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.
Robust covariant local feature detectors are important for detecting local features that are (1) discriminative of the image content and (2) can be repeatably detected at consistent locations when the image undergoes diverse transformations. Such detectors are critical for applications such as image search and scene reconstruction. Many learning-based local feature detectors address one of these two...
Researchers gave the vehicle and pedestrian detection lots of attention to alarm the drivers for improving the safety of transportation systems. However, bicycles are also the significant factor of the safety on road. In this paper, a bicycle detector for side-view image is proposed based on the observation that a bicycle consists of two wheels in the form of ellipse shapes and a frame in the form...
Color represents an important attribute in the field of traffic sign recognition. However, when the color of the traffic sign fades or the traffic scene is collected in gray as in the case of Infrared imaging, then color based recognition systems fail. Other problems related to color are simply that different countries use different colors. Even within the European Union, colors of traffic signs are...
If we compare the object recognition abilities of human and computer-based system, it is much complex task for a machine. Human brain can recognize an object quickly but for a computer system accuracy depends on the level of algorithms, software and tools used for recognition. Image processing, pattern recognition and compute vision are being challenging but becomes a crucial component for developing...
Museums, libraries, national archives and art galleries deal with visual objects that must be made accessible to a wide variety of experts or non-experts like researchers, art lovers or interested people. The ability to identify objects sharing some aspect of visual similarity can be useful when trying to trace historical influences or when looking for further examples of paintings, sculptures or...
This paper describes a computer vision system to detect and count moving vehicles on roads. The system uses a real-time traffic video surveillance camera mounted over roads and computes the total number of vehicles which passed the road. Moving vehicle image is extracted using ‘double difference image ‘algorithm and counting is accomplished by tracking vehicle movements within a tracking zone, called...
Object recognition in real scenes is a central problem in computer vision. In this paper we propose a new approach for shape based recognition of objects in real scenes. This approach uses moment invariants for identification of shape features. Moment Invariants are functions of central moments. They are invariant against linear transformations such as rotation, translation and scaling. Therefore,...
In this paper, we present two methods to improve the performance of landmark detection algorithms that are designed to detect individual landmarks. We focus on the landmark configuration module that takes the output of the individual landmark detectors and searches for a configuration of optimal landmark locations based on appropriate shape constraints. We design two configuration search approaches:...
Several popular corner detectors were evaluated on imagery containing corners with a variety of internal angles. Even in a noise-free environment, differences in performance were found. A null hypothesis approach was taken in evaluating whether these performance differences were significant, taking into account correctly the size of the dataset and the number of discrepancies. It was found that some...
Finding corresponding image points is a challenging computer vision problem, especially for confusing scenes with surfaces of low textures or repeated patterns. Despite the well-known challenges of extracting conceptually meaningful high-level matching primitives, many recent works describe high-level image features such as edge groups, lines and regions, which are more distinctive than traditional...
This paper presents a novel approach for interest point and region detection which is invariant to affine transformations. Such transformations introduce significant changes in the point location as well as in the scale and the shape of the neighborhood of an interest point. Our approach allows to solve for these problems simultaneously. The approach is based on three key ideas: 1) Interest points...
Recently great progress has been made in the field of region detecting and matching. However, an extra step, fitting the irregular regions into fixed shapes, must be implemented in advance when constructing these descriptors on irregular regions. This shape fitting step can cause great errors, and thus will result in poor matching. In this paper, a method for irregular regions automatic matching is...
In this paper, anisotropic scale space is introduced to SIFT method. The method will detect stable elliptical Gaussian blob features of different orientations. Additional feature parameters can be utilized to match features with high probability. New salient features are detected by convolving image with elliptical Gaussian instead circular one. The elliptical Gaussian pyramid is carefully constructed...
Basically, detecting convex and concave points on the boundary of an object plays an important role in computer vision, object recognition and image understanding. In this paper a method that combines boundary and skeleton information for detecting these critical points is proposed. Specifically, the method is developed with the aim of obtaining high performance and efficiency, and producing a more...
Maximally Stable Extremal Regions (MSERs) are one of the most prominent interest region detectors in computer vision due to their powerful properties and low computational demands. In general MSERs are detected in single images, but given image sequences as input, the repeatability of MSER detection can be improved by exploiting correspondences between subsequent frames by feature based analysis....
Feature matching plays an important role in many applications, including 3D reconstruction, object recognition and video understanding. Point matching has made great progress recently, while it has made little progress in the fields of line and curve matching. By computing statistics of point descriptors constructed at each edge points, this paper develops a novel method for extending point descriptors...
A method of object detecting based on local contour learning and matching is proposed. Firstly, the representative images are obtained through unsupervised clustering to be as templates. The local contour information of template is extracted and generalized as the template feature, at the same time, codebook dictionary of local contour is built up. Secondly, based on codebook dictionary, using simple...
The paper overviews a vision-based technique that can be instrumental in assisting visually impaired humans in their activities. This category includes both blind people and individuals unable (e.g. due to neural disabilities) to understand semantics of the perceived visual data. Alternatively, the technique can be used as a tool for autonomous agents (e.g. mobile robots) performing in complex environments...
Local image features are used for a wide range of applications in computer vision and range imaging. While there is a great variety of detector-descriptor combinations for image data and 3D point clouds, there is no general method readily available for 2D range data. For this reason, the paper first proposes a set of benchmark experiments on detector repeatability and descriptor matching performance...
Human detection remains a challenge in computer vision due to highly articulated body postures, viewpoints changes, varying illumination conditions and cluttered background. Because of these difficulties, most of the previous publications often focus only on low-articulated postures, e.g. pedestrians, in still images. In this paper, we propose a new method to detect a human region from still images...
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.