Monitoring and managing maize seedlings post-planting is essential for ensuring yield and quality. Unmanned aerial vehicle (UAV) remote sensing technology has been widely integrated for non-destructive detection of ma...
详细信息
Monitoring and managing maize seedlings post-planting is essential for ensuring yield and quality. Unmanned aerial vehicle (UAV) remote sensing technology has been widely integrated for non-destructive detection of maize seedlings. However, significant challenges remain in maize seedling monitoring, such as relatively late monitoring periods, high data annotation costs, and lack of geolocation feedback for missing seedlings. To tackle these issues, this study focused on maize seedlings up to and including the second vegetative leaf (V2) stage. Firstly, the detection performance of both seedlings and missing seedlings was evaluated using a fully labeled dataset, achieving a mean precision of 92.06 %, recall of 87.44 %, and AP50 of 91.23 %. Then, the role of unlabeled data in enhancing the effectiveness of objectdetection was studied based on the efficient teacher semi-supervised learning framework. Significant improvements were observed when the labeled to unlabeled data ratio ranged from 1:2 to 1:12. The best results for mean precision, recall, and AP50 were improved by 2.69 %, 2.65 %, and 2.35 %, respectively. Additionally, an end-to-end pipeline was developed from image collection to seedling condition analysis, which effectively enhanced the detection of missing seedlings and accurately mapped them to geographical coordinates with an average deviation of 0.462m. This pipeline bridges the gap between missing seedling detection and replanting feedback, providing a feasible and precise detection solution for maize seedlings and supporting efficient field production management.
Recently, semi-supervised learning methods are being actively developed to increase the performance of neural networks by using large amounts of unlabeled data. Among these techniques, pseudo-labeling methods have the...
详细信息
In-vitro tests are an alternative to animal testing for the toxicity of medical devices. Detecting cells as a first step, a cell expert evaluates the growth of cells according to cytotoxicity grade under the microscop...
详细信息
ISBN:
(数字)9783031168529
ISBN:
(纸本)9783031168529;9783031168512
In-vitro tests are an alternative to animal testing for the toxicity of medical devices. Detecting cells as a first step, a cell expert evaluates the growth of cells according to cytotoxicity grade under the microscope. Thus, human fatigue plays a role in error making, making the use of deep learning appealing. Due to the high cost of training data annotation, an approach without manual annotation is needed. We propose Seamless Iterative semi-supervised correction of Imperfect labels (SISSI), a new method for training objectdetection models with noisy and missing annotations in a semi-supervised fashion. Our network learns from noisy labels generated with simple image processing algorithms, which are iteratively corrected during self-training. Due to the nature of missing bounding boxes in the pseudo labels, which would negatively affect the training, we propose to train on dynamically generated syntheticlike images using seamless cloning. Our method successfully provides an adaptive early learning correction technique for objectdetection. The combination of early learning correction that has been applied in classification and semantic segmentation before and synthetic-like image generation proves to be more effective than the usual semi-supervised approach by >15% AP and >20% AR across three different readers. Our code is available at https://***/marwankefah/SISSI.
Detecting sparse, small, lost persons with only a few pixels in high-resolution aerial images was, is, and remains an important and difficult mission, in which a vital role is played by accurate monitoring and intelli...
详细信息
Detecting sparse, small, lost persons with only a few pixels in high-resolution aerial images was, is, and remains an important and difficult mission, in which a vital role is played by accurate monitoring and intelligent co-rescuing for the search and rescue (SaR) system. However, many problems have not been effectively solved in existing remote-vision-based SaR systems, such as the shortage of person samples in SaR scenarios and the low tolerance of small objects for bounding boxes. To address these issues, a copy-paste mechanism (ISCP) with semi-supervised object detection (SSOD) via instance segmentation and maximum mean discrepancy distance is proposed (MMD), which can provide highly robust, multi-task, and efficient aerial-based person detection for the prototype SaR system. Specifically, numerous pseudo-labels are obtained by accurately segmenting the instances of synthetic ISCP samples to obtain their boundaries. The SSOD trainer then uses soft weights to balance the prediction entropy of the loss function between the ground truth and unreliable labels. Moreover, a novel evaluation metric MMD for anchor-based detectors is proposed to elegantly compute the IoU of the bounding boxes. Extensive experiments and ablation studies on Heridal and optimized public datasets demonstrate that our approach is effective and achieves state-of-the-art person detection performance in aerial images.
暂无评论