The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
Road detection from the perspective of moving vehicles is a challenging issue in autonomous driving. Recently, many deep learning methods spring up for this task because they can extract high-level local features to find road regions from raw RGB data, such as Convolutional Neural Networks (CNN) and Fully Convolutional Networks (FCN). However, how to detect the boundary of road accurately is still...
Person re-identification is a critical yet challenging task in video surveillance which intends to match people over non-overlapping cameras. Most metric learning algorithms for person re-identification use symmetric matrix to project feature vectors into the same subspace to compute the similarity while ignoring the discrepancy between views. To solve this problem, we proposed an asymmetric cross-view...
In this paper, a new perspective of congestion is presented to promote the development of traffic video analysis. Our main contributions are threefold: a) An unified and quantifiable definition of congestion is proposed to describe the traffic state in video. b) Based on the definition, a congestion dataset which contains multiple traffic scenes is constructed as a platform for the research community...
Group detection aims to classify pedestrians into categories according to their motion dynamics. It's fundamental for analyzing crowd behaviors and involves a wide range of applications. In this paper, we propose a Anchor-based Manifold Ranking (AMR) method to detect groups in crowd scenes. Our main contributions are threefold: (1) the topological relationship of individuals are effectively investigated...
The sintering status of rotary kiln is so complex that it can not be described by a precise mathematical model. Therefore it is difficult to monitor the online status continuously and control the sintering conditions automatically. The evaluation and control of the sintering information from burning flame images have been shown effective yet challenging techniques in the rotary kiln process. Based...
Sub-health is an intermediate state between healthy and diseased, and it is becoming more and more popular. Sub-healthy individuals are at high risk of developing disease if not treated in time. In order to evaluate sub-health state, synchronous acquisition of pulse and electrocardiogram (ECG) signals was conducted by using self-designed synchronous acquisition system. An objective measurement to...
This paper demonstrates that a single thermally-modulated semiconductor gas sensor can discriminate and measure concentrations between two different explosive gases (CH4 and H2) and their mixtures. This method uses a novel feature extraction method, which is based on the wavelet singular entropy (WSE). From the time-frequency domain and energy spectrum perspective, wavelet decomposition coefficients...
An efficient method for 3D reconstruction of nanostructures based on the SEM imaging principle is reported in this paper. By analyzing the contrast of one single top-view SEM image which contains all the surface information of visible structures, both the 3D morphology and shape parameters of nanostructures can be obtained. Thus it can provide more details of nanostructures and conduct subsequent...
Sparse modeling is a powerful framework for data analysis and processing. It is especially useful for high-dimensional regression and classification problems in which a large number of feature variables exist but the amount of training samples is limited. In this paper, we address the problems of feature description, feature selection and classifier design for hyperspectral images using structured...
This paper proposes a real-time traffic sign detection system. In order to extract accurately the shape feature of the traffic sign, reduce the computational load and further improve the traffic sign detection rate, a novel approach based on surround suppression of texture edges and cascade detector is presented. The principle of surround suppression mainly adds a computational step to the canny edge...
This paper proposes a novel method for reconstruction of the target three-dimensional (3D) objects based on motion vision. The main contribution of this paper is twofold: (1) we build a new mathematical model to express the position relationship of the camera, the image plane, the ground plane and the target 3D objects at different times. (2) We propose and implement a 3D reconstruction algorithm...
An expert system for road extraction from remote sensing image was proposed to increase the efficiency of road mapping. It is designed based on the technology of image processing and machine vision. This approach obtains the basic characteristics of the road with the expert experience to simulate the process of visual interpretation from remote sensing image. The performance of this expert system...
A new prototype of self-validating pressure sensor is described. The elastic body of the transducer is based on circular-flat diaphragm structure. Eight groups of strain gauges are distributed on the diaphragm. One group of metal strain gauge with little temperature drift is used as primary pressure sensor, the other seven groups of semiconductor strain gauges with high sensitivity are used as calibration...
Existing BVHs are restricted to surface-based hierarchical decomposition, which lose the inner space properties of object and provide little guidance for the collision avoidance. We present a novel, volume-based BvH - inner space bounding volume hierarchy (ISBVH). Compared with the surface-based BVH, ISBVH can enclose the boundary surface and inner space simultaneously in any order. Due to approximating...
It is difficult to recognize sign language in different viewpoint. The HMM method is hindered by the difficulty of extracting view invariant features. The general template matching methods have a strong constraint such as accurate alignment between the template sign and the test sign. In the paper, we introduce a novel approach for viewpoint invariant sign language recognition. The proposed approach...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.