Abstract: Machine learning models can process a video and generate outputs such as action segmentation assigning portions of the video to a particular action, or action classification assigning an action class for each frame of the video. Some machine learning models can accurately make predictions for short videos but may not be particularly suited for performing action segmentation for long duration, structured videos. An effective machine learning model may include a hybrid architecture involving a temporal convolutional network and a bi-directional graph neural network. The machine learning model can process long duration structured videos by using a temporal convolutional network as a first pass action segmentation model to generate rich, frame-wise features. The frame-wise features can be converted into a graph having forward edges and backward edges. A graph neural network can process the graph to refine a final fine-grain per-frame action prediction.

Abstract: A video compression framework based on parametric object and background compression is proposed. At the encoder, an object is detected and frames are segmented into regions corresponding to the foreground object and the background. The encoder generates object motion and appearance parameters. The motion or warping parameters may include at least two parameters for object translation; two parameters for object scaling in two primary axes and one object orientation parameter indicating a rotation of the object. Particle filtering may be employed to generate the object motion parameters. The proposed methodology is the formalization of the concept and usability for perceptual quality scalability layer for Region(s) of Interest. A coded video sequence format is proposed which aims at “network friendly” video representation supporting appearance and generalized motion of object(s).

Abstract: A method for moving objection detection in an image analysis system is provided. The method includes analyzing consecutive video frames from a single camera to extract box properties and exclude objects that are not of interest based upon the box properties. Motion and structure data are obtained for boxes not excluded. The motion and structure data are sent to a trained classifier. Moving object boxes are determined by the trained classifier. The moving object box identifications are provided to a vehicle system. The data sent to the classifier can consist of the motion and structure data, and no deep learning methods are applied to the video frame data. Driver assistance vehicle systems and autonomous driving systems are also provided based upon the moving object box detection.

Abstract: A video compression framework based on parametric object and background compression is proposed. At the encoder, an embodiment detects objects and segments frames into regions corresponding to the foreground object and the background. The object and the background are individually encoded using separate parametric coding techniques. While the object is encoded using the projection of coefficients to the orthonormal basis of the learnt subspace (used for appearance based object tracking), the background is characterized using an auto-regressive (AR) process model. An advantage of the proposed schemes is that the decoder structure allows for simultaneous reconstruction of object and background, thus making it amenable to the new multi-thread/multi-processor architectures.

Abstract: A video compression framework based on parametric object and background compression is proposed. At the encoder, an object is detected and frames are segmented into regions corresponding to the foreground object and the background. The encoder generates object motion and appearance parameters. The motion or warping parameters may include at least two parameters for object translation; two parameters for object scaling in two primary axes and one object orientation parameter indicating a rotation of the object. Particle filtering may be employed to generate the object motion parameters. The proposed methodology is the formalization of the concept and usability for perceptual quality scalability layer for Region(s) of Interest. A coded video sequence format is proposed which aims at “network friendly” video representation supporting appearance and generalized motion of object(s).

Abstract: A GOP-independent dynamic bit-rate controller system includes a user interface to receive one or more input parameters, a bit-rate controller and an encoder. The bit-rate controller regulates a bit-rate of an output bit-stream. The bit-rate controller includes multiple bit-rate modules to determine a bit-estimate and a quantization parameter, and a control module to calculate a convergence period based on the received input parameters and a frame rate. The control module selects a bit rate module based on the convergence period and the encoder generates the output bit-stream using the quantization parameter determined by the bit rate module.

Abstract: An embodiment is a computer-implemented method for detecting a straight line in a digital image comprising a plurality of pixels comprising the steps: detecting an edge in the digital image, generating a first straight line which passes through a first pixel of the detected edge, generating a second straight line which passes through a second pixel of the detected edge, which is different from the first pixel, determining at least two intersections with a boundary of the digital image for each generated straight line, determining a set of two parameter values for each generated straight line based on the respective determined at least two intersections, wherein the set of two parameter values uniquely determines the respective generated straight line, and detecting the straight line in the digital image based on the determined sets of two parameter values.

Abstract: A system and corresponding method determines a macroblock partition to transcode digital data from a first video standard to a second video standard with any spatial resolution. The system includes a processing module and an encoding module. The processing module processes digital data to determine a macroblock partition. The encoding module is coupled to the processing module for encoding the digital data based on the macroblock partition. The system is further coupled to a decoding module for receiving the digital data. The method determines the partition of a macroblock for transcoding digital data with any spatial resolution and without any motion estimation.

Abstract: A GOP-independent dynamic bit-rate controller system includes a user interface to receive one or more input parameters, a bit-rate controller and an encoder. The bit-rate controller regulates a bit-rate of an output bit-stream. The bit-rate controller includes multiple bit-rate modules to determine a bit-estimate and a quantization parameter, and a control module to calculate a convergence period based on the received input parameters and a frame rate. The control module selects a bit rate module based on the convergence period and the encoder generates the output bit-stream using the quantization parameter determined by the bit rate module.

Abstract: A video compression framework based on parametric object and background compression is proposed. At the encoder, an embodiment detects objects and segments frames into regions corresponding to the foreground object and the background. The object and the background are individually encoded using separate parametric coding techniques. While the object is encoded using the projection of coefficients to the orthonormal basis of the learnt subspace (used for appearance based object tracking), the background is characterized using an auto-regressive (AR) process model. An advantage of the proposed schemes is that the decoder structure allows for simultaneous reconstruction of object and background, thus making it amenable to the new multi-thread/multi-processor architectures.

Abstract: A video compression framework based on parametric object and background compression is proposed. At the encoder, an embodiment detects objects and segments frames into regions corresponding to the foreground object and the background. The object and the background are individually encoded using separate parametric coding techniques. While the object is encoded using the projection coefficients to the orthonormal basis of the learnt subspace (used for appearance based object tracking), the background is characterized using an auto-regressive (AR) process model. An advantage of the proposed schemes is that the decoder structure allows for simultaneous reconstruction of object and background, thus making it amenable to the new multi-thread/multi-processor architectures.

Abstract: An embodiment is a computer-implemented method for detecting a straight line in a digital image comprising a plurality of pixels comprising the steps: detecting an edge in the digital image, generating a first straight line which passes through a first pixel of the detected edge, generating a second straight line which passes through a second pixel of the detected edge, which is different from the first pixel, determining at least two intersections with a boundary of the digital image for each generated straight line, determining a set of two parameter values for each generated straight line based on the respective determined at least two intersections, wherein the set of two parameter values uniquely determines the respective generated straight line, and detecting the straight line in the digital image based on the determined sets of two parameter values.

Abstract: A video compression framework based on parametric object and background compression is proposed. At the encoder, an object is detected and frames are segmented into regions corresponding to the foreground object and the background. The encoder generates object motion and appearance parameters. The motion or warping parameters may include at least two parameters for object translation; two parameters for object scaling in two primary axes and one object orientation parameter indicating a rotation of the object. Particle filtering may be employed to generate the object motion parameters. The proposed methodology is the formalization of the concept and usability for perceptual quality scalability layer for Region(s) of Interest. A coded video sequence format is proposed which aims at “network friendly” video representation supporting appearance and generalized motion of object(s).

Abstract: A video compression framework based on parametric object and background compression is proposed. At the encoder, an object is detected and frames are segmented into regions corresponding to the foreground object and the background. The encoder generates object motion and appearance parameters. The motion or warping parameters may include at least two parameters for object translation; two parameters for object scaling in two primary axes and one object orientation parameter indicating a rotation of the object. Particle filtering may be employed to generate the object motion parameters. The proposed methodology is the formalization of the concept and usability for perceptual quality scalability layer for Region(s) of Interest. A coded video sequence format is proposed which aims at “network friendly” video representation supporting appearance and generalized motion of object(s).

Abstract: A GOP-independent dynamic bit-rate controller system includes a user interface to receive one or more input parameters, a bit-rate controller and an encoder. The bit-rate controller regulates a bit-rate of an output bit-stream. The bit-rate controller includes multiple bit-rate modules to determine a bit-estimate and a quantization parameter, and a control module to calculate a convergence period based on the received input parameters and a frame rate. The control module selects a bit rate module based on the convergence period and the encoder generates the output bit-stream using the quantization parameter determined by the bit rate module.

Abstract: A video compression framework based on parametric object and background compression is proposed. At the encoder, an embodiment detects objects and segments frames into regions corresponding to the foreground object and the background. The object and the background are individually encoded using separate parametric coding techniques. While the object is encoded using the projection of coefficients to the orthonormal basis of the learnt subspace (used for appearance based object tracking), the background is characterized using an auto-regressive (AR) process model. An advantage of the proposed schemes is that the decoder structure allows for simultaneous reconstruction of object and background, thus making it amenable to the new multi-thread/multi-processor architectures.

Abstract: A system and corresponding method determines a macroblock partition to transcode digital data from a first video standard to a second video standard with any spatial resolution. The system includes a processing module and an encoding module. The processing module processes digital data to determine a macroblock partition. The encoding module is coupled to the processing module for encoding the digital data based on the macroblock partition. The system is further coupled to a decoding module for receiving the digital data. The method determines the partition of a macroblock for transcoding digital data with any spatial resolution and without any motion estimation.