Convolutional neural networks (CNNs) have achieved state-of-the-art performance in numerous aspects of human life and the agricultural sector is no exception. One of the main objectives of deep learning for smart farming is to identify the precise location of weeds and crops on farmland. In this paper, we propose a semantic segmentation method based on a cascaded encoder-decoder network, namely CED-Net, to differentiate weeds from crops. The existing architectures for weeds and crops segmentation are quite deep, with millions of parameters that require longer training time. To overcome such limitations, we propose an idea of training small networks in cascade to obtain coarse-to-fine predictions, which are then combined to produce the final results. Evaluation of the proposed network and comparison with other state-of-the-art networks are conducted using four publicly available datasets: rice seeding and weed dataset, BoniRob dataset, carrot crop vs. weed dataset, and a paddy–millet dataset. The experimental results and their comparisons proclaim that the proposed network outperforms state-of-the-art architectures, such as U-Net, SegNet, FCN-8s, and DeepLabv3, over intersection over union (IoU), F1-score, sensitivity, true detection rate, and average precision comparison metrics by utilizing only (1/5.74 × U-Net), (1/5.77 × SegNet), (1/3.04 × FCN-8s), and (1/3.24 × DeepLabv3) fractions of total parameters.

Autonomous harvesters can be used for the timely cultivation of high-value crops such as strawberries, where the robots have the capability to identify ripe and unripe crops. However, the real-time segmentation of strawberries in an unbridled farming environment is a challenging task due to fruit occlusion by multiple trusses, stems, and leaves. In this work, we propose a possible solution by constructing a dynamic feature selection mechanism for convolutional neural networks (CNN). The proposed building block namely a dense attention module (DAM) controls the flow of information between the convolutional encoder and decoder. DAM enables hierarchical adaptive feature fusion by exploiting both inter-channel and intra-channel relationships and can be easily integrated into any existing CNN to obtain category-specific feature maps. We validate our attention module through extensive ablation experiments. In addition, a dataset is collected from different strawberry farms and divided into four classes corresponding to different maturity levels of fruits and one is devoted to background. Quantitative analysis of the proposed method showed a 4.1% and 2.32% increase in mean intersection over union, over existing state-of-the-art semantic segmentation models and other attention modules respectively, while simultaneously retaining a processing speed of 53 frames per second.

Supervised semantic segmentation algorithms have been a hot area of exploration recently, but now the attention is being drawn towards completely unsupervised semantic segmentation. In an unsupervised framework, neither the targets nor the ground truth labels are provided to the network. That being said, the network is unaware about any class instance or object present in the given data sample. So, we propose a convolutional neural network (CNN) based architecture for unsupervised segmentation. We used the squeeze and excitation network, due to its peculiar ability to capture the features’ interdependencies, which increases the network’s sensitivity to more salient features. We iteratively enable our CNN architecture to learn the target generated by a graph-based segmentation method, while simultaneously preventing our network from falling into the pit of over-segmentation. Along with this CNN architecture, image enhancement and refinement techniques are exploited to improve the segmentation results. Our proposed algorithm produces improved segmented regions that meet the human level segmentation results. In addition, we evaluate our approach using different metrics to show the quantitative outperformance.

No abstract

Timely harvesting and disease identification of strawberry fruits is a major concern for commercial level cultivators. Failing to harvest the grown strawberries can result in the fruit rotting which makes their damaged tissues more prone to grey mold pathogens. Immediate removal of the overgrown or diseased strawberries is inevitable to curb the mass spreading of the pathogen. In this paper, we propose a deep learning-based framework to identify three different strawberry fruit classes (unripe, partially ripe and ripe), as well as a class of overgrown or diseased strawberries. We equip the proposed convolutional encoderdecoder network with three different modules. One for adaptively controlling receptive filed size of the network to detect objects of multiple sizes. Second for controlling the flow of salient features (information) to the deeper layers of the network and the other for controlling the architecture's computational complexity. These modules combined, outperform the previous state-of-the-art semantic segmentation networks on the task of strawberry fruit phenotyping. We also introduce a dataset collected from different farms to evaluate the performance of the network. Quantitative and qualitative results show that notwithstanding heterogeneity in the data and the effect of the real-field variations, our approach produced remarkable results with a 3% increase in mean intersection over union as compared to the other state-of-the-art networks and was able to recognize diseased fruits with a precision of 92.45%.

The emergence of deep neural networks has allowed the development of fully automated and efficient diagnostic systems for plant disease and pest phenotyping. Although previous approaches have proven to be promising, they are limited, especially in real-life scenarios, to properly diagnose and characterize the problem. In this work, we propose a framework which besides recognizing and localizing various plant abnormalities also informs the user about the severity of the diseases infecting the plant. By taking a single image as input, our algorithm is able to generate detailed descriptive phrases (user-defined) that display the location, severity stage, and visual attributes of all the abnormalities that are present in the image. Our framework is composed of three main components. One of them is a detector that accurately and efficiently recognizes and localizes the abnormalities in plants by extracting region-based anomaly features using a deep neural network-based feature extractor. The second one is an encoder–decoder network that performs pixel-level analysis to generate abnormality-specific severity levels. Lastly is an integration unit which aggregates the information of these units and assigns unique IDs to all the detected anomaly instances, thus generating descriptive sentences describing the location, severity, and class of anomalies infecting plants. We discuss two possible ways of utilizing the abovementioned units in a single framework. We evaluate and analyze the efficacy of both approaches on newly constructed diverse paprika disease and pest recognition datasets, comprising six anomaly categories along with 11 different severity levels. Our algorithm achieves mean average precision of 91.7% for the abnormality detection task and a mean panoptic quality score of 70.78% for severity level prediction. Our algorithm provides a practical and cost-efficient solution to farmers that facilitates proper handling of crops.

Fine segmentation labelling tasks are time consuming and typically require a great deal of manual labor. This paper presents a novel method for efficiently creating pixel-level fine segmentation labelling that significantly reduces the amount of necessary human labor. The proposed method utilizes easily produced multiple and complementary coarse labels to build a complete fine label via supervised learning. The primary label among the coarse labels is the manual label, which is produced with simple contours or bounding boxes that roughly encompass an object. All others coarse labels are complementary and are generated automatically using existing algorithms. Fine labels can be rapidly created during the supervised learning of such coarse labels. In the experimental study, the proposed technique achieved a fine label IOU (intersection of union) of 92% in segmenting our newly constructed bean field dataset. The proposed method also achieved 95% and 92% mean IOU when tested on publicly available agricultural CVPPP and CWFID datasets, respectively. Our proposed method of segmentation also achieved a mean IOU of 81% when it was tested on our newly constructed paprika disease dataset, which includes multiple categories.

No abstract