Beet Seedling and Weed Recognition Based on Convolutional Neural Network and Multi-modality Images

Background: Difficulties in the recognition of beet seedlings and weeds can arise from a complex background in the natural environment and a lack of light at night. In the current study, a novel depth fusion algorithm was proposed based on visible and near-infrared imagery. Results: Visible (RGB) and near-infrared images were superimposed at the pixel-level via a depth fusion algorithm and were subsequently fused into three-channel multi-modality images in order to characterize the edge details of beets and weeds. Moreover, an improved region-based fully convolutional network (R-FCN) model was applied in order to overcome the geometric modeling restriction of traditional convolutional kernels. More specifically, for the convolutional feature extraction layers, deformable convolution was adopted to replace the traditional convolutional kernel, allowing for the entire network to extract more precise features. In addition, online hard example mining was introduced to excavate the hard negative samples in the detection process for the retraining of misidentified samples. A total of four models were established via the aforementioned improved methods. Results demonstrate that the average precision of the improved optimal model for beets and weeds were 84.8% and 93.2%, respectively, while the mean average precision was improved to 89.0%. Conclusion: Compared with the classical R-FCN model, the performance of the optimal model was not only greatly improved, but the parameters were also not significantly expanded. Our study can provide a theoretical basis for the subsequent development of intelligent weed control robots.

Performances of the LBP Based Algorithm over CNN Models for Detecting Crops and Weeds with Similar Morphologies

Weed invasions pose a threat to agricultural productivity. Weed recognition and detection play an important role in controlling weeds. The challenging problem of weed detection is how to discriminate between crops and weeds with a similar morphology under natural field conditions such as occlusion, varying lighting conditions, and different growth stages. In this paper, we evaluate a novel algorithm, filtered Local Binary Patterns with contour masks and coefficient k (k-FLBPCM), for discriminating between morphologically similar crops and weeds, which shows significant advantages, in both model size and accuracy, over state-of-the-art deep convolutional neural network (CNN) models such as VGG-16, VGG-19, ResNet-50 and InceptionV3. The experimental results on the “bccr-segset” dataset in the laboratory testbed setting show that the accuracy of CNN models with fine-tuned hyper-parameters is slightly higher than the k-FLBPCM method, while the accuracy of the k-FLBPCM algorithm is higher than the CNN models (except for VGG-16) for the more realistic “fieldtrip_can_weeds” dataset collected from real-world agricultural fields. However, the CNN models require a large amount of labelled samples for the training process. We conducted another experiment based on training with crop images at mature stages and testing at early stages. The k-FLBPCM method outperformed the state-of-the-art CNN models in recognizing small leaf shapes at early growth stages, with error rates an order of magnitude lower than CNN models for canola–radish (crop–weed) discrimination using a subset extracted from the “bccr-segset” dataset, and for the “mixed-plants” dataset. Moreover, the real-time weed–plant discrimination time attained with the k-FLBPCM algorithm is approximately 0.223 ms per image for the laboratory dataset and 0.346 ms per image for the field dataset, and this is an order of magnitude faster than that of CNN models.

Field Weed Recognition Based on an Improved VGG With Inception Module

The precision spraying of herbicides can significantly reduce herbicide use, and recognizing different field weeds is an important part of it. In order to enhance the efficiency and accuracy of field weed recognition, this article proposed a field weed recognition algorithm based on VGG model called VGG Inception (VGGI). In this article, three optimizations were made. First, the reduced number of convolution layers to reduce parameters of network. Then, the Inception structure was added, which can maintain the main features, and have better classification accuracy. Finally, data augmentation and transfer learning methods were used to prevent the problem of over-fitting, and further enhance the field weed recognition effect. The Kaggle Images dataset was used in the experiment. This work achieved greater than 98% precision in the detection of field weeds. In actual field, the accuracy could reach 80%. It indicated that the VGGI model has an outstanding identification performance for seedling, and has significant potential for actual field weed recognition.