Abstract
With the continuous improvement of the intelligence level of facility agriculture, agricultural robots are undertaking more and more autonomous tasks in greenhouse environments, and the multifunctional integration of visual perception systems has become a key technological bottleneck. A perception system for agricultural robots that integrates visual navigation and phenotype recognition is developed to address issues such as path recognition being susceptible to environmental interference and poor real-time plant detection. The system consists of a path navigation module and a plant detection module. The former introduces an image segmentation method based on visual transformation structure to extract agricultural path information. The latter adopts a lightweight instance segmentation structure to achieve precise segmentation and structural localization of crop phenotype regions. In the navigation model test, in the rain and fog disturbance scene, the average delay is 51.0 ms, the frame rate is 44.2 FPS, and the control jitter amplitude is 1.36°. The test results of the detection module show that its boundary F1 values for Tomato, Cucumber, Pepper, and Lettuce crops are 90.2%, 87.6%, 88.8%, and 86.3%, respectively. The experimental results show that the proposed scheme reduces inference delay while ensuring accuracy, has good environmental adaptability and edge deployment potential, and demonstrates good robustness and practicality in complex greenhouse environments.
Abstract from the paper’s OpenAlex record; open copy licensed cc-by-nc-nd. Read at the source ↗
The text the model read, with the source record’s inline markup (italics, sub- and superscripts) rendered and its character entities decoded; quote offsets refer to the raw text.
Claims 8
Claim · model-written summary
The navigation model had 51.0 ms average delay in rain and fog.
Not reportedTaxon
Verbatim
e0“in the rain and fog disturbance scene, the average delay is 51.0 ms, the frame rate is 44.2 FPS, and the control jitter amplitude is 1.36°”
Claim · model-written summary
The navigation model reached 44.2 FPS in rain and fog.
Not reportedTaxon
Verbatim
e0“in the rain and fog disturbance scene, the average delay is 51.0 ms, the frame rate is 44.2 FPS, and the control jitter amplitude is 1.36°”
Claim · model-written summary
The navigation model had 1.36° control jitter in rain and fog.
Not reportedTaxon
Verbatim
e0“in the rain and fog disturbance scene, the average delay is 51.0 ms, the frame rate is 44.2 FPS, and the control jitter amplitude is 1.36°”
Claim · model-written summary
Tomato boundary F1 was 90.2%.
- Taxon
- Tomato
Solanum lycopersicume0 - Outcome
- boundary F1e0
- Value
- 90.2%e0
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
e0“boundary F1 values for Tomato, Cucumber, Pepper, and Lettuce crops are 90.2%, 87.6%, 88.8%, and 86.3%, respectively”
Claim · model-written summary
Cucumber boundary F1 was 87.6%.
- Taxon
- Cucumber
Cucumis sativuse0 - Outcome
- boundary F1e0
- Value
- 87.6%e0
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
e0“boundary F1 values for Tomato, Cucumber, Pepper, and Lettuce crops are 90.2%, 87.6%, 88.8%, and 86.3%, respectively”
Claim · model-written summary
Pepper boundary F1 was 88.8%.
Verbatim
e0“boundary F1 values for Tomato, Cucumber, Pepper, and Lettuce crops are 90.2%, 87.6%, 88.8%, and 86.3%, respectively”
Claim · model-written summary
Lettuce boundary F1 was 86.3%.
- Taxon
- Lettuce
Lactuca sativae0 - Outcome
- boundary F1e0
- Value
- 86.3%e0
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
e0“boundary F1 values for Tomato, Cucumber, Pepper, and Lettuce crops are 90.2%, 87.6%, 88.8%, and 86.3%, respectively”
Claim · model-written summary
The proposed scheme reduced inference delay while maintaining accuracy.
Not reportedComparator
Verbatim
e0“the proposed scheme reduces inference delay while ensuring accuracy”
t0“plant automatic detection”