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.
We propose a simple, yet powerful regularization technique that can be used to significantly improve both the pairwise and triplet losses in learning local feature descriptors. The idea is that in order to fully utilize the expressive power of the descriptor space, good local feature descriptors should be sufficiently “spread-out” over the space. In this work, we propose a regularization term to maximize...
With the increased use of smart devices, digital cameras and abundance of memory in the devices, the pictures of the same scenes have been taken several times, resulting in a number of images consisting of the same or very similar content in memory. Manually selecting the good ones is time-consuming as well as error prone. In this paper, the features of the images in the data sets were extracted and...
This paper proposes a novel inherently rotation invariant local descriptor which combined intensity information and gradient information of key feature. The CS-LBP shows a better performance than SIFT and do not need large computation. To further enhance its performance and robustness, we calculated the gradient of key feature and computed a combined histogram included intensity and gradient information...
One technical challenge in the field of computer vision is to acquire information in three dimensions from an arbitrary environment. There have been successful algorithms that focus on the precision and robustness, the 3D vision, or a generalized vision system, yet none of them performs very well in all these aspects and approach the level of human vision. The research problem of this project is to...
The present paper describes a low-cost algorithm for video stabilization. Like other feature based algorithms, it is robust to motion blur, noise and illumination changes. Moreover, maintaining real time processing, it is not negatively affected by moving objects in the scene, works fine even in conditions of low details in the background and it is robust to scene changes.
Many emerging motion-related applications, such as virtual reality, decision making, and health monitoring, demand reliability and quick response upon input changes. Motion capture has been a well-researched topic in the past decades with applications in many industries. The ability to capture motion goes hand in hand with real-time capability in a system. This paper gives an overview on real-time...
In this paper, a new shaped marker is designed for augmented reality applications that has 360 degree viewing angle about its shaft axis. The main advantage of the designed marker is that it is very simple to extract marker area from images with basic image processing methods. And decoding of the marker codes is very simple with basic mathematical functions. Experimental results showed that, the designed...
We present a robust particle filter based visual tracker based on an earlier approach called mean-transform which can track a window with orientation and scale changes. This work is the first work combining sparse coding, mean transform and particle filtering in visual tracking. We show that particle filter is effective in enhancing the mean-transform tracker. From the result, we see that such architecture...
Object tracking is one of the most important components in numerous applications of computer vision. In this paper, the target is represented by a series of binary patterns, where each binary pattern consists of several rectangle pairs in variable size and location. As complementary to traditional binary descriptors, these patterns are extracted in both the intensity domain and the gradient domain...
In this paper, we present an improved version of MOBIL descriptor [1] (Improved MOments based BInary differences for Local description), which introduces two main contributions. The first one is the use of geometric information for the binary test instead of the classical intensity binary test, to get more precision in the description step. The second one is to attribute two bits for each test, to...
Local feature descriptor plays a fundamental role in many visual tasks, and its rotation invariance is a key issue for many recognition and detection problems. This paper proposes a novel rotation invariant descriptor by ordinal pyramid pooling of local Fourier transform features based on their radial gradient orientations. Since both the low-level feature and pooling strategy are rotation invariant,...
Definition and extraction of local features play a very important role in image retrieval (IR), pattern recognition and computer vision. Fast growth of technology today calls for local features to be as compact as possible toward real-time and limited bandwidth applications. In this paper, we study the problem of representing images in a compact way to achieve low bit-rate transmission while maintaining...
We propose a new categorical object recognition algorithm robust to scale changes. We first partition an input image into k regions by using depth data from an RGB-D sensor, and then we estimate the object scale for each partitioned region. Finally, scaled model is applied to recognize the object.
Video has difficulty to maintain consistent intensity and color tone from frame to frame. Particularly, it happens when imaging device such as black box camera has to deal with fast changing illumination environment. However, conventional automatic white balance algorithms cannot handle this good enough to maintain tone consistency, which is observed in most commercial black box products. In this...
Occlusion is one important problem in single object tracking. However, conventional methods are not capable of making full use of the spatial information because of occlusion, which may lead to the drift. In this paper, we propose a robust patches-based tracking method via sparse representation, namely RPSR, which selects the unoccluded patches, and adaptively assigns larger contribution factors to...
This paper presents a novel method to find corners that are well located and stable interest points in a given image. Our corners are defined as intersection points of non collinear straight image edges, which are very robust against various image transformations like image scaling, rotation, translation and also to viewpoint and illumination changes. Some light updates on the linking edge step that...
Catadioptric omnidirectional view sensor has a convenient 360 degree field of view that favours various robotic applications. The distortion nature in omnidirectional view images allows the discovery of a new robust image feature in the form of vertical/central propagating lines. In this paper, we proposed an improvement to the existing vertical line detection algorithm using Haar wavelet transform...
We present an adaptive non-local means (NLM) denoising method for a sequence of images captured by a multiview imaging system, where direct extensions of existing single image NLM methods are incapable of producing good results. Our proposed method consists of three major components: (1) a robust joint-view distance metric to measure the similarity of patches; (2) an adaptive procedure derived from...
Pose tracking technique has great potential for many applications such as marker-free human motion capture system, Human Computer Interactions (HCI), and video surveillance. Though many methods are introduced during last decades, self-occlusion - one body part is occluded by another one - is still considered one of the most difficult problems for 3D human pose tracking. In this paper, we propose a...
Reliable and effective matching of visual descriptors is a key step for many vision applications, e.g. image retrieval. In this paper, we propose to integrate the Hausdorff distance matching together with our pairing algorithm, in order to obtain a robust while computationally efficient process of matching feature descriptors for image-to-image querying in standards datasets. For this purpose, Scale...
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.