Volumetric radiance fields have recently gained significant attention as promising representations of photorealistic scene reconstruction. However, the non-photorealistic rendering of such a representation has barely ...
详细信息
Volumetric radiance fields have recently gained significant attention as promising representations of photorealistic scene reconstruction. However, the non-photorealistic rendering of such a representation has barely been explored. In this study, we investigate the artistic posterization of the volumetric radiance fields. We extend the recent palette-based image-editing framework, which naturally introduces intuitive color manipulation of the posterized results, into the radiance field. Our major challenge is applying stylization effects coherently across different views. Based on the observation that computing a palette frame-by-frame can produce flickering, we propose pre-computing a single palette from the volumetric radiance field covering its entire visible color. We present a method based on volumetric visibility to sample visible colors from the radiance field while avoiding occluded and noisy regions. We demonstrate our workflow by applying it to pre-trained volumetric radiance fields with various stylization effects. We also show that our approach can produce more coherent and robust stylization effects than baseline methods that compute a palette on each rendered view.
This paper describes an automatic method that measures the orientation angle of sugarcane planting lines in relation to the vertical axis of an image using digital imageprocessing techniques. The methodology has thre...
详细信息
ISBN:
(纸本)9781665407618
This paper describes an automatic method that measures the orientation angle of sugarcane planting lines in relation to the vertical axis of an image using digital imageprocessing techniques. The methodology has three main steps: First, RGB images are converted to the Excess Green vegetation index. The image is then binarized based on the Otsu Method threshold and morphological operation. Then, different vertical projection vectors of the cut lines are generated with different orientation angles of the image. The orientation angle is detected where the maximum variation between black (ground) and white (cut lines) occurs, measured after applying the Savitzky-Golay filter. A full factorial experimental design was performed over 40 images taken from a drone and previously annotated. Results showed that the proposed methodology was able to detect the crop lines with a median absolute error of 0.9 degrees and interquartile range of just 1.5 degrees, without any outlier, even in the presence of images with almost no indication of orientation, and even faulty lines.
Many power line companies are using UAVs to perform their inspection processes instead of putting their workers at risk by making them climb high voltage power line towers, for instance. A crucial task for the inspect...
详细信息
ISBN:
(纸本)9781665423540
Many power line companies are using UAVs to perform their inspection processes instead of putting their workers at risk by making them climb high voltage power line towers, for instance. A crucial task for the inspection is to detect and classify assets in the power transmission lines. However, public data related to power line assets are scarce, preventing a faster evolution of this area. This work proposes the STN Power Line Assets Dataset, containing high-resolution and real-world images of multiple high-voltage power line components. It has 2,409 annotated objects divided into five classes: transmission tower, insulator, spacer, tower plate, and Stockbridge damper, which vary in size (resolution), orientation, illumination, angulation, and background. This work also presents an evaluation with popular deep object detection methods and MS-PAD, a new pipeline for detecting power line assets in hi-res UAV images. The latter outperforms the other methods achieving 89.2% mAP, showing considerable room for improvement.
computer vision methods for fire detection have made significant advancements compared to traditional fire detection systems. The incorporation of fire segmentation masks enables precise analysis, offering valuable in...
computer vision methods for fire detection have made significant advancements compared to traditional fire detection systems. The incorporation of fire segmentation masks enables precise analysis, offering valuable insights into the origin and spread of fires to prevent future incidents. This paper presents a novel approach that combines deep neural networks, graph cuts, and color thresholding to achieve fine-grained fire segmentation results. By incorporating graph cuts segmentation with global and local color information, our method enhances accuracy and detailed fire detection. As our results show, our method neatly improves recall, with a competitive precision, leading to an effective fire detection framework.
The revolutionary advances in image representation have led to impressive progress in many image understanding-related tasks, primarily supported by Convolutional Neural Networks (CNN) and, more recently, by Transform...
详细信息
ISBN:
(数字)9798350376036
ISBN:
(纸本)9798350376043
The revolutionary advances in image representation have led to impressive progress in many image understanding-related tasks, primarily supported by Convolutional Neural Networks (CNN) and, more recently, by Transformer models. Despite such advances, assessing the similarity among images for retrieval in unsupervised scenarios remains a challenging task, mostly grounded on traditional pairwise measures, such as the Euclidean distance. The scenario is even more challenging when different visual features are available, requiring the selection and fusion of features without any label information. In this paper, we propose an Unsupervised Dual-Layer Aggregation (UDLA) method, based on contextual similarity approaches for selecting and fusing CNN and Transformer-based visual features trained through transfer learning. In the first layer, the selected features are fused in pairs focused on precision. A sub-set of pairs is selected for a second layer aggregation focused on recall. An experimental evaluation conducted in different public datasets showed the effectiveness of the proposed approach, which achieved results significantly superior to the best-isolated feature and also superior to a recent fusion approach considered as baseline.
image retrieval approaches typically involve two fundamental stages: visual content representation and similarity measurement. Traditional methods rely on pairwise dissimilarity metrics, such as Euclidean distance, wh...
详细信息
ISBN:
(数字)9798350376036
ISBN:
(纸本)9798350376043
image retrieval approaches typically involve two fundamental stages: visual content representation and similarity measurement. Traditional methods rely on pairwise dissimilarity metrics, such as Euclidean distance, which overlook the global structure of datasets. Aiming to address this limitation, various unsupervised post-processing approaches have been developed to redefine similarity measures. Diffusion processes and rank-based methods compute a more effective similarity by considering the relationships among images and the overall dataset structure. However, neither approach is capable of defining novel image representations. This paper aims to overcome this limitation by proposing a novel self-supervised image re-ranking method. The proposed method exploits a hypergraph model, clustering strategies, and Graph Convolutional Networks (GCNs). Initially, an unsupervised rank-based manifold learning method computes global similarities to define small and reliable clusters, which are used as soft labels for training a semi-supervised GCN model. This GCN undergoes a two-stage training process: an initial classification-focused stage followed by a retrieval-focused stage. The final GCN embeddings are employed for retrieval tasks using the cosine similarity. An experimental evaluation conducted on four public datasets with three different visual features indicates that the proposed approach outperforms traditional and recent rank-based methods.
Facial expression synthesis has gained significant attention in the image synthesis field. Generative Adversarial Network (GAN) models have recently gained popularity due to the high-quality synthetic images they prod...
Facial expression synthesis has gained significant attention in the image synthesis field. Generative Adversarial Network (GAN) models have recently gained popularity due to the high-quality synthetic images they produce. However, these models require complex network architectures that can take days to train, even with high-performance graphicsprocessing Units (GPUs). Many efforts have been made to accelerate and compress such models, but little attention has been paid to the resolution of the images. This study aims to assess the impact of input/output spatial resolution on the resources needed for training a facial expression synthesis model, as well as on the quality of the results. Our results indicate that the produced images and videos had similar quality results measured through objective measures for the spatial resolution of 128 × 128, 256 × 256, and 480 × 480. Furthermore, we found that lower-resolution images could significantly reduce the time required to generate new facial expressions without compromising quality, as measured by objective measures.
Equipment health monitoring (EHM) techniques are increasing in their ability to accurately diagnose defective equipment. This increase in capability comes with an increase in computational complexity. For these techni...
详细信息
ISBN:
(数字)9798350385267
ISBN:
(纸本)9798350385274
Equipment health monitoring (EHM) techniques are increasing in their ability to accurately diagnose defective equipment. This increase in capability comes with an increase in computational complexity. For these techniques to be useful in real applications, the algorithms must be computable in real time. The Fast Orthogonal Search (FOS) algorithm shows the potential to be effective in a variety of EHM applications. In this paper, we demonstrate that the FOS algorithm can be accelerated to real-time processing on real examples of ship-radiated noise by using parallel processing, making it suitable for use in EHM.
暂无评论