Image segmentation is a chief and basic issue in the field of image analysis as well as patternrecognition. Meanwhile, it is also the classical puzzle in image processing. And the watershed transform is a powerful mo...
详细信息
Image segmentation is a chief and basic issue in the field of image analysis as well as patternrecognition. Meanwhile, it is also the classical puzzle in image processing. And the watershed transform is a powerful morphological tool for image segmentation. But its short-coming is to cause over-segmentation. Therefore, labeling watershed algorithm has been presented in this paper. Firstly, a bilateral filtering is applied to smooth the original image, so it can reduce part of noise. Secondly, according to the characteristics of the ore image the distance transform and morphological reconstruction are used to realize labeling watershed transformation on this basis. Finally, segmentation result is obtained by using an improved method of labeling watershed algorithm. The experimental result shows that the method can reduce over-segmentation more efficiently, with a precision of more than 80%.
During tracking process in optical flow, some points are normally easy to be lost or become outliers, due to the fact that the object undergoes changes of illumination or becomes partially occluded. The paper presents...
详细信息
ISBN:
(纸本)9781457716218
During tracking process in optical flow, some points are normally easy to be lost or become outliers, due to the fact that the object undergoes changes of illumination or becomes partially occluded. The paper presents a novel scheme, Heterogeneity Elimination Individually (HEI), for outlier rejections from the tracking results of optical flow. HEI determines the most poisonous element by the distance between the tracked point and the projected point which is determined by its complements set from the source to the target one. Then HEI eliminates the farthest point every time from the element heterogeneous sequence until all remaining points are within the error tolerance and ensures the accuracy of the optical flow tracking results. Finally, we make an experiment by comparing our method with a popularly used method, RANSAC. The comparison results show the validity and effectiveness of our proposed method for outlier rejection.
Identification of motion patterns in video is an important problem because it is the first step towards analysis of complex multi-person behaviors to obtain long-term interaction models. In this paper, we will present...
详细信息
Identification of motion patterns in video is an important problem because it is the first step towards analysis of complex multi-person behaviors to obtain long-term interaction models. In this paper, we will present a flow based technique to identify spatio-temporal motion patterns in a multi-object video. We use the Helmholtz decomposition of optical flow and compute singular points corresponding to component fields. We will show that the optical flow can be used to identify regions which correspond to different moving entities in the video. The singular points in these regions capture the characteristics of the field around them and can be used to identify these regions. This representation would provide us with a framework to analyze activities of individual entities in the scene as well as the global interactions between them. We demonstrate our algorithm on a dataset composed of multi-object videos recorded in a realistic environment.
In the conventional bag of visual words (BoW) based image representation, single visual word is not discriminative enough and the spatial contextual information among local image features is ignored. In this paper, de...
详细信息
In the conventional bag of visual words (BoW) based image representation, single visual word is not discriminative enough and the spatial contextual information among local image features is ignored. In this paper, descriptive local feature groups are proposed to address these two problems. First, local image features are refined by slightly transforming the original image. Then they are clustered and represented by visual words. Second, the candidate local feature groups are generated by searching the neighbors of every local image features. This kind of grouping shows more discriminative power than a single feature and the local spatial contexts can be catched. Third, we obtain the groups more descriptive to the object category by defining a significance score and the groups with high score are selected. Finally, the high order descriptive local feature groups are integrated to the vector based object categorization framework by a feature reweighting strategy. Experimental results on Scene-15 and Caltech 101 demonstrate the superior performance of our method.
We present a method for spotting a subgraph in a graph repository. Subgraph spotting is a very interesting research problem for various application domains where the use of a relational data structure is mandatory. Ou...
详细信息
ISBN:
(纸本)9781457713507
We present a method for spotting a subgraph in a graph repository. Subgraph spotting is a very interesting research problem for various application domains where the use of a relational data structure is mandatory. Our proposed method accomplishes subgraph spotting through graph embedding. We achieve automatic indexation of a graph repository during off-line learning phase, where we (i) break the graphs into 2-node sub graphs (a.k.a. cliques of order 2), which are primitive building-blocks of a graph, (ii) embed the 2-node sub graphs into feature vectors by employing our recently proposed explicit graph embedding technique, (iii) cluster the feature vectors in classes by employing a classic agglomerative clustering technique, (iv) build an index for the graph repository and (v) learn a Bayesian network classifier. The subgraph spotting is achieved during the on-line querying phase, where we (i) break the query graph into 2-node sub graphs, (ii) embed them into feature vectors, (iii) employ the Bayesian network classifier for classifying the query 2-node sub graphs and (iv) retrieve the respective graphs by looking-up in the index of the graph repository. The graphs containing all query 2-node sub graphs form the set of result graphs for the query. Finally, we employ the adjacency matrix of each result graph along with a score function, for spotting the query graph in it. The proposed subgraph spotting method is equally applicable to a wide range of domains, offering ease of query by example (QBE) and granularity of focused retrieval. Experimental results are presented for graphs generated from two repositories of electronic and architectural document images.
The re-identification of individuals aims to retrieve persons across multiple non-overlapping cameras. With the advancement of deep learning features and the increase in the number of surveillance videos, the computer...
详细信息
The re-identification of individuals aims to retrieve persons across multiple non-overlapping cameras. With the advancement of deep learning features and the increase in the number of surveillance videos, the computervision community has experienced significant progress. However, person re-identification is still faced with various challenges such as low resolution images and pose variations. To overcome these challenges, state-of-the-art algorithms for person re-identification are supported by convolutional neural networks. This paper proposes the use of a Siamese network, which is a neural architecture that takes a pair of images or videos as input and predicts the similarity or dissimilarity of a person across two cameras. The output includes the prediction of similar and dissimilar persons along with their prediction scores. The proposed method was evaluated using iLIDS-VID and PRID 2011 datasets, and achieved recognition accuracy of 79.52% and 85.82%, respectively. These results demonstrate the effectiveness of the Siamese network for person re-identification tasks. Overall, this study contributes to the ongoing research on improving the accuracy of person re-identification across multiple cameras in surveillance videos.
Image denoising is an important pre-processing step for many image analysis and computervision system. It refers to the task of recovering a good estimate of the true image from a degraded observation without alterin...
详细信息
Image denoising is an important pre-processing step for many image analysis and computervision system. It refers to the task of recovering a good estimate of the true image from a degraded observation without altering and changing useful structure in the image such as discontinuities and edges. In this paper, we propose a new approach for image denoising based on the combination of two non linear diffusion tensors. One allows diffusion along the orientation of greatest coherences, while the other allows diffusion along orthogonal directions. The idea is to track perfectly the local geometry of the degraded image and applying anisotropie diffusion mainly along the preferred structure direction. To illustrate the effective performance of our model, we present some experimental results on a test and real photographic color images.
Recent advances in deep neural networks (DNNs) have mainly focused on innovations in network ar-chitecture and loss function. In this paper, we introduce a flexible high-order coverage function (HCF) neuron model to r...
详细信息
Recent advances in deep neural networks (DNNs) have mainly focused on innovations in network ar-chitecture and loss function. In this paper, we introduce a flexible high-order coverage function (HCF) neuron model to replace the fully-connected (FC) layers. The approximation theorem and proof for the HCF are also presented to demonstrate its fitting ability. Unlike the FC layers, which cannot handle high-dimensional data well, the HCF utilizes weight coefficients and hyper-parameters to mine under-lying geometries with arbitrary shapes in an n-dimensional space. To explore the power and poten-tial of our HCF neuron model, a high-order coverage function neural network (HCFNN) is proposed, which incorporates the HCF neuron as the building block. Moreover, a novel adaptive optimization method for weights and hyper-parameters is designed to achieve effective network learning. Compre-hensive experiments on nine datasets in several domains validate the effectiveness and generalizability of the HCF and HCFNN. The proposed method provides a new perspective for further developments in DNNs and ensures wide application in the field of image classification. The source code is available at https://***/Tough2011/*** (c) 2022 Elsevier Ltd. All rights reserved.
The discretization of a HT space results in the ρ value detection error of a line. This paper addresses the ρ-direction precision improvement by compensating for this error. The mage are vertically or horizontally s...
详细信息
The discretization of a HT space results in the ρ value detection error of a line. This paper addresses the ρ-direction precision improvement by compensating for this error. The mage are vertically or horizontally shifted, and a series peak positions are obtained by applying the standard HT (SHT) on these shifted images. The change of ρ value of a line due to these shifts is studied. On one hand this change can be measured by detecting the peak shift in HT space, on the other hand it can be obtained by geometric analysis on the vertical or horizontal shift in image space. The difference between the unit change in HT space (i.e. the ρ-direction resolution Δρ) and the unit change in image space (i.e. ρ value change due to vertical or horizontal unit shift) is used to measure the SHT ρ value detection error. A high precision ρ value is obtained by compensating for this error. The experiments show the effectiveness of the proposed method.
暂无评论