Abstract: This application discloses an image processing method, device, and apparatus, and a storage medium. The method is performed by a computing device, the method including: receiving an input image; determining a context feature of the input image; determining a first feature set and a second feature set according to the context feature and based on a size of a target image and a location of the input image in the target image; adjusting the second feature set according to a first feature statistic of the first feature set, to obtain an adjusted second feature set; and generating the target image based on the adjusted second feature set and the first feature set.

Abstract: A method for inspecting cargo with is disclosed. The method includes scanning the cargo with a matrix including at least two rows of detectors, wherein each zone of the cargo irradiated by a first X ray pulse is irradiated by at least one second X ray pulse, and a radiation corresponding to the first X ray pulse is detected by a first row of the matrix, and a radiation corresponding to the at least one second pulse is detected by at least one second row of the matrix, generating a first image of the cargo and at least one second image of the cargo, determining, for each zone of the cargo irradiated, a local mutual parasitic displacement between the cargo and the matrix, determining a total mutual parasitic displacement, and generating a corrected image of the cargo without the mutual parasitic displacement.

Abstract: Disclosed herein are systems, methods, and instrumentalities associated with reconstructing magnetic resonance (MR) images based on under-sampled MR data. The MR data include 2D or 3D information, and may encompass multiple contrasts and multiple coils. The MR images are reconstructed using deep learning (DL) methods, which may accelerate the scan and/or image generation process. Challenges imposed by the large quantity of the MR data and hardware limitations are overcome by separately reconstructing MR images based on respective subsets of contrasts, coils, and/or readout segments, and then combining the reconstructed MR images to obtain desired multi-contrast results.

Abstract: An intensity spectrum designing unit of a data generating device includes an initial value setting unit that sets a plurality of objects of a first generation of an intensity spectrum function A(?) and a phase spectrum function ?(?), an evaluation value calculating unit that calculates an evaluation value for each of a plurality of objects of an n-th generation, an object selecting unit that selects two or more objects used for generating a plurality of objects of an (n+1)-th generation among objects of the n-th generation on the basis of superiority of the evaluation value, and a next-generation generating unit that generates a plurality of objects of the (n+1)-th generation on the basis of the selected two or more objects. The evaluation value calculating unit, the object selecting unit, and the next-generation generating unit repeat processes while 1 is added to n until a predetermined condition is satisfied.

Abstract: The invention relates to a real-time object detection and 3D localization method based on a single frame image. Comprising following steps: S1: inputting a 2D RGB image; S2: performing feature extraction on the 2D RGB image, extracting features of a deep network and a shallow network respectively; S3: carrying out 2D object detection and applying to subsequent modules; S4: estimating vertices, instance-level depth and center point of a 3D-box respectively; S5: adding a regularization term for maintaining horizontal locality into prediction of center point of a 3D-box to constrain and optimize the prediction of center point of the 3D-box; and S6: outputting a 2D RGB image with a 3D-box tag in combination with predictions of all modules. The invention increases the speed of model training convergence and the accuracy of 3D object detection and localization, and meets the accuracy requirements of an Advanced Driver Assistant System (ADAS) with a low hardware cost.

Abstract: System, methods, and other embodiments described herein relate to improving depth prediction for objects within a low-light image using a style model. In one embodiment, a method includes encoding, by a style model, an input image to identify content information. The method also includes decoding, by the style model, the content information into an albedo component and a shading component. The method also includes generating, by the style model, a synthetic image using the albedo component and the shading component. The method also includes providing the synthetic image to a depth model.

Abstract: This document describes techniques, apparatuses, and systems for enabling multispectral object-detection with thermal imaging. A thermal sensor, a multispectral stereo camera system, and an illumination system are used in combination to provide a multispectral object-detection system for use with safety or driving systems for autonomous and semi-autonomous vehicles. The illumination system can provide illumination for the stereo camera system and serve as a range-finder that can determine a distance between the stereo camera system and an object in the system's field-of-view. The stereo camera system can include one or more of various camera or sensor technologies, including infrared or near-infrared, thermal imaging, or visible light. The system can be used to detect objects in the field-of-view, determine a distance to the object, and estimate the object's size and relative motion.

Abstract: The disclosure provides an image recognition network model training method, including: acquiring a first image feature corresponding to an image set; acquiring a first identity prediction result by using an identity classifier, and acquiring a first pose prediction result by using a pose classifier; obtaining an identity classifier according to the first identity prediction result and an identity tag, and obtaining a pose classifier according to the first pose prediction result and a pose tag; performing pose transformation on the first image feature by using a generator, to obtain a second image feature corresponding to the image set; acquiring a second identity prediction result by using the identity classifier, and acquiring a second pose prediction result by using the pose classifier; and training the generator.

Abstract: A method for identifying potentially hazardous or at-risk objects in the surroundings of a vehicle. The method includes detecting an area of the surroundings using at least one event-based sensor, the event-based sensor including light-sensitive pixels, and a relative change of the light intensity incident upon a pixel by at least a predefined percentage prompting the sensor to output an event assigned to this pixel. The method also includes assigning events output by the sensor to objects in the area; analyzing, for at least one object to which events are assigned, the events assigned to the object with respect to present movements of the object; and ascertaining an impending movement of the object, and/or an impending change of state, of the object from the present movements. An associated computer program is also described.