When searching for a dynamic target in an unknown real world scene,search efficiency is greatly reduced if users lack information about the spatial structure of the *** target search studies,especially in robotics,foc...
详细信息
When searching for a dynamic target in an unknown real world scene,search efficiency is greatly reduced if users lack information about the spatial structure of the *** target search studies,especially in robotics,focus on determining either the shortest path when the target’s position is known,or a strategy to find the target as quickly as possible when the target’s position is ***,the target’s position is often known intermittently in the real world,e.g.,in the case of using surveillance *** goal is to help user find a dynamic target efficiently in the real world when the target’s position is intermittently *** order to achieve this purpose,we have designed an AR guidance assistance system to provide optimal current directional guidance to users,based on searching a prediction *** assume that a certain number of depth cameras are fixed in a real scene to obtain dynamic target’s *** system automatically analyzes all possible meetings between the user and the target,and generates optimal directional guidance to help the user catch up with the target.A user study was used to evaluate our method,and its results showed that compared to free search and a top-view method,our method significantly improves target search efficiency.
Background Three-dimensional(3D)shape representation using mesh data is essential in various applications,such as virtual reality and simulation *** methods for extracting features from mesh edges or faces struggle wi...
详细信息
Background Three-dimensional(3D)shape representation using mesh data is essential in various applications,such as virtual reality and simulation *** methods for extracting features from mesh edges or faces struggle with complex 3D models because edge-based approaches miss global contexts and face-based methods overlook variations in adjacent areas,which affects the overall *** address these issues,we propose the Feature Discrimination and Context Propagation Network(FDCPNet),which is a novel approach that synergistically integrates local and global features in mesh *** FDCPNet is composed of two modules:(1)the Feature Discrimination Module,which employs an attention mechanism to enhance the identification of key local features,and(2)the Context Propagation Module,which enriches key local features by integrating global contextual information,thereby facilitating a more detailed and comprehensive representation of crucial areas within the mesh *** Experiments on popular datasets validated the effectiveness of FDCPNet,showing an improvement in the classification accuracy over the baseline ***,even with reduced mesh face numbers and limited training data,FDCPNet achieved promising results,demonstrating its robustness in scenarios of variable complexity.
Fine-grained visual parsing, including fine-grained part segmentation and fine-grained object recognition, has attracted considerable critical attention due to its importance in many real-world applications, e.g., agr...
详细信息
Fine-grained visual parsing, including fine-grained part segmentation and fine-grained object recognition, has attracted considerable critical attention due to its importance in many real-world applications, e.g., agriculture, remote sensing, and space technologies. Predominant research efforts tackle these fine-grained sub-tasks following different paradigms, while the inherent relations between these tasks are neglected. Moreover, given most of the research remains fragmented, we conduct an in-depth study of the advanced work from a new perspective of learning the part relationship. In this perspective, we first consolidate recent research and benchmark syntheses with new taxonomies. Based on this consolidation, we revisit the universal challenges in fine-grained part segmentation and recognition tasks and propose new solutions by part relationship learning for these important challenges. Furthermore, we conclude several promising lines of research in fine-grained visual parsing for future research.
Medical image segmentation has an important application value in the modern medical field, it can help doctors accurately locate and analyze the tissue structure, lesion areas, and organ boundaries in the image, which...
详细信息
Visual localization and object detection both play important roles in various *** many indoor application scenarios where some detected objects have fixed positions,the two techniques work closely ***,few researchers ...
详细信息
Visual localization and object detection both play important roles in various *** many indoor application scenarios where some detected objects have fixed positions,the two techniques work closely ***,few researchers consider these two tasks simultaneously,because of a lack of datasets and the little attention paid to such *** this paper,we explore multi-task network design and joint refinement of detection and *** address the dataset problem,we construct a medium indoor scene of an aviation exhibition hall through a semi-automatic *** dataset provides localization and detection information,and is publicly available at https://***/drive/folders/1U28zk0N4_I0db zkqyIAK1A15k9oUKOjI?usp=sharing for benchmarking localization and object detection *** this dataset,we have designed a multi-task network,JLDNet,based on YOLO v3,that outputs a target point cloud and object bounding *** dynamic environments,the detection branch also promotes the perception of *** includes image feature learning,point feature learning,feature fusion,detection construction,and point cloud ***,object-level bundle adjustment is used to further improve localization and detection *** test JLDNet and compare it to other methods,we have conducted experiments on 7 static scenes,our constructed dataset,and the dynamic TUM RGB-D and Bonn *** results show state-of-the-art accuracy for both tasks,and the benefit of jointly working on both tasks is demonstrated.
We introduce an improved position-based dynamics method with corrected smoothed particle hydrodynamics(SPH) kernel to simulate deformable solids. Using a strain energy constraint that follows the continuum mechanics, ...
详细信息
We introduce an improved position-based dynamics method with corrected smoothed particle hydrodynamics(SPH) kernel to simulate deformable solids. Using a strain energy constraint that follows the continuum mechanics, the method can maintain the efficiency and stability of the position-based approach while improving the physical plausibility of the simulation. We can easily simulate the behavior of anisotropic and plastic materials because the method is based on physics. Unlike the previous position-based simulations of continuous materials, we use weakly structured particles to discretize the model for the convenience of deformable object cutting. In this case, a corrected SPH kernel function is adopted to measure the deformation gradient and calculate the strain energy on each particle. We also propose a solution for the interparticle inversion and penetration in large deformation. To perform complex interaction scenarios, we provide a simple method for collision detection. We demonstrate the flexibility, efficiency, and robustness of the proposed method by simulating various scenes, including anisotropic elastic deformation, plastic deformation, model cutting, and large-scale elastic collision.
Depth information can benefit various computer vision tasks on both images and ***,depth maps may suffer from invalid values in many pixels,and also large *** improve such data,we propose a joint self-supervised and r...
详细信息
Depth information can benefit various computer vision tasks on both images and ***,depth maps may suffer from invalid values in many pixels,and also large *** improve such data,we propose a joint self-supervised and reference-guided learning approach for depth *** the self-supervised learning strategy,we introduce an improved spatial convolutional sparse coding module in which total variation regularization is employed to enhance the structural information while preserving edge *** module alternately learns a convolutional dictionary and sparse coding from a corrupted depth ***,both the learned convolutional dictionary and sparse coding are convolved to yield an initial depth map,which is effectively smoothed using local contextual *** reference-guided learning part is inspired by the fact that adjacent pixels with close colors in the RGB image tend to have similar depth *** thus construct a hierarchical joint bilateral filter module using the corresponding color image to fill in large *** summary,our approach integrates a convolutional sparse coding module to preserve local contextual information and a hierarchical joint bilateral filter module for filling using specific adjacent *** results show that the proposed approach works well for both invalid value restoration and large hole inpainting.
Recently,a new research trend in our video salient object detection(VSOD)research community has focused on enhancing the detection results via model self-fine-tuning using sparsely mined high-quality keyframes from th...
详细信息
Recently,a new research trend in our video salient object detection(VSOD)research community has focused on enhancing the detection results via model self-fine-tuning using sparsely mined high-quality keyframes from the given *** such a learning scheme is generally effective,it has a critical limitation,i.e.,the model learned on sparse frames only possesses weak generalization *** situation could become worse on“long”videos since they tend to have intensive scene ***,in such videos,the keyframe information from a longer time span is less relevant to the previous,which could also cause learning conflict and deteriorate the model ***,the learning scheme is usually incapable of handling complex pattern *** solve this problem,we propose a divide-and-conquer framework,which can convert a complex problem domain into multiple simple ***,we devise a novel background consistency analysis(BCA)which effectively divides the mined frames into disjoint *** for each group,we assign an individual deep model on it to capture its key attribute during the fine-tuning *** the testing phase,we design a model-matching strategy,which could dynamically select the best-matched model from those fine-tuned ones to handle the given testing *** experiments show that our method can adapt severe background appearance variation coupling with object movement and obtain robust saliency detection compared with the previous scheme and the state-of-the-art methods.
Intrinsic image decomposition is an important and long-standing computer vision *** an input image,recovering the physical scene properties is *** physically motivated priors have been used to restrict the solution sp...
详细信息
Intrinsic image decomposition is an important and long-standing computer vision *** an input image,recovering the physical scene properties is *** physically motivated priors have been used to restrict the solution space of the optimization problem for intrinsic image *** work takes advantage of deep learning,and shows that it can solve this challenging computer vision problem with high *** focus lies in the feature encoding phase to extract discriminative features for different intrinsic layers from an input *** achieve this goal,we explore the distinctive characteristics of different intrinsic components in the high-dimensional feature embedding *** define feature distribution divergence to efficiently separate the feature vectors of different intrinsic *** feature distributions are also constrained to fit the real ones through a feature distribution *** addition,a data refinement approach is provided to remove data inconsistency from the Sintel dataset,making it more suitable for intrinsic image *** method is also extended to intrinsic video decomposition based on pixel-wise correspondences between adjacent *** results indicate that our proposed network structure can outperform the existing state-of-the-art.
Compared to 2D imaging data,the 4D light field(LF)data retains richer scene’s structure information,which can significantly improve the computer’s perception capability,including depth estimation,semantic segmentati...
详细信息
Compared to 2D imaging data,the 4D light field(LF)data retains richer scene’s structure information,which can significantly improve the computer’s perception capability,including depth estimation,semantic segmentation,and LF ***,there is a contradiction between spatial and angular resolution during the LF image acquisition *** overcome the above problem,researchers have gradually focused on the light field super-resolution(LFSR).In the traditional solutions,researchers achieved the LFSR based on various optimization frameworks,such as Bayesian and Gaussian *** learning-based methods are more popular than conventional methods because they have better performance and more robust generalization *** this paper,the present approach can mainly divided into conventional methods and deep learning-based *** discuss these two branches in light field spatial super-resolution(LFSSR),light field angular super-resolution(LFASR),and light field spatial and angular super-resolution(LFSASR),***,this paper also introduces the primary public datasets and analyzes the performance of the prevalent approaches on these ***,we discuss the potential innovations of the LFSR to propose the progress of our research field.
暂无评论