Samsung Electronics Co., Ltd.

Ajou University Industry-Academic Cooperation Foundation

Beijing Samsung Telecom R&d Center

Hyunku Lee

Hyunsurk Eric Ryu

Keun Woo Park

JOngseok Seo

Junseok Kim

Jooyeon Woo

Yohan J Roh

Heejae Jung

Qiang Wang

Jin-Man Park

Weiheng Liu

Jia Qi Li

Eric Hyunsurk Ryu

Feng Shi

Junhyuk Park

Ha Young Kim

Dongqing Zou

Keun Joo Park

Yinlong Qian

Keunjoo Paul Park

BaRom Kang

An image processing device includes a vision sensor and a processor. The vision sensor generates a plurality of events in which an intensity of light changes and generates a plurality of timestamps depending on times when the events occur. In addition, the processor may regenerate a timestamp of a pixel where an abnormal event occurs, based on temporal correlation of the events.

Image processing device configured to regenerate timestamp and electronic device including the same

A vision sensor includes a pixel array comprising pixels arranged in a matrix, an event detection circuit, an event rate controller, and an interface circuit. Each pixel is configured to generate an electrical signal in response to detecting a change in incident light intensity. The event detection circuit detects whether a change in incident light intensity has occurred at any pixels, based on processing electrical signals received from one or more pixels, and generates one or more event signals corresponding to one or more pixels at which a change in intensity of incident light is determined to have occurred. The event rate controller selects a selection of one or more event signals corresponding to a region of interest on the pixel array as one or more output event signals. The interface circuit communicates with an external processor to transmit the one or more output event signals to the external processor.

Vision sensors, image processing devices including the vision sensors, and operating methods of the vision sensors

Provided is a vision sensor including a pixel array including a plurality of pixels disposed in a matrix form, an event detection circuit configured to detect whether an event has occurred in the plurality of pixels and generate event signals corresponding to pixels from among the plurality of pixels in which an event has occurred, a map data processor configured to generate a timestamp map based on the event signals, and an interface circuit configured to transmit vision sensor data including at least one of the event signals and the timestamp map to an external processor, wherein the timestamp map includes timestamp information indicating polarity information, address information, and an event occurrence time of a pixel included in an event signal corresponding to the pixel.

Vision sensor, image processing device including the same, and operating method of the vision sensor

Vision sensor, image processing device including the vision sensor, and operating method of the vision sensor

An image processing method including: capturing changes in a monitored scene; and performing a sparse feature calculation on the changes in the monitored scene to obtain a sparse feature map.

Image processing method, an image processing apparatus, and a surveillance system

Disclosed is a computer-readable medium including a program code that, when executed by processing circuitry, causes the processing circuitry to generate a feature map from an input image, to extract a region of interest from the feature map, and to generate a predicted mask based on the region of interest. The processing circuitry may use a predicted mask and a real mask to learn a convolutional neural network system. The real mask includes first pixels corresponding to the real boundary and second pixels corresponding to a fake boundary adjacent to the real boundary.

Convolutional neural network for object detection

An object detection method and a neural network system for object detection are disclosed. The object detection method acquires a current frame of a sequence of frames representing an image sequence, and extracts a feature map of the current frame. The extracted feature map is pooled with information of a pooled feature map of a previous frame to thereby obtain a pooled feature map of the current frame. An object is detected from the pooled feature map of the current frame. A dynamic vision sensor (DVS) may be utilized to provide the sequence of frames. Improved object detection accuracy may be realized, particularly when object movement speed is slow.

Object detection method and system

Provided is an event signal processing method and apparatus. The event signal processing method includes acquiring, from an event based sensor, coordinates of an active pixel corresponding to an event and a timestamp corresponding to the event; mapping the event to a target voxel included in a three-dimensional (3D) grid based on the coordinates of the active pixel and the timestamp; and updating a value of the target voxel based on the event.

Event signal processing method and apparatus

An event signal processing method and an event-based sensor performing the event signal processing method are provided. The event signal processing method includes receiving an activation signal to indicate sensing of an event from a sensor array, increasing the cumulative event number of a sensing area corresponding to the activation signal among sensing areas of the sensor array, reducing the cumulative event number of each of the sensing areas based on a parameter; and determining, as a flickering area, a sensing area among the sensing areas, of which the cumulative event number exceeds a threshold.

Method for processing event signal and event-based sensor performing the same

Growing community of inventors

Suwon-si, South Korea

Hyunku Lee