Reflection Symmetry Axes Localization Framework for Object Intelligent Perception based on Salient Symmetry Feature

This paper presents an optimized feature-centered reflection symmetry axis detection and localization framework for object perception. The proposed framework is formed to obtain an improved reflection symmetry axis based on the salient symmetry feature. It starts with a refined Multi-scale Saliency Symmetry Model (MSSM), which is realized by applying isotropic symmetry operator on salient points in scale-space rather than all pixels. In each scale, salient points are initially extracted as local extremal from an image, and they are further refined by a multi-scale implementation for generating salient symmetry feature maps. A Symmetric Transformation Matrix is then computed using the optimal feature matching pairs, which can be explicitly used as an abstract representation of the constraint regions of symmetry objects in an image to optimize the performance of the potential symmetry axis detection. The framework has been investigated experimentally both on the classical dataset from a symmetry detection challenge and the latest dataset. It has shown that the framework can get a better or comparative result and also can be further adapted into terminated human--computer equipment for reflection symmetry object perception and tracking.

Download Full-text

A Novel Detection Method of Paper Defects Based on Visual Attention Mechanism

International Journal of Advanced Pervasive and Ubiquitous Computing ◽

10.4018/japuc.2011070103 ◽

2011 ◽

Vol 3 (3) ◽

pp. 24-31 ◽

Cited By ~ 1

Author(s):

Ping Jiang ◽

Tao Gao

Keyword(s):

Visual Attention ◽

Detection Method ◽

Saliency Map ◽

Attention Mechanism ◽

Feature Maps ◽

Seed Point ◽

Multi Scale ◽

Comparative Maps ◽

Salient Points ◽

Visual Attention Mechanism

In this paper, an improved paper defects detection method based on visual attention mechanism computation model is presented. First, multi-scale feature maps are extracted by linear filtering. Second, the comparative maps are obtained by carrying out center-surround difference operator. Third, the saliency map is obtained by combining conspicuity maps, which is gained by combining the multi-scale comparative maps. Last, the seed point of watershed segmentation is determined by competition among salient points in the saliency map and the defect regions are segmented from the background. Experimental results show the efficiency of the approach for paper defects detection.

Download Full-text

A Novel Detection Method of Paper Defects Based on Visual Attention Mechanism

Global Applications of Pervasive and Ubiquitous Computing ◽

10.4018/978-1-4666-2645-4.ch018 ◽

2013 ◽

pp. 159-165 ◽

Cited By ~ 1

Author(s):

Ping Jiang ◽

Tao Gao

Keyword(s):

Visual Attention ◽

Detection Method ◽

Saliency Map ◽

Attention Mechanism ◽

Feature Maps ◽

Seed Point ◽

Multi Scale ◽

Comparative Maps ◽

Salient Points ◽

Visual Attention Mechanism

Download Full-text

U2-ONet: A Two-Level Nested Octave U-Structure Network with a Multi-Scale Attention Mechanism for Moving Object Segmentation

Remote Sensing ◽

10.3390/rs13010060 ◽

2020 ◽

Vol 13 (1) ◽

pp. 60

Author(s):

Chenjie Wang ◽

Chengyuan Li ◽

Jun Liu ◽

Bin Luo ◽

Xin Su ◽

...

Keyword(s):

Moving Objects ◽

Object Segmentation ◽

Contextual Information ◽

Attention Mechanism ◽

Moving Object ◽

Feature Maps ◽

Moving Object Segmentation ◽

Practical Applications ◽

Multi Scale ◽

Spatial Redundancy

Most scenes in practical applications are dynamic scenes containing moving objects, so accurately segmenting moving objects is crucial for many computer vision applications. In order to efficiently segment all the moving objects in the scene, regardless of whether the object has a predefined semantic label, we propose a two-level nested octave U-structure network with a multi-scale attention mechanism, called U2-ONet. U2-ONet takes two RGB frames, the optical flow between these frames, and the instance segmentation of the frames as inputs. Each stage of U2-ONet is filled with the newly designed octave residual U-block (ORSU block) to enhance the ability to obtain more contextual information at different scales while reducing the spatial redundancy of the feature maps. In order to efficiently train the multi-scale deep network, we introduce a hierarchical training supervision strategy that calculates the loss at each level while adding knowledge-matching loss to keep the optimization consistent. The experimental results show that the proposed U2-ONet method can achieve a state-of-the-art performance in several general moving object segmentation datasets.

Download Full-text

Hybrid Graph Neural Networks for Crowd Counting

Proceedings of the AAAI Conference on Artificial Intelligence ◽

10.1609/aaai.v34i07.6839 ◽

2020 ◽

Vol 34 (07) ◽

pp. 11693-11700 ◽

Cited By ~ 2

Author(s):

Ao Luo ◽

Fan Yang ◽

Xin Li ◽

Dong Nie ◽

Zhicheng Jiao ◽

...

Keyword(s):

Network Architecture ◽

Message Passing ◽

Large Scale ◽

State Of The Art ◽

Density Variation ◽

Feature Maps ◽

Crowd Counting ◽

Multi Scale ◽

Crowd Density ◽

Graph Neural Networks

Crowd counting is an important yet challenging task due to the large scale and density variation. Recent investigations have shown that distilling rich relations among multi-scale features and exploiting useful information from the auxiliary task, i.e., localization, are vital for this task. Nevertheless, how to comprehensively leverage these relations within a unified network architecture is still a challenging problem. In this paper, we present a novel network structure called Hybrid Graph Neural Network (HyGnn) which targets to relieve the problem by interweaving the multi-scale features for crowd density as well as its auxiliary task (localization) together and performing joint reasoning over a graph. Specifically, HyGnn integrates a hybrid graph to jointly represent the task-specific feature maps of different scales as nodes, and two types of relations as edges: (i) multi-scale relations capturing the feature dependencies across scales and (ii) mutual beneficial relations building bridges for the cooperation between counting and localization. Thus, through message passing, HyGnn can capture and distill richer relations between nodes to obtain more powerful representations, providing robust and accurate results. Our HyGnn performs significantly well on four challenging datasets: ShanghaiTech Part A, ShanghaiTech Part B, UCF_CC_50 and UCF_QNRF, outperforming the state-of-the-art algorithms by a large margin.

Download Full-text

Vessel enhancement using Multi-scale Space-Intensity domain Fusion Adaptive filtering

Biomedical Signal Processing and Control ◽

10.1016/j.bspc.2021.102799 ◽

2021 ◽

Vol 69 ◽

pp. 102799

Author(s):

Mingxu Huang ◽

Chaolu Feng ◽

Wei Li ◽

Dazhe Zhao

Keyword(s):

Adaptive Filtering ◽

Scale Space ◽

Multi Scale ◽

Domain Fusion ◽

Vessel Enhancement

Download Full-text

High-Resolution SAR Image Classification Using Multi-Scale Deep Feature Fusion and Covariance Pooling Manifold Network

Remote Sensing ◽

10.3390/rs13020328 ◽

2021 ◽

Vol 13 (2) ◽

pp. 328

Author(s):

Wenkai Liang ◽

Yan Wu ◽

Ming Li ◽

Yice Cao ◽

Xin Hu

Keyword(s):

High Resolution ◽

Image Classification ◽

Feature Fusion ◽

Representation Learning ◽

Sar Image ◽

Gabor Filtering ◽

Feature Maps ◽

Sar Images ◽

Multi Scale ◽

Deep Feature

The classification of high-resolution (HR) synthetic aperture radar (SAR) images is of great importance for SAR scene interpretation and application. However, the presence of intricate spatial structural patterns and complex statistical nature makes SAR image classification a challenging task, especially in the case of limited labeled SAR data. This paper proposes a novel HR SAR image classification method, using a multi-scale deep feature fusion network and covariance pooling manifold network (MFFN-CPMN). MFFN-CPMN combines the advantages of local spatial features and global statistical properties and considers the multi-feature information fusion of SAR images in representation learning. First, we propose a Gabor-filtering-based multi-scale feature fusion network (MFFN) to capture the spatial pattern and get the discriminative features of SAR images. The MFFN belongs to a deep convolutional neural network (CNN). To make full use of a large amount of unlabeled data, the weights of each layer of MFFN are optimized by unsupervised denoising dual-sparse encoder. Moreover, the feature fusion strategy in MFFN can effectively exploit the complementary information between different levels and different scales. Second, we utilize a covariance pooling manifold network to extract further the global second-order statistics of SAR images over the fusional feature maps. Finally, the obtained covariance descriptor is more distinct for various land covers. Experimental results on four HR SAR images demonstrate the effectiveness of the proposed method and achieve promising results over other related algorithms.

Download Full-text