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.
In order to eliminate vehicle shadow in moving vehicle detection, a novel vehicle shadow elimination approach is presented based on mark growing of multi-feature fusion. The selection of mark points and the establishment of growing rules are critical. Firstly, background model is obtained by mixture Gaussian method. Then gradient difference of foreground and background is calculated. Morphological...
In this paper, under the non-local means framework, we propose a non-local bilateral filter algorithm for image denoising based on the neighborhoods' gray value and the corresponding neighborhoods' Gaussian curvature. We also adopt a new method to provide the optimum denoising parameter h based on the discrete wavelet transform and the smoothing spline estimation. Meanwhile the generalized cross-validation...
Fuzzy clustering algorithms have been successfully applied to POLSAR classification, but not to POLInSAR. In this paper, a Fuzzy C Means (FCM) clustering algorithm integrating the complementary physical information and statistical property contained in both polarimetric and interferometric data, is used for POLInSAR classification. At first, the area dominated by volume scattering is extracted from...
It is an intriguing challenge that insects can catch small moving targets amidst the clutter and moving scene accurately by the compound eye system which is with limited resolution. Especially when the velocity of the target is matched to the background, insect can also detect and catch it. Inspired by the neural mechanism of compound eye, this paper proposed a bio-inspired nonlinear self-adaptive...
Reichardt motion detector is the most basic mechanism of motion perception of biological vision system. But because of the aperture problem and the dependence of scene pattern, the detected motion information is always ambiguity. However, the vision cognition mechanism shows that: the motion perception of vision system doesn't only detect motion velocity, but also supplies the temporal feature to...
In order to reduce the massive manual intervention involved in the existing segmentation methods for human cross-section slice images, a segmentation algorithm based on the theory of region growing and threshold in normal gray histogram was proposed in this paper, according to the features of slice images of human brain. More exactly, these slice images were initially segmented coarsely by means of...
By reversing secret images, a novel multi-secret visual cryptography scheme is presented in this paper. During the secret sharing process, the correlative matrices are designed to encode multiple images into two ring shares. Compared with the previous ones, the proposed scheme makes the number of secret images not restricted and has obviously improved the pixel expansion and the relative difference.
A wide variety of present approaches work well in detecting frontal faces, but they are often unable to detect faces with partial occlusion, rotation and strong shadows. To address this problem, we propose an efficient technique. First, we filter the face-like regions from the input image using skin-color model. And then component classifiers are used to detect the faces' components from these potential...
Spatial resolution reduction of compressed video is highly desirable in video transcoding. Many studies have addressed this problem, but they either cause drift error or have high computation complexity. A new spatial downsampling algorithm for DCT-Domain video transcoder is proposed in this paper, in which L??M sub-blocks of N??N are combined into a L??N rows and M??N columns blocks in DCT-Domain...
3D moment invariants are traditionally based on region characteristics and the location of every pixel point, this will cause high calculation cost. In this paper, a novel shape representation named 3D gray level moment invariants is constructed. Some properties of the new representation including the independence of the translation, scaling and rotation transforms are proved. Experiments indicate...
We address the problem of robust appearance-based visual tracking. First, a set of simplified biologically inspired features (SBIF) is proposed for object representation and the Bhattacharyya coefficient is used to measure the similarity between the target model and candidate targets. Then, the proposed appearance model is combined into a Bayesian state inference tracking framework utilizing the SIR...
Speed and precision are important for object detection algorithms. In this paper, a novel object detection algorithm based on color histogram and adaptive bandwidth mean shift is proposed. The algorithm is capable of detecting objects rapidly and precisely. It is composed of two stages: a rough detection stage and a precise detection stage. At the rough detection stage, histogram back projection and...
Focusing on the fusion problem of infrared and visible images with the same scene, a novel multi-sensor image fusion scheme based on the contourlet transform (CT) was proposed, which can capture the intrinsic geometrical structure that is key in visual information. The scheme uses the multiresolution contourlet decomposition to execute the detail extraction phase and a fusion rule that combines the...
We study the problem of robust pedestrian detection. A new descriptor, Pyramidal Statistics of Oriented Filtering (PSOF), is proposed for shape representation. Unlike one-scale gradient-based methods, the PSOF descriptor constructs an image pyramid and uses a Gabor filter bank to obtain multi-scale pixel-level orientation information. Then, locally normalized pyramidal statistics of these Gabor responses...
Image measurement technology applies the digital image processing technology to the field of precision measurement. And compared to traditional ways of measurement, image measurement technology has advantages of high accuracy, large dynamic range, non-contact and flexibility, therefore, it is very suitable for a number of on-site uses that traditional ways are difficult to achieve, and it has broad...
Since multisensor image fusion is becoming a promising technique, many image fusion techniques based on the multiresolution wavelet decomposition have been developed. However, wavelets have been proved to have disappointing behaviors in higher dimensions. So, we proposed a novel multisensor image fusion scheme based on contourlet transform, which can capture the intrinsic geometrical structure that...
In this paper, we develop an improved error concealment scheme for entire frame loss of H.264/AVC by using variable-size block motion vector extrapolation. At first, the proposed algorithm extrapolates MVs from available neighboring frames onto the lost frame and determines the MV of each 8times8 block, for those blocks with dissimilar candidate MVs, they are divided into four sub-blocks and an re-estimation...
We address the problem of 3D model based vehicle localization in calibrated traffic scenes. A wire-frame vehicle model is set up as prior information and an efficient local gradient based method is proposed to evaluate the fitness between the projection of 3D model and image data, which illustrates smooth optimization surface and more conspicuous peak with low computational cost. Gradient decent is...
Fuzzy c-means (FCM) clustering algorithm has been widely used in automated image segmentation. However, the standard FCM algorithm takes a long time to partition a large dataset. In addition, in current fuzzy cluster algorithms it is difficult to determine the cluster centers. This paper proposes a modified FCM algorithm for MR (magnetic resonance) brain images segmentation. This method fetches in...
The article analyzes the advantage and disadvantage of part lacking fidelity searching algorithm, based on early ending technology thought. Given the disadvantage of the partial distortion search (PDS) algorithm, it brings up one kind of improved method which is similar to it. The improved algorithm also calculates sum of absolute difference (SAD) once within a row and add it to the block pixel SAD,...
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.