Samsung Electronics Co., Ltd.

Qualcomm Incorporated

Chung Ang University Industry Academic Cooperation

Chung-aug University Industry-academy Cooperation

Hee-Seok Lee

Yong-hoon Kim

Yun-seok Choi

Duck Hoon Kim

Seungwoo Yoo

Eun-seok Song

Hyun-Mook Cho

Kyung-Lae Jang

Heesoo Myeong

Eun-Seok Song

Se-Ho You

Donghan Kim

Kang Min Kim

Yun-Hee Lee

Chul-Woo Kim

Young-Ki Baik

Ye-chung Chung

Seong-Ho Shin

Na-rae Shin

Chan Won Lee

Keung-beum Kim

Young-Sang Cho

Jeong-Kyun Lee

ChaeSeong Lim

Jin-ha Jeong

Hyuk-Hwan Song

So-young Lim

Jihoon Kim

Sung-woo Park

Young-Don Choi

Jin-Ho Lee

Ji-Yong Park

Young-Bae Kim

Heung-Kyu Kwon

Seung-Hwan Kim

Yong-Hoon Kim

Jong-joo Lee

Ji-hyun Lee

Jae-Wook Yoo

Jae-Jin Park

Kwang-Jin Bae

Kyoung-sei Choi

Kyol Park

Jin-Ha Jeong

Byeong-yeon Cho

Sang-Gui Jo

Sungwoong Kim

Hyo-Soon Kang

Yun-hyeok Im

Kang-Yeop Choo

Tae-je Cho

Ki-Won Choi

Jang-Ho Cho

Jeong-Oh Ha

Sung-hwan Min

Seok-Soo Hong

Ji-Hwan Hyun

Bok-Sik Myung

Byeong-Yeon Cho

Sang-Youb Lee

Yun-Hyoek Im

Kyung-Tae Na

Chan Lee

Disclosed are techniques for estimating a 3D bounding box (3DBB) from a 2D bounding box (2DBB). Conventional techniques to estimate 3DBB from 2DBB rely upon classifying target vehicles within the 2DBB. When the target vehicle is misclassified, the projected bounding box from the estimated 3DBB is inaccurate. To address such issues, it is proposed to estimate the 3DBB without relying upon classifying the target vehicle.

Bounding box estimation and object detection

Certain aspects of the present disclosure provide techniques for lane marker detection. A set of feature tensors is generated by processing an input image using a convolutional neural network. A set of localizations is generated by processing the set of feature tensors using a localization network, a set of horizontal positions is generated by processing the set of feature tensors using row-wise regression, and a set of end positions is generated by processing the set of feature tensors using y-end regression. A set of lane marker positions is determined based on the set of localizations, the set of horizontal positions, and the set of end positions.

Lane marker recognition

Certain aspects of the present disclosure provide a method for lane marker detection, including: receiving an input image; providing the input image to a lane marker detection model; processing the input image with a shared lane marker portion of the lane marker detection model; processing output of the shared lane marker portion of the lane marker detection model with a plurality of lane marker-specific representation layers of the lane marker detection model to generate a plurality of lane marker representations; and outputting a plurality of lane markers based on the plurality of lane marker representations.

Lane marker detection

Disclosed are techniques for performing lane instance recognition. Lane instances are difficult to recognize since they are long and elongated, and they also look different from view to view. An approach is proposed in which local mask segmentation lane estimation and global control points lane estimation are combined.

Lane marker detection and lane instance recognition

Certain aspects of the present disclosure are directed to methods and apparatus for deep learning in an artificial neural network. One example method generally includes receiving input data at an input to a layer of the neural network; replicating a group of neural processing units in the layer to form a superset of neural processing units, the superset comprising n instances of the group of neural processing units; processing the input data using the superset to generate output data for the layer; and determining an uncertainty of the output data. Processing the input data includes performing a dropout function by zeroing out one or more weights of a set of weights for each of the n instances of the superset of neural processing units and convolving, for each of the n instances in parallel, the input data with one or more non-zeroed out weights of the set of weights.

Efficient dropout inference for bayesian deep learning

A method for capturing an image of a traffic sign by an image sensor is disclosed. The method may include capturing, by the image sensor, at least one image including the traffic sign, wherein the image sensor is mounted in a vehicle. The method may include detecting, by a processor, the traffic sign in the at least one image. The method may also include in response to detecting the traffic sign, determining, by the processor, at least one direction of the image sensor based on the at least one image and motion of the vehicle. In addition, the method may include adjusting, by the processor, the image sensor to the at least one direction.

Method and device for capturing image of traffic sign

A method, a computer-readable medium, and an apparatus for object detection are provided. The apparatus may determine a regression vector using a neural network based on an input image that contains an object. The object may have a planar surface with a known shape. The apparatus may derive a transform matrix based on the regression vector. The apparatus may identify a precise boundary of the object based on the transform matrix. The precise boundary of the object may include a plurality of vertices of the object. To identify the boundary of the object, the apparatus may apply the transform matrix to a determined shape of the object.

Simultaneous object detection and rigid transform estimation using neural network

According to example embodiments, an image display panel assembly includes a flexible printed circuit (FPC), an image display panel, at least one gate driver integrated circuit (IC) package, and at least one source driver IC package. The FPC is configured to receive gate and source driving signals. The image display panel is electrically connected to the FPC, and includes a gate driving signal transfer pattern along a first edge of the image display panel, a source driving signal transfer pattern along a second edge adjacent to the first end, and a plurality of pixels. The at least one gate driver integrated circuit (IC) package is configured to receive the gate driving signal through the gate driving signal transfer pattern and configured to provide the gate driving signal to gate lines of the plurality of pixels. The at least one source driver IC package is configured to receive the source driving signal through the source driving signal transfer pattern and configured to provide the source driving signal to source lines of the plurality of pixels.

Source driver, an image display assembly and an image display apparatus

A method, which is performed by an electronic device, for resizing an image having text is disclosed. The method may include determining layout information of at least one text region in the image. The layout information may include at least one of a number, a size, a location, a shape, or a text density of the at least one text region in the image. The method may also select a seam carving operation, a cropping operation, or a scaling operation for the image based on the layout information, a size of the image, and a target image size. The selected operation may be performed to resize the image to the target image size based at least on one of the layout information, the size of the image, or the target image size. The resized image may include the at least one text region.

Text-based image resizing

A method, which is performed by an electronic device, of automatically activating a flash for an image sensor of the electronic device is disclosed. The method may include receiving a first image including at least one text region and determining feature data characterizing the at least one text region in the first image. The method may also identify at least one candidate specular reflection region in the first image. Based on the feature data and the at least one candidate specular reflection region, the flash may be activated. Upon activating the flash, a second image including the at least one text region may be captured.

Activating flash for capturing images with text

An image display panel assembly includes a flexible printed circuit (FPC), an image display panel, a gate driver integrated circuit (IC) package, and a source driver IC package. The FPC is configured to receive gate and source driving signals. The image display panel is electrically connected to the FPC, and includes a gate driving signal transfer pattern along a first edge of the image display panel, a source driving signal transfer pattern along a second edge adjacent to the first end, and a plurality of pixels. The gate driver integrated circuit (IC) package is configured to receive the gate driving signal through the gate driving signal transfer pattern and provide the gate driving signal to the plurality of pixels. The source driver IC package is configured to receive the source driving signal through the source driving signal transfer pattern and provide the source driving signal to the plurality of pixels.

A stacked package structure is provided. The stacked package structure includes a stacked package including a lower semiconductor package, an upper semiconductor package disposed on the lower semiconductor package and spaced a predetermined distance apart from the lower semiconductor package, an inter-package connecting portion electrically connecting the lower semiconductor package and the upper semiconductor package while supporting a space therebetween, and an insulation layer disposed at least outside the inter-package connecting portion and filling the space between the lower semiconductor package and the upper semiconductor package, and an electromagnetic shielding layer surrounding lateral and top surfaces of the stacked package.

Stacked package structure and method of forming a package-on-package device including an electromagnetic shielding layer

A semiconductor chip including a substrate, a first data pad arranged on the substrate, and a first control/address pad arranged on the substrate, wherein the first data pad is arranged in an edge region of the substrate, and the first control/address pad is arranged in a center region of the substrate.

Semiconductor chip and a semiconductor package having a package on package (POP) structure including the semiconductor chip

A semiconductor package includes a substrate in which a plurality of wires are formed; at least one semiconductor chip electrically connected to portions of the plurality of wires; and a shielding can mounted on the substrate, surrounding the at least one semiconductor chip, electrically connected to at least one wire of the plurality of wires and including a soft magnetic material. The semiconductor package can prevent or substantially reduce electromagnetic interference (EMI).

Semiconductor package

Growing community of inventors

Yongin-si, South Korea

Hee-Seok Lee