Patents by Inventor Vadim Pisarevsky
Vadim Pisarevsky has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).
-
Patent number: 10180782Abstract: A specified object in still images or video may be detected using a sliding search window technique, applied to the original image and its downscaled versions, in order to detect objects of different sizes. At each scale and each position of the sliding window, the technique may use a boosted tree classifier to determine whether the window contains the object. It may exit earlier if some intermediate sum falls below the certain threshold. To accelerate object detection, hybrid features are used in different boosted chains. For first boosted chains, the fastest features may be applied and then, after more complex (but slower) features and for the last few chains, the most powerful feature (but most computationally expensive) is used. This strategy may improve the speed of detection because for a majority of checking windows, only first boosted chains are used and so only the fastest features are calculated in some embodiments.Type: GrantFiled: August 22, 2016Date of Patent: January 15, 2019Assignee: Intel CorporationInventors: Alexander Bovyrin, Vadim Pisarevsky, Irina Kostina
-
Publication number: 20170053193Abstract: A specified object in still images or video may be detected using a sliding search window technique, applied to the original image and its downscaled versions, in order to detect objects of different sizes. At each scale and each position of the sliding window, the technique may use a boosted tree classifier to determine whether the window contains the object. It may exit earlier if some intermediate sum falls below the certain threshold. To accelerate object detection, hybrid features are used in different boosted chains. For first boosted chains, the fastest features may be applied and then, after more complex (but slower) features and for the last few chains, the most powerful feature (but most computationally expensive) is used. This strategy may improve the speed of detection because for a majority of checking windows, only first boosted chains are used and so only the fastest features are calculated in some embodiments.Type: ApplicationFiled: August 22, 2016Publication date: February 23, 2017Inventors: Alexander Bovyrin, Vadim Pisarevsky, Irina Kostina
-
Patent number: 8538202Abstract: Super-resolution images may be produced by dividing a higher resolution image into a set of non-overlapping rectangular tiles of substantially the same size. Then, each pixel in each lower resolution image is mapped to the higher resolution image and it is determined which tiles are mapped to which lower resolution image pixels. A continuous buffer may be allocated for each tile and the relevant lower resolution pixels may be stored, together with optical flow vectors, in that continuous buffer. Then, the determination of gradients may use the information now stored in the buffer to facilitate symmetric multiprocessing using multi-core processors.Type: GrantFiled: November 6, 2012Date of Patent: September 17, 2013Assignee: Intel CorporationInventors: Oleg Maslov, Vadim Pisarevsky, Konstantin Rodyushkin
-
Publication number: 20130064474Abstract: Super-resolution images may be produced by dividing a higher resolution image into a set of non-overlapping rectangular tiles of substantially the same size. Then, each pixel in each lower resolution image is mapped to the higher resolution image and it is determined which tiles are mapped to which lower resolution image pixels. A continuous buffer may be allocated for each tile and the relevant lower resolution pixels may be stored, together with optical flow vectors, in that continuous buffer. Then, the determination of gradients may use the information now stored in the buffer to facilitate symmetric multiprocessing using multi-core processors.Type: ApplicationFiled: November 6, 2012Publication date: March 14, 2013Inventors: Oleg Maslov, Vadim Pisarevsky, Konstantin Rodyushkin
-
Patent number: 8326069Abstract: Super-resolution images may be produced by dividing a higher resolution image into a set of non-overlapping rectangular tiles of substantially the same size. Then, each pixel in each lower resolution image is mapped to the higher resolution image and it is determined which tiles are mapped to which lower resolution image pixels. A continuous buffer may be allocated for each tile and the relevant lower resolution pixels may be stored, together with optical flow vectors, in that continuous buffer. Then, the determination of gradients may use the information now stored in the buffer to facilitate symmetric multiprocessing using multi-core processors.Type: GrantFiled: June 30, 2008Date of Patent: December 4, 2012Assignee: Intel CorporationInventors: Oleg Maslov, Vadim Pisarevsky, Konstantin Rodyushkin
-
Publication number: 20090324118Abstract: Super-resolution images may be produced by dividing a higher resolution image into a set of non-overlapping rectangular tiles of substantially the same size. Then, each pixel in each lower resolution image is mapped to the higher resolution image and it is determined which tiles are mapped to which lower resolution image pixels. A continuous buffer may be allocated for each tile and the relevant lower resolution pixels may be stored, together with optical flow vectors, in that continuous buffer. Then, the determination of gradients may use the information now stored in the buffer to facilitate symmetric multiprocessing using multi-core processors.Type: ApplicationFiled: June 30, 2008Publication date: December 31, 2009Inventors: Oleg Maslov, Vadim Pisarevsky, Konstantin Rodyushkin
-
Patent number: 7348902Abstract: Embodiments of the present invention perform efficient decoding of variable length codes statically defined by a coding standard for a wide range of source data. According to the disclosed method, special data structures (decoding tables) are created. A bit set size is associated with each decoding table. Each decoding table contains a decoded value, actual code length, reference to another table (from the set of created tables), and validity indicator for each bit combination that can be formed from the number of bits equal to the bit set size. An active decoding table is selected. Then the number of bits equal to the bit set size associated with the active decoding table is read from a bit stream. The active decoding table is indexed with the actual value of bits read to obtain the decoded value, actual code length, reference to another table, and validity indicator. The validity indicator is then checked to determine whether the decoded value obtained is valid.Type: GrantFiled: July 29, 2003Date of Patent: March 25, 2008Assignee: Intel CorporationInventors: Vadim Pisarevsky, Sergey Zheltov, Alexander Irhin, Stanislav Bratanov
-
Publication number: 20070109160Abstract: Embodiments of the present invention perform efficient decoding of variable length codes statically defined by a coding standard for a wide range of source data. According to the disclosed method, special data structures (decoding tables) are created. A bit set size is associated with each decoding table. Each decoding table contains a decoded value, actual code length, reference to another table (from the set of created tables), and validity indicator for each bit combination that can be formed from the number of bits equal to the bit set size. An active decoding table is selected. Then the number of bits equal to the bit set size associated with the active decoding table is read from a bit stream. The active decoding table is indexed with the actual value of bits read to obtain the decoded value, actual code length, reference to another table, and validity indicator. The validity indicator is then checked to determine whether the decoded value obtained is valid.Type: ApplicationFiled: July 29, 2003Publication date: May 17, 2007Inventors: Vadim Pisarevsky, Sergey Zheltov, Alexander Irhin, Stanislav Bratanov
-
Patent number: 6768509Abstract: The present invention allows for the locations of points of interest in a calibration object in a calibration image for a digital camera to be identified automatically. The image is an array of pixels corresponding to the calibration object, which has a known reference pattern. In a preferred embodiment, the invention includes receiving an array of pixels produced by a camera, classifying each pixel of the image as light or dark, extracting contours from the image by identifying lines between light and dark pixels, comparing the extracted contours to the shapes of the known reference pattern, and identifying the shapes of the known reference pattern in the image using the extracted contours. Preferably, the image is a color image, and the color information in the pixels of the image are converted into gray scale values to render the image as a gray scale image before the pixels are classified.Type: GrantFiled: June 12, 2000Date of Patent: July 27, 2004Assignee: Intel CorporationInventors: Gary R. Bradski, Jean-Yves Bouguet, Vadim Pisarevsky, Valery Mosyagin