and classify plants (weed and crop) we further improve their performance by fusing the platform available GNSS and wheel odometry. This improves tracking accuracy of our crop monitoring approach from a normalized average error of 8.3% to 3.5%, evaluated on a new publicly available corn dataset. We also present a novel arrangement of weeding tools mounted on linear actuators evaluated in simulated environments. We replicate weed distributions from a real field, using the results from our monitoring approach, and show the validity of our work-space division techniques which require significantly less movement (a 50% reduction) to achieve similar results. Overall, BonnBot-I is a significant step forward in precise weed management with a novel method of selectively spraying and controlling weeds in an arable field.

show abstract

Explicitly Incorporating Spatial Information to Recurrent Networks for Agriculture

Cited by 5 publications

References 35 publications

A cross-domain challenge with panoptic segmentation in agriculture

A cross-domain challenge with panoptic segmentation in agriculture

Panoptic One-Click Segmentation: Applied to Agricultural Data

BonnBot-I: A Precise Weed Management and Crop Monitoring Platform

Contact Info

Product

Resources

About