Abstract: The present invention integrates a low power and high compression pixel-wise coded exposure (PCE) camera with advanced object detection, tracking, and classification algorithms into a real-time system. A PCE camera can control exposure time of every pixel in the camera and at the same time can compress multiple frames into a compressed frame. Consequently, it can significantly improve the dynamic range as well as reduce data storage and transmission bandwidth usage. Conventional approaches utilize PCE camera for object detection, tracking and classification, require the compressed frames to be reconstructed. These approaches are extremely time consuming and hence makes the PCE cameras unsuitable for real-time applications. The present invention presents an integrated solution that incorporates advanced algorithms into the PCE camera, saving reconstruction time and making it feasible to work in real-time applications.

Abstract: The present invention integrates a low power and high compression pixel-wise coded exposure (PCE) camera with advanced object detection, tracking, and classification algorithms into a real-time system. A PCE camera can control exposure time of every pixel in the camera and at the same time can compress multiple frames into a compressed frame. Consequently, it can significantly improve the dynamic range as well as reduce data storage and transmission bandwidth usage. Conventional approaches utilize PCE camera for object detection, tracking and classification, require the compressed frames to be reconstructed. These approaches are extremely time consuming and hence makes the PCE cameras unsuitable for real-time applications. The present invention presents an integrated solution that incorporates advanced algorithms into the PCE camera, saving reconstruction time and making it feasible to work in real-time applications.

Abstract: A system and method for generating high-resolution stereo images and depth map in multi-camera systems having multiple cameras with different resolutions and view angles. One method is to improve the lower resolution image and combining it with the higher resolution image, then the resulting image is processed by extensive algorithms to ensure utmost high quality. The system can also handle non-planar image contents. The process is to generate a crude depth map first and then divide the map into multiple layers. Each layer will be separately registered. The results from the registered layers will be merged to improve the depth map generation. The improved depth map could be repeatedly fed back to the beginning of the process to further improve the registration performance. The system and method can generate stereo images using uncalibrated cameras with different views and resolutions.

Abstract: The present invention provides a method and system to conceal video errors due to lost packets in the transmission without incurring additional bandwidth usage. The present invention is to use current and previous frames to search for similar patches for the corrupted blocks in the current frame. The search process speed for locating the lost packets is significantly improved by incorporating a smart search concept. The concealment algorithm of the present invention can be implemented in GPUs and multi-core CPUs.

Abstract: The present invention is to provide a method and system using compressed data directly for target tracking and target classification in videos. The present invention uses a video imager to generate compressive measurements, and a random subsampling operator to compress the video data. It uses a Gaussian Mixture Model (GMM) for target detection and manual location of the target and putting a bounding box around the targets in the first frame is not required. It further applies a saliency-based algorithm to re-center the captured target. This re-centering process can be repeated multiple times and each application of re-centering will improve over the previous one. A pixel completion algorithm is used to fill in the missing pixels for the captured target area. A Sparse Representation Classification (SRC) for target classification. Both the target templates in a dictionary and captured targets are transformed to the frequency domain using Fast Fourier Transform (FFT).

Abstract: A system and method for generating high-resolution stereo images and depth map in multi-camera systems having multiple cameras with different resolutions and view angles. One method is to improve the lower resolution image and combining it with the higher resolution image, then the resulting image is processed by extensive algorithms to ensure utmost high quality. The system can also handle non-planar image contents. The process is to generate a crude depth map first and then divide the map into multiple layers. Each layer will be separately registered. The results from the registered layers will be merged to improve the depth map generation. The improved depth map could be repeatedly fed back to the beginning of the process to further improve the registration performance. The system and method can generate stereo images using uncalibrated cameras with different views and resolutions.

Abstract: A method and system for enhancing predictive accuracy of planet surface characteristics from orbit using an extended approach of Pan-Sharpening by using multiple high resolution bands to reconstruct high resolution hyperspectral image is disclosed. Sparsity based classification algorithm is applied to rock type classification. An Extended Yale B face database is used for performance evaluation; and utilizing deep Neural Networks for pixel classification. The present invention presents a system that can significantly enhance the predictive accuracy of surface characteristics from the orbit. The system utilizes complementary images collected from imagers onboard satellites.

Abstract: The present invention is to provide a method and system using compressed data directly for target tracking and target classification in videos. The present invention uses a video imager to generate compressive measurements, and a random subsampling operator to compress the video data. It uses a Gaussian Mixture Model (GMM) for target detection and manual location of the target and putting a bounding box around the targets in the first frame is not required. It further applies a saliency-based algorithm to re-center the captured target. This re-centering process can be repeated multiple times and each application of re-centering will improve over the previous one. A pixel completion algorithm is used to fill in the missing pixels for the captured target area. A Sparse Representation Classification (SRC) for target classification. Both the target templates in a dictionary and captured targets are transformed to the frequency domain using Fast Fourier Transform (FFT).

Abstract: The present invention is to incorporate a novel two-step image registration algorithm that can achieve sub-pixel accuracy in order to provide a method and system that can significantly improve the remote monitoring performance of coral reefs and volcanoes using a future NASA remote imager known as HyspIRI, by increasing the spatial and temporal resolution of remote sensing data from multiple satellites. Our invention focuses on change detection, multiple images registration, target detection, coral reef and volcano monitoring. The objectives are achieved by accurate and early change detection in coral health, and volcanic activities, such as, by detecting color changes in crater lakes; accurate bottom-type classification in coral reefs; accurate concentration estimation of SO2, volcanic ashes, etc.; high temporal resolution of monitoring so that early mitigation steps can be activated; and high spatial resolution in multispectral and hyperspectral images.

Abstract: The present invention presents four fusion approaches, which can be directly applied to Worldview-3 (WV-3) images. Moreover, they can also be applied to other current or future satellite images that have similar characteristics of WV-3. The present invention also presents data processing methods, including image fusion method, anomaly detection method, material classification method, and concentration estimation method that utilize the high-resolution images generated by the mentioned fusion methods. There are four fusion approaches disclosed in the present invention, e.g. Parallel one-step fusion approach; Sequential fusion of various bands; Sequential-Parallel fusion; and Parallel-Sequential fusion.

Abstract: A method and system for enhancing predictive accuracy of planet surface characteristics from orbit using an extended approach of Pan-Sharpening by using multiple high resolution bands to reconstruct high resolution hyperspectral image is disclosed. Sparsity based classification algorithm is applied to rock type classification. An Extended Yale B face database is used for performance evaluation; and utilizing deep Neural Networks for pixel classification. The present invention presents a system that can significantly enhance the predictive accuracy of surface characteristics from the orbit. The system utilizes complementary images collected from imagers onboard satellites.

Abstract: An active noise reduction system and method to cancel fan or blower noise. The system utilizes 2 microphones: one to pick up the subject noise and the noisy signal at far field. The proposed system utilizes a portable loudspeaker that is placed near the subject. The loudspeaker broadcasts omni-directional or directional anti-phase signals to reduce the noise at far field. The system includes a real-time processor (DSP or FPGA) with fast adaptive filter to process the 2 microphone signals and generate the anti-phase signal. The adaptive filter uses the second microphone as a reference to generate an out-of-phase signal, which can then suppress the far field noise. The system is simple to set up and portable. The system utilizes frequency-domain adaptive filter and proven algorithms to quickly compute the anti-phase signals for cancelling detected noise.

Abstract: The present invention presents four fusion approaches, which can be directly applied to Worldview-3 (WV-3) images. Moreover, they can also be applied to other current or future satellite images that have similar characteristics of WV-3. The present invention also presents data processing methods, including image fusion method, anomaly detection method, material classification method, and concentration estimation method that utilize the high-resolution images generated by the mentioned fusion methods. There are four fusion approaches disclosed in the present invention, e.g. Parallel one-step fusion approach; Sequential fusion of various bands; Sequential-Parallel fusion; and Parallel-Sequential fusion.

Abstract: An active noise reduction system and method to cancel fan or blower noise. The system utilizes 2 microphones: one to pick up the subject noise and the noisy signal at far field. The proposed system utilizes a portable loudspeaker that is placed near the subject. The loudspeaker broadcasts omni-directional or directional anti-phase signals to reduce the noise at far field. The system includes a real-time processor (DSP or FPGA) with fast adaptive filter to process the 2 microphone signals and generate the anti-phase signal. The adaptive filter uses the second microphone as a reference to generate an out-of-phase signal, which can then suppress the far field noise. The system is simple to set up and portable. The system utilizes frequency-domain adaptive filter and proven algorithms to quickly compute the anti-phase signals for cancelling detected noise.

Abstract: The present invention is to provide a method and system for generating contingency flight plans for normal landing and flight termination (crash) of UAVs (drones) in the event of lost communications with ground control stations. The system is fast, automatic, comprehensive, and systematic. The contingency plan can be generated using laptops or PCs. The execution of contingency plans will involve the coordination of flight computer in drones, ground control station, air traffic controllers (ATC), and pilot in command (PIC). External devices such as satellites and RF towers are also involved in the process such as reestablishment of communications.

Abstract: A method and apparatus for real-time target recognition within a multispectral image includes generating radiance signatures from reflectance signatures, sensor information and environment information and detecting targets in the multispectral image with a sparsity-driven target recognition algorithm utilizing set of parameters tuned with a deep neural network.

Abstract: The present invention provides a method and system to conceal video errors due to lost packets in the transmission without incurring additional bandwidth usage. The present invention is to use current and previous frames to search for similar patches for the corrupted blocks in the current frame. The search process speed for locating the lost packets is significantly improved by incorporating a smart search concept. The concealment algorithm of the present invention can be implemented in GPUs and multi-core CPUs.

Abstract: The present invention is to provide a method and system for generating contingency flight plans for normal landing and flight termination (crash) of UAVs (drones) in the event of lost communications with ground control stations. The system is fast, automatic, comprehensive, and systematic. The contingency plan can be generated using laptops or PCs. The execution of contingency plans will involve the coordination of flight computer in drones, ground control station, air traffic controllers (ATC), and pilot in command (PIC). External devices such as satellites and RF towers are also involved in the process such as reestablishment of communications.

Abstract: This invention fuses spectral information from multiple imagers of an unmanned ground vehicle (UGV). Since the imagers contain different spectral information for each pixel location, the invention provides highly accurate targeting and guidance information to the UGV. The invention applies a robust 2-step image registration process for alignment of images captured by each of the multiple imagers to automatically identify targets of interest, so that the UGV can move toward the targets. This two-step image registration process can achieve sub-pixel accuracy. After registration, a new multispectral image is formed with pixels containing spectral information from all imagers. The invention further incorporates an accurate anomaly detection algorithm to help detect new targets in the scene, and incorporates advanced composition estimation algorithms to determine the composition of targets.

Abstract: The present invention provides a system to create a quiet zone by suppressing background noise near a user's head. The present invention utilizes two microphones; one microphone receives environmental noise and the other one is located close to a person's head. A parabolic dish loudspeaker creates a uniform sound field near a user's head. A high performance frequency-domain filtered-x least mean square with band selection (FD-FX-LMS-BS) algorithm is utilized to generate the anti-phase noise signals. The algorithm has high noise reduction performance and also allows selection of specific frequency bands for noise reduction. The FD-FX-LMS-BS algorithm is performed by a field programmable gate array (FPGA) chip, which has minimal delay in algorithm processing.