National Yang Ming Chiao Tung University

Academia Sinica

Throughtek Co., Ltd.

Throughtek Technology (shenzhen) Co., Ltd.

Kaohsiung Chang Gung Memorial Hospital

Yong-Sheng Chen

Jen-Hui Chuang

Mu-Tien Lu

Kai-Ying Lin

Yu-Chih Liu

Yi-Ping Hung

Wei-Che Lin

Yung-Cheng Cheng

Evelyne Calista

Shih-Yen Lin

Yu-Lin Yeh

Pi-Ling Chiang

Hsiang-Chun Yang

In an automated detection system for acute ischemic stroke, a preprocessor performs registration on a whole-brain image and a standard-brain spatial template to extract individual brain region masks from the whole-brain image. A deep learning encoder performs feature extraction on the whole-brain image and the individual brain region masks, thereby converting the whole-brain image into 2D whole-brain slice images. A first processor maps the individual brain masks onto the whole-brain slice images for registration, thereby generating sets of brain region slice images. A second processor computes the stroke-related weight values of the slice images of each of the sets of brain region slice images and sums the weight values to obtain the characteristic value of each brain region. A disparity-aware classifier determines whether any brain region has acute ischemic stroke according to the characteristic value of each brain region.

Automated detection system for acute ischemic stroke

A remote wakeup method includes: receiving a wakeup request packet from a first apparatus, obtaining a wakeup information according to the wakeup request packet, generating an apparatus wakeup packet according to the wakeup request packet and the wakeup information, obtaining a connection information corresponding to a second apparatus according to the wakeup request packet, and sending the apparatus wakeup packet to the second apparatus based on the connection information. The wakeup request packet includes a device identifier (UID) of the second apparatus, and the apparatus wakeup packet includes the device identifier of the second apparatus and wakeup information.

Remote wakeup method, connection server, and networking apparatus having sleep mode

A camera principal point automatic calibration system including an image acquiring device, a controller, a first display and a second display is provided, wherein the controller controls the first and second display to display parallel first line and second line. The controller selectively rotates the first and second line according to whether a first and second image line generated by the image acquiring device corresponding to the first and second line are parallel or not, and the controller calculates the principal point from parallel first image line and second image line.

System and method of automatic calibration of principal point

A method for estimating epipolar geometry and to be performed by a processing module includes the steps of: A) choosing, in each first and third images captured by a first image capturing module, two points which are collinear with a corresponding one of a first reference object in the first image and a second reference object in the third image, such that in each second and fourth images captured by a second image capturing module, two points corresponding to the two points chosen in a respective one of the first and third images are collinear with a corresponding one of the first reference object in the second image and the second reference object in the fourth image; and B) determining first and second epipoles based on the aforementioned points.

Method and system for estimating epipolar geometry

Disclosed is an integrated multi-view surveillance system which integrates multiple surveillance camera images of an area into a large-coverage image of the area in order to monitor the area. The system includes a first camera, a second camera, a third camera, an image processing device, and a display device. The image processing device includes a first defining component, a first synthesis component, a second defining component, an adjusting component, a transforming component, a third defining component, and a second synthesis component.

Integrated image surveillance system and image synthesis method thereof

The present invention discloses an image synthesis system for a vehicle to provide the driver with a downward-facing image of the car's 360&#xb0; surrounding view. The system includes: a first camera, which is used to shoot a first image of the periphery of the vehicle; a second camera, which is used to shoot a second image of the periphery of said vehicle, wherein the second image and the first image have an overlap region; an image processing device comprising a defining component and a synthesis component, which is used to synthesize the first image and the second image and output a third image; a display device, which is used to display the third image.

Image synthesis system for a vehicle and the manufacturing method thereof

A method is described that greatly reduces the computational cost of determining the globally optimal match between a template and one or more samples. For every sample in a search range, intermediate distance measures between the template and each sample are first computed in one designated dimension. The computed distance measures are then sorted according to their magnitude. The sample with the minimal distance measure is selected to accumulate a new distance measure in the next higher dimension. This new distance measure is recorded and the samples are sorted again according to the updated distance measures. The above process is repeated until a minimal distance measure has been computed in all dimensions. For motion estimate, this method can reduce the number of computational operations by about 90% to 99%. This method can also provide a list of globally best matches. By sacrificing the global optimality, this method can satisfy the time constraint required by some applications and provide a suboptimal match.

Growing community of inventors

Taipei, Taiwan

Yong-Sheng Chen