3. Producción

Browse

Settings

Start date: 2022Subject: search.filters.subject.Semantic segmentation

Search Results

Now showing 1 - 3 of 3
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    SHREC 2022: Pothole and crack detection in the road pavement using images and RGB-D data
    (Elsevier Ltd, 2022-10-01)
    This paper describes the methods submitted for evaluation to the SHREC 2022 track on pothole and crack detection in the road pavement. A total of 7 different runs for the semantic segmentation of the road surface are compared, 6 from the participants plus a baseline method. All methods exploit Deep Learning techniques and their performance is tested using the same environment (i.e., a single Jupyter notebook). A training set, composed of 3836 semantic segmentation image/mask pairs and 797 RGB-D video clips collected with the latest depth cameras was made available to the participants. The methods are then evaluated on the 496 image/masks pairs in the validation set, on the 504 pairs in the test set and finally on 8 video clips. The analysis of the results is based on quantitative metrics for image segmentation and qualitative analysis of the video clips. The participation and the results show that the scenario is of great interest and that the use of RGB-D data is still challenging in this context.
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    Semantic Segmentation of Fish and Underwater Environments Using Deep Convolutional Neural Networks and Learned Active Contours
    (Institute of Electrical and Electronics Engineers Inc., 2023-01-01)
    The conservation of marine resources requires constant monitoring of the underwater environment by researchers. For this purpose, visual automated monitoring systems are of great interest, especially those that can describe the environment using semantic segmentation based on deep learning. Although they have been successfully used in several applications, such as biomedical ones, obtaining optimal results in underwater environments is still a challenge due to the heterogeneity of water and lighting conditions, and the scarcity of labeled datasets. Even more, the existing deep learning techniques oriented to semantic segmentation only provide low resolution results, lacking the enough spatial details for a high performance monitoring. To address these challenges, a combined loss function based on the active contour theory and level set methods is proposed to refine the spatial segmentation resolution and quality. To evaluate the method, a new underwater dataset with pixel annotations for three classes (fish, seafloor, and water) was created using images from publicly accessible datasets like SUIM, RockFish, and DeepFish. The performance of architectures of convolutional neural networks (CNNs), such as UNet and DeepLabV3+, trained with different loss functions (cross entropy, dice, and active contours) was compared, finding that the proposed combined loss function improved the segmentation results by around 3%, both in the metric Intercept Over Union (IoU) as in Hausdorff Distance (HD).
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    Automated Real-Time Estimation of Severity and Early Diagnosis of Infestations Produced by Tetranychus spp. in Strawberry Crops
    (Institute of Electrical and Electronics Engineers Inc., 2026-01-01)
    Tetranychusspp. is a prominent pest that affects strawberry cultivation, causing a significant decrease in economic yields. Manual inspection is the most common method used for identifying this pest, but it requires arduous labor, is slow, expensive, and inaccurate. This situation limits the ability to make an adequate early diagnosis of the damage caused by these spider mites. Thus, this paper presents a non-invasive method for real-time analysis of strawberry crops to determine the severity ofTetranychusspp. infestations. A field experiment was conducted to validate this systematic method through the biological characterization of spider mites, and a lightweight UNet-based convolutional neural network is proposed for the recognition of visual symptoms manifested on strawberry leaves containingTetranychusspp. This proposed model uses a Residual bottleneck block to reduce the number of layers and network complexity, and an atrous spatial pyramid pooling algorithm with a custom kernel that improves accuracy for this application. A total of 2273 images with a resolution of 512 × 512 pixels were collected from strawberry crops containing visible adaxial symptoms in complex backgrounds and were split into training (1772), validation (197), and test (304) datasets. The proposed model was evaluated alongside other state of the art semantic segmentation networks under the exact same training, validation, and testing conditions for a fair comparison. The results show that the proposed model achieves accuracy indicators comparable to the most recent semantic segmentation models, such as an IoU of 0.4791, but with twice the inference speed of the most accurate methods. Modifying the kernels for atrous convolutions demonstrated a substantial improvement in symptom recognition accuracy compared to standard atrous convolutions. Measurements of Lin's Concordance Correlation Coefficient evidence that our model produces accurate severity estimations for a proper understanding of the actual degree of infestation present in crops. These outcomes evidence the value of the proposed algorithm to detectTetranychusspp. in strawberry crop fields through real-time automated inspections.