Video Person Reidentification based on Neural Ordinary Differential Equations and Graph Convolution Network

Abstract Person reidentification rate has become a challenging research topic in the field of computer vision due to the fact that person appearance is easily affected by lighting, posture and perspective. In order to make full use of the continuity of video data on the time line and the unstructured relationship of features, a video person reidentification algorithm combining the neural ordinary differential equation with the graph convolution network is proposed in this paper. First, a continuous time model is constructed by using the ordinary differential equation (ODE) network so as to capture hidden information between video frames. By simulating the hidden space of the hidden variables with the hidden time series model, the hidden information between frames that may be ignored in the discrete model can be obtained. Then, the features of the generated video frames are given to the graph convolution network to reconstruct them. Finally, weak supervision are used to classify the features. Experiments on PRID2011 data sets show that the proposed algorithm can significantly improve person reidentification performance.

Download Full-text

Video person reidentification based on neural ordinary differential equations and graph convolution network

EURASIP Journal on Advances in Signal Processing ◽

10.1186/s13634-021-00747-1 ◽

2021 ◽

Vol 2021 (1) ◽

Author(s):

Li-qiang Zhang ◽

Long-yang Huang ◽

Xiao-li Duan

Keyword(s):

Differential Equation ◽

Ordinary Differential Equation ◽

Hidden Variables ◽

Video Data ◽

Hidden Information ◽

Continuous Time Model ◽

Time Model ◽

Weak Supervision ◽

Video Frames ◽

Relationship Of

AbstractPerson reidentification rate has become a challenging research topic in the field of computer vision due to the fact that person appearance is easily affected by lighting, posture and perspective. In order to make full use of the continuity of video data on the time line and the unstructured relationship of features, a video person reidentification algorithm combining the neural ordinary differential equation with the graph convolution network is proposed in this paper. First, a continuous time model is constructed by using the ordinary differential equation (ODE) network so as to capture hidden information between video frames. By simulating the hidden space of the hidden variables with the hidden time series model, the hidden information between frames that may be ignored in the discrete model can be obtained. Then, the features of the generated video frames are given to the graph convolution network to reconstruct them. Finally, weak supervision is used to classify the features. Experiments on PRID2011 datasets show that the proposed algorithm can significantly improve person reidentification performance.

Download Full-text

Content-Based Video Scene Clustering and Segmentation

Computer Vision for Multimedia Applications ◽

10.4018/978-1-60960-024-2.ch010 ◽

2011 ◽

pp. 166-179

Author(s):

Hong Lu ◽

Xiangyang Xue

Keyword(s):

Large Scale ◽

Video Summarization ◽

Gaussian Mixture ◽

Visual Similarity ◽

Video Data ◽

Data Sets ◽

Scene Segmentation ◽

Clustering Methods ◽

Video Frames ◽

Video Scene

With the amount of video data increasing rapidly, automatic methods are needed to deal with large-scale video data sets in various applications. In content-based video analysis, a common and fundamental preprocess for these applications is video segmentation. Based on the segmentation results, video has a hierarchical representation structure of frames, shots, and scenes from the low level to high level. Due to the huge amount of video frames, it is not appropriate to represent video contents using frames. In the levels of video structure, shot is defined as an unbroken sequence of frames from one camera; however, the contents in shots are trivial and can hardly convey valuable semantic information. On the other hand, scene is a group of consecutive shots that focuses on an object or objects of interest. And a scene can represent a semantic unit for further processing such as story extraction, video summarization, etc. In this chapter, we will survey the methods on video scene segmentation. Specifically, there are two kinds of scenes. One kind of scene is to just consider the visual similarity of video shots and clustering methods are used for scene clustering. Another kind of scene is to consider both the visual similarity and temporal constraints of video shots, i.e., shots with similar contents and not lying too far in temporal order. Also, we will present our proposed methods on scene clustering and scene segmentation by using Gaussian mixture model, graph theory, sequential change detection, and spectral methods.

Download Full-text

A Topological Framework for Flow Characterization and Identification

Volume 2: Dynamic Modeling and Diagnostics in Biomedical Systems; Dynamics and Control of Wind Energy Systems; Vehicle Energy Management Optimization; Energy Storage, Optimization; Transportation and Grid Applications; Estimation and Identification Methods, Tracking, Detection, Alternative Propulsion Systems; Ground and Space Vehicle Dynamics; Intelligent Transportation Systems and Control; Energy Harvesting; Modeling and Control for Thermo-Fluid Applications, IC Engines, Manufacturing ◽

10.1115/dscc2014-5837 ◽

2014 ◽

Cited By ~ 1

Author(s):

Flavia Tauro ◽

Salvatore Grimaldi ◽

Maurizio Porfiri

Keyword(s):

Large Scale ◽

Video Data ◽

Data Sets ◽

Digital Cameras ◽

Flow Characterization ◽

Video Frames ◽

Novel Approach ◽

Flow Features ◽

Computationally Intensive ◽

Isometric Feature Mapping

The characterization of complex flows is often based on kinetic and kinematic measurements computed from high dimensional sets of data. Computationally intensive processing of such large scale data sets is a major challenge in climatological and microfluidic applications. Here, we offer a novel approach based on noninvasive and unsupervised analysis of fluid flows through nonlinear manifold learning. Specifically, we study varying flow regimes in the wake of a circular cylinder by acquiring experimental video data with digital cameras and analyze the video frames with the isometric feature mapping (Isomap). We show that the topology of Isomap embedding manifolds directly captures inherent flow features without performing velocity measurements. Further, we establish relationships between the amount of embedded data and the Reynolds number, which are utilized to detect the flow regime of independent experiments.

Download Full-text

A Bayesian approach to estimating hidden variables as well as missing and wrong molecular interactions in ordinary differential equation-based mathematical models

Journal of The Royal Society Interface ◽

10.1098/rsif.2017.0332 ◽

2017 ◽

Vol 14 (131) ◽

pp. 20170332 ◽

Cited By ~ 7

Author(s):

Benjamin Engelhardt ◽

Maik Kschischo ◽

Holger Fröhlich

Keyword(s):

Differential Equation ◽

Experimental Data ◽

Ordinary Differential Equation ◽

Molecular Interactions ◽

Bayesian Approach ◽

Hidden Variables ◽

Influence Factors ◽

Erythropoietin Receptor ◽

Molecular Networks ◽

Biological Knowledge

Ordinary differential equations (ODEs) are a popular approach to quantitatively model molecular networks based on biological knowledge. However, such knowledge is typically restricted. Wrongly modelled biological mechanisms as well as relevant external influence factors that are not included into the model are likely to manifest in major discrepancies between model predictions and experimental data. Finding the exact reasons for such observed discrepancies can be quite challenging in practice. In order to address this issue, we suggest a Bayesian approach to estimate hidden influences in ODE-based models. The method can distinguish between exogenous and endogenous hidden influences. Thus, we can detect wrongly specified as well as missed molecular interactions in the model. We demonstrate the performance of our Bayesian dynamic elastic-net with several ordinary differential equation models from the literature, such as human JAK–STAT signalling, information processing at the erythropoietin receptor, isomerization of liquid α -Pinene, G protein cycling in yeast and UV-B triggered signalling in plants. Moreover, we investigate a set of commonly known network motifs and a gene-regulatory network. Altogether our method supports the modeller in an algorithmic manner to identify possible sources of errors in ODE-based models on the basis of experimental data.

Download Full-text