Abstract
Crop recognition is one of the key processes for robotic weeding in precision agriculture, which remains an open problem due to the unstructured field environment and the wide variety of plant species. It becomes especially challenging when the weeds are prominent and overlap with the crop plants. This paper presents a novel method for recognizing crop plants of field images with a high weed presence. This method segments crop plants from overlapped weeds based on the visual attention mechanism of the human visual system using a convolutional neural network. The network utilizes ResNet-10 as backbone, while introducing side outputs and short connections for multi-scale feature fusion. The Adaptive Affinity Fields method is adopted to improve the segmentation at object boundaries and for fine structures. To train and test the network, a field image dataset has been created which consists of 788 color images with manually segmented annotations. The images are captured under challenging conditions with extremely high weed pressure. The experimental results show that the proposed method can accurately segment crops from weeds and soil, with mean absolute errors less than 0.005 and F-measure scores exceeding 97%. In terms of efficiency, the proposed method can process up to 169 images per second when accelerated by a NVIDIA RTX 2080Ti graphics processing unit (GPU), and operate at approximately 5.6 Hz in a Jetson TX2 embedded computer. The results indicate that the proposed method has the potential to provide an efficient solution for recognizing crop plants, even in the presence of severe weed growth. The code and the dataset are available at https://github.com/ZhangXG001/Real-Time-Crop-Recognition .
Highlights
Weed control plays an important role in agricultural production since uncontrolled weeds can have significant effects on crop yield and quality
Since the model is trained on a general dataset without field images, the results demonstrate that the crop plants present saliency in field images and can be detected by a general salient object detection model
The results show that both Conditional Random Field (CRF) and Adaptive Affinity Fields (AAF) bring significant improvements to the performances of the models in terms of the mean absolute error (MAE) and F-measure scores
Summary
Weed control plays an important role in agricultural production since uncontrolled weeds can have significant effects on crop yield and quality. Environmental and commercial pressures are pushing growers away from a reliance on the uniform spaying of herbicides. The associate editor coordinating the review of this manuscript and approving it for publication was Feng Lin. regarded as a viable alternative to reduce the environmental loading of agrochemicals by performing precise mechanical weeding [1] or targeted herbicide spraying [2]. One of the key processes for robotic weeding is the fast and accurate localization of crop plants or weeds. When conducting the crop recognition by means of computer vision, one of the main challenges comes from weed infestations, since weeds and crops have much in common in terms of appearance.
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
