International Business Machines Corporation

Huawei Technologies Co., Limited

Huawei Device Co., Ltd.

Sheng Nan Zhu

Peng Ji

Guo Qiang Hu

Yuan Yuan Ding

Jian Ding

Fan Li

Jing Chang Huang

Jian Xu

JingChang Huang

Guoqiang Hu

Jinfeng Li

Zhonghua Cai

Lipeng Zhang

Kaizhan Wang

Zhiyuan Pang

Wei Zhao

Dan Zhang

Dongxing Tu

Hong Bing Zhang

Huiliang Xu

Dingjie Wang

Qizhi Zhan

Guangsheng Pan

Tian Tian Chai

Wei Jiao

Zhaoliang Yang

Provided is a vehicle-mounted fragrance holder comprising a connecting device, a holder body, a movable piece, a first elastic element, a first articulated piece, a second elastic element, and a second articulated piece. The holder body is arranged on the connecting device for fixation within the vehicle, and the connecting device. The holder body is used for accommodating a fragrance and provided with a louver. One end of the second articulated piece is a first abutting end for abutting against the louver to push it open when the second articulated piece rotates forward, while the other end is a second abutting end. The second articulated piece is articulated within the holder body, and the first articulated piece is articulated within the holder body and located between the movable piece and the second abutting end of the second articulated piece. The movable piece is movably mounted on the holder body.

Vehicle-mounted fragrance holder

Combined car aroma diffuser and phone holder

A plurality of different images of a same region of interest in an object are input into a set of neural networks, wherein each image of the region has been captured under a different value of a variable condition. A classification for each image is generated by the set of neural networks, wherein each classification includes a confidence score in a prediction of whether a feature is present in the region. The image classifications are ensembled to generate a final classification for the region. By applying a loss function, a loss is computed based on comparing the final classification to a ground truth of whether the feature is present in the region. The parameters of the set of neural networks are adjusted based on the computed loss.

Feature detection based on neural networks

A method for detecting and labeling a target object in a 2D image includes receiving a plurality of 2D images from a visual sensor, manually marking points of the target object on each of the 2D images, generating from the 2D images a 3D world coordinate system of the environment surrounding the target object, mapping each of the marked points on the 2D images to the 3D world coordinate system using a simultaneous localization and mapping (SLAM) engine, automatically generating a 3D bounding box covering all the marked points mapped to the 3D world coordinate system, mapping the 3D bounding box to each of the 2D images, generating a label for the target object on each of the 2D images using a machine learning object detection model, and training the machine learning object detection model based on the generated label for the target object.

AR-based labeling tool for 3D object detection model training

A system, method, and computer program product provides a way to separate connected or adhered adjacent characters of a digital image for license plate recognition. As a threshold processing, the method performs a recognition of character adhesion by obtaining character parameters using an image processor. The parameters include a horizontal max crossing and a ratio of width and height. A first rule-based module is used responsive to the character parameters to distinguish the adhered characters (character adhesions) that are easy to judge, leaving the uncertain part to a character adhesion classifier model for discrimination. Character adhesion data is obtained by data augmentation including the adding of a random distance between two single characters to create class like adhered characters. Then the character adhesion classifier model of single character and character adhesion data is trained. Any uncertain part can be distinguished by the trained character adhesion classifier model.

Character recognition of license plate under complex background

The present invention relates to a method, system and computer program product for defect enhancement. According to the method, a plurality of proposed regions from a plurality of images taken for a display panel is obtained. Each of proposed region of the plurality of proposed regions include a suspected defect on the display panel. At least two proposed regions from the plurality of proposed regions that deserve to be superimposed based on a set of conditions is determined. The at least two proposed regions for acquiring an enhanced defect are superimposed.

Display panel defect enhancement

In an approach for object detection with missing annotations under visual inspection, a processor receives an image. A processor classifies the image being a not-good image using a pre-trained classifier. A not-good image means one or more defect objects being in the image. A processor, in response to classifying the image being the not-good image, detects the one or more defect objects in the not-good image. A processor masks the one or more defect objects in the not-good image. A processor inputs the masked image to train a detector.

Object detection with missing annotations in visual inspection

The present disclosure relates to training a machine learning model to classify images. An example method generally includes receiving a training data set including images in a first category and images in a second category. A convolutional neural network (CNN) is trained using the training data set, and a feature map is generated from layers of the CNN based on features of images in the training data set. A first area in the feature map including images in the first category and a second area in the feature map where images in the first category overlap with images in the second category are identified. The first category is split into a first subcategory corresponding to the first area and a second subcategory corresponding to the second area. The CNN is retrained based on the images in the first subcategory, images in the second subcategory, and images in the second category.

Classifying images in overlapping groups of images using convolutional neural networks

A method, a device and a computer program product for image processing are proposed. In the method, a first training image and region information are obtained. The region information indicates a region of a defect in the first training image. A second training image with the defect at least partially removed is generated using an image generator based on the first training image and the region information. The image generator is trained to recover the first training image by replacing pixels included in the region indicated by the region information. The image generator is updated based on the second training image. In this way, the image including the defect can be accurately and efficiently recovered.

Image recovery

A method, a device and a computer program product for image processing are proposed. In the method, whether a first image indicates a defect associated with a target object is determined. In response to determining that the first image indicates the defect, a second image absent from the defect is obtained based on the first image. The defect is identified by comparing the first image with the second image. In this way, the defect associated with the target object in the image can be accurately and efficiently identified or segmented.

Image defect identification

A computer implemented method for surface defect inspection that includes recording an optical image of a surface including a defect; converting the optical image including the defect into a heat map; extracting a region of interest including the defect from the heat map; and comparing the region of interest including the defect from the heat map to a binary classification model using a sliding window based voting mechanism to determine if the defect is greater than or less than a threshold failure value.

Efficient defect localization/segmentation for surface defect inspection

Embodiments of the present invention provide a power amplifier, a radio remote unit RRU, and a base station. A multiphase pulse width modulator performs modulation to generate N multiphase pulse-width modulation PWM signals. The multiphase pulse-width modulation PWMn signal may be amplified. The multiphase pulse-width modulation PWMn signal may be filtered and a combination may be performed at a drain or a collector of a power amplifier transistor. According to the new radio frequency amplifier in accordance with the disclosure, envelope feeding loop inductance can be effectively reduced, so that video bandwidth is increased and DPD correction performance is improved.

Power amplifier, radio remote unit, and base station

A power amplifier control method is disclosed. A phase modulation control signal may be generated according to an envelope signal that is output by a baseband unit. The phase modulation may be performed on a signal of a main power amplifier link and/or an auxiliary power amplifier link in the Doherty power amplifier circuit according to the phase modulation control signal, so that a phase difference between the signal of the main power amplifier link and the signal of the auxiliary power amplifier link after the phase modulation is a specified value corresponding to a current value of the envelope signal, where the specified value is an optimal phase value of a Doherty power amplifier circuit when the supply voltage of the Doherty power amplifier circuit is an envelope voltage corresponding to the current value of the envelope signal. High-efficiency power amplifier technology is realized.

Power amplifier control method and apparatus, and power amplifier control system

A USB connector, a PCB connected to the USB connector, and a USB device are provided. The USB connector includes a metal surface, and on the metal surface, a solid metal part is set at a location corresponding to a spring of a socket, so that the spring contacts the solid metal part after the USB connector is inserted into the socket to reduce electromagnetic interference. The USB connector may include an in-line weld leg; a metal enclosure located at the same side as the in-line weld leg fully contacts a PCB when the USB connector is connected to the PCB; and contact surfaces on the USB connector that contact the PCB are metal surfaces. The PCB includes a suppression circuit configured to suppress harmonic waves in USB data transmission.

USB connector, PCB connected thereto, and USB device

An improved Universal Serial Bus (USB) connector apparatus is provided. In one embodiment, the USB connector apparatus comprises a top wall; a bottom wall having one or two openings; two side walls; an internal cavity with a rectangular cross section enclosed by the top wall, the bottom wall and the two side walls; a gasket disposed within the internal cavity; and a first connecting piece made of a conductive material and positioned at the one or more openings of the bottom wall and at least partially covering the one or more openings of the bottom wall, wherein the top wall, bottom wall, two side walls, internal cavity and gasket are configured to comply with a USB interface standard. The USB connector apparatus ensures that a bottom wall elastic sheet of the USB socket effectively contacts with the bottom wall of the USB connector, thereby providing higher grounding performance. Further, it improves on the conventional USB connector without much additional cost.

Growing community of inventors

Shanghai, China

Sheng Nan Zhu