Abstract: A method of instance segmentation, comprising, defining a bounding box, depth mapping the bounding box, sorting the depth map, estimating stability due to noise of the sorted depth map, detecting low frequency jumps of the sorted depth map based on the estimated stability, detecting high frequency jumps of the sorted depth map, comparing the detected low frequency jumps and the detected high frequency jumps, detecting at least one of a largest object and a closest object based on the comparison and pixel masking the at least one of the largest object and the closest object.

Abstract: The present invention discloses a system for precise representation of object segmentation with multi-modal input for real-time video applications. The multi-modal segmentation system takes advantage of optical, temporal as well as spatial information to enhance the segmentation for AR and VR or other entrainment purpose with accurate details. The system can segment foreground objects such as human and salient objects within a video frame and allows locating object-of-interest for multiple-purposes.

Abstract: A method of motion control and textured display, comprising, receiving an image, extracting an initial mask of a subject of interest from the image, segmenting the image into the initial mask and a background, determining a color texture of the initial mask, estimating motion of the initial mask to a new mask and merging the new mask and the background into a merged image.

Abstract: The present invention discloses system and method for processing an image. The invention processes the image by segmenting a human portrait region of the image. The invention uses ahierarchical hybrid loss module for masking the portrait region generating masked portrait region. The invention also uses data learning the masked portrait region.

Abstract: A distributed light source couple-able to a mobile device, comprising, a distributed array of light emitting points and a mount connected to the distributed array and couple-able to the mobile device, the distributed array capable of light emission from a plurality of areas.

Abstract: An example method of infrared access, comprising, receiving a plurality of visual images, receiving a plurality of infrared images, calibrating pairs of at least one of the plurality of visual images to a respective at least one of the plurality of infrared images, determining an average temperature of the plurality of infrared images, determining a temperature of the respective calibrated pairs, and granting access if a visual image of the calibrated pair is authenticated by a facial recognition library and if the temperature of the calibrated pair is within a predefined threshold of the average temperature.

Abstract: A method of depth-of-field simulation, including receiving a plurality of images, predicting a layer of interest mask of the plurality of images, determining a plurality of mean brightness anchor values of a respective plurality of layers of interest window arrays, setting a plurality of layers of interest set of binary codes, determining a hamming distance between plurality of layers of interest set of binary codes, determining a cost volume based on the hamming distance, resampling a vertical cost based on a vertical ordinal direction the cost volume, resampling a horizontal cost based on a horizontal ordinal direction the cost volume, determining an all-in-focus layer based on the vertical cost and the horizontal cost, determining an out-of-focus layer based on the vertical cost and the horizontal cost and determining a depth of the all-in-focus layer and out-of-focus layer.

Abstract: A method of auto white balancing, including, receiving an original image, determining an RG logarithmic ratio of a set of red to green channel values of the original image, determining a BG logarithmic ratio of a set of blue to green channel values of the original image, determine an original two-dimensional histogram utilizing the RG logarithmic ratio and the BG logarithmic ratio, determine a Gaussian-blur two-dimensional histogram utilizing the RG logarithmic ratio and the BG logarithmic ratio, determining a sharpened two-dimensional histogram of a sharpened image utilizing the RG logarithmic ratio and the BG logarithmic ratio, determining a Laplacian-edge two-dimensional histogram of a Laplacian-edge image utilizing the RG logarithmic ratio and the BG logarithmic ratio and determining a white balancing gain utilizing a neural network based on the original 2D histogram, the Gaussian-blur 2D histogram, the sharpened 2D histogram and the Laplacian-edge 2D histogram.

Abstract: The present invention discloses system and method for fake face identification. The system is a multi-spectral sensing based bio-security system. The system uses CNN module along with thermal sensors to detect human face and also detects the human temperature. The system authenticates a human face and in case of temperature generates an alarm as an alert.

Abstract: The present invention discloses system and method for replacing a texture of a background region in a multimedia. The system is an AI-based multi-media processing system for replacing the original texture of the background of the multimedia with a texture template. The system applies a foreground mask to hide and protect the foreground region and multiple textures of the background. The system uses deep learning to segment specific texture from images or video sequences. The system replaces the texture of the original input image with a texture template to form a processed image.

Abstract: A polarization imaging system for generating a super resolution image is disclosed in the present invention. The polarization imaging system consists of multiple functional elements for the generation of the super resolution image including a camera device, a polarization analysis module, a weight module, a fusion module and an output module. The lens of the imaging system captures light coming from a subject which is detected and acted upon by a polarization sensor. The polarization sensor generates multiple low resolution images and calculates degree of linear polarization and angle of polarization of the light rays based on which a guided mask is generated. The system employs an algorithm to combine the one or more low resolution images to produce a final super resolution image as the output.

Abstract: A system on a chip, including a first domain having a first processor, a first local memory coupled to the first processor, wherein the first local memory having a first memory format and a first sub-network coupled to the first processor, a second domain having a second processor, a second local memory coupled to the second processor and a second sub-network coupled to the second processor, wherein the second local memory having a second memory format which differs from the first memory format, a multi-tier network coupled to the first sub-network and the second sub-network, a global memory coupled to the multi-tier network and a multi-port DDR controller coupled to the global memory to receive, transmit and share the first local memory having the first memory format and the second local memory having the second memory format based on a predetermined criteria.

Abstract: A Sidwf1 gene of Sesamum indicum, including two exons and an intron, is 1638 bp in total, and has a sequence represented by SEQ ID NO: 1. Also provided is a method for determining the internode length type in sesame samples, the method including: 1) extracting a genomic DNA of a sesame sample; 2) synthesizing three primers including SiSNPdwf1 F1, SiSNPdwf1 F2, and SiSNPdwf1 R; amplifying the Sidwf1 gene or an allele SiDWF1 thereof with the genomic DNA of the sesame sample as a template, with a combination of SiSNPdwf1 F1, SiSNPdwf1 F2, and SiSNPdwf1 R a combination of SiSNPdwf1 F1 and SiSNPdwf1 R, or a combination of SiSNPdwf1 F2 and SiSNPdwf1 R, as primers, thereby yielding a PCR product; and performing electrophoresis on the PCR product or sequencing the PCR product, and determining the phenotype of the sesame sample according to an electrophoresis or sequencing result.

Abstract: The invention discloses a method and a system for achieving a unified flow control system for multiple camera devices. The system provides inline and offline streams to share resources by converting the streams into one another. The resource sharing is performed by using different time interval to process inline and offline streams. The system also includes a STALL & REDO operation to keep whole image un-broken and shut down the write stream from ISP right away.

Abstract: A method of defect pixel correction, includes, receiving at least one center pixel signal in a plurality of frames, receiving a plurality of neighboring pixel signals adjacent the center pixel in the plurality of frames, determining a brightness of the center pixel signal, determining the brightness of the plurality of neighboring pixel signals, determining if the brightness of the center pixel signal exceeds a wounded pixel threshold of the plurality of neighboring pixel signals, determining a location of the center pixel having the brightness greater than the wounded pixel threshold in at least one frame, determining a number of reoccurrences of the center pixel having the brightness greater than the wounded pixel threshold, determining if the number of reoccurrences exceeds a defect pixel threshold and updating the at least one center pixel signal to a mean of the plurality of neighboring pixel signals.

Abstract: A method of wheel encoder to camera calibration, including receiving a LiDAR (Light Detection and Ranging) signal, receiving a camera signal, receiving a wheel encoder signal, calibrating the camera signal to the LiDAR signal, calibrating the wheel encoder signal to the LiDAR signal and calibrating the camera signal to the wheel encoder signal based on the calibration of the camera signal to the LiDAR signal and the wheel encoder signal to the LiDAR signal.

Abstract: A method of adaptive quantization for a convolutional neural network, includes at least one of receiving an acceptable model accuracy, determining a float value multiply accumulate for the layer based on a float value weight and a float value input, quantizing the float value weight at multiple weight quantization precisions, quantizing the float value input at multiple input quantization precisions, determining a multiply accumulate at multiple multiply accumulate quantization precisions based on the weight quantization precisions and the input quantization precisions, determining multiple quantization errors based on differences between the float value multiply accumulate and the multiple multiply accumulate quantization precisions and selecting one of the multiple weight quantization precisions, one of the multiple input quantization precisions and one of the multiple multiply accumulate quantization precisions based on the predetermined acceptable model accuracy and the multiple quantization errors.

Abstract: An example method of infrared access, comprising, receiving a plurality of visual images, receiving a plurality of infrared images, calibrating the plurality of visual images to the plurality of infrared images, determining an average temperature of the plurality of infrared images, determining an outlier temperature of an outlier infrared image of the plurality of infrared images and matching the outlier infrared image to a visual image.

Abstract: A method of depth estimation utilizing heterogeneous cameras, comprising, homogenizing a first camera image and a second camera image based on a first camera calibration dataset and a second camera calibration dataset respectively, wherein the first camera image and second camera image are distortion corrected and are zoom compensated, determining an initial image pair rectification transformation matrix of the homogenized first camera image and the homogenized second camera image, determining a delta image pair rectification transformation matrix based on the initial image pair rectification transformation matrix, determining, a final image pair rectification transformation matrix based on the initial image pair rectification transformation matrix and the delta image pair rectification transformation matrix resulting in a final rectified image pair and disparity mapping the final rectified image pair based on a depth net regression.

Abstract: A method of mapping and localization is disclosed that includes, reconstructing a point cloud and a camera pose based on VSLAM, synchronizing the camera pose and a GPS timestamp at a first set of GPS coordinate points and transforming the first set of GPS coordinate points corresponding to the GPS timestamp into a first set of ECEF coordinate points. The method also includes determining a translation and a rotation between the camera pose and the first set of ECEF coordinate points, transforming the point cloud and the camera pose into a second set of ECEF coordinates based on the translation and the rotation and transforming the point cloud and the camera pose into a second set of GPS coordinate points. The method further includes constructing and storing a key-frame image, a key-frame timestamp and a key-frame GPS based on the second set of GPS coordinate points.