Automotive Research & Testing Center

Taiwan Semiconductor Manufacturing Comp. Ltd.

Automotive Research & Test Center

Kuo-Ching Chang

Ho-Chun Liou

Hung-Sen Wang

Chuan-Ren Li

Wei-Sho Hung

Shih-Chi Yang

Li-Chen Fu

Pei-Yung Hsiao

Yu-Sheng Liao

Yi-Ming Chan

Chih-Hung Yang

Hsuan-Yu Huang

Han-Wen Huang

Zhen-Wei Zhu

Pang-Ting Huang

A hierarchical system for detecting an object with parallel architecture and a hierarchical method thereof is disclosed. The system includes at least one image-retrieving device retrieving at least an image and searching a plurality of obstacle position images in it. The image-retrieving device is electrically connected with an image-processing device to receive the obstacle position images transmitted by the image-retrieving device, uses parallel architecture classification to obtain at least one object image and a plurality of cropping frames thereof from the obstacle position images, synchronously separates the cropping frames to retrieve characteristic values of each cropping frame, uses convolutional neural network to simultaneously recognize the characteristic values of each cropping frame, and searches and outputs the correct cropping frame from the object image, thereby immediately detecting the object outside a vehicle and obtaining the cropping frame of the object to avoid detection error.

Hierarchical system for detecting object with parallel architecture and hierarchical method thereof

A target object detection system includes a detection unit and a machine learning unit. The detection unit obtains an image and outputs a notification signal upon determining that a portion of the image resembles a target object by performing a classification operation. The machine learning unit performs a training operation using the image to obtain new weak classifier parameters for update in the detection unit when a determination made using weak classifier parameters used in the classification operation of the detection unit differs from one made using strong classifier parameters.

Target object detection system and a method for target object detection

A calibration method for merging object coordinates and a calibration board device using the same are provided. The calibration board device has a plurality of characteristic points and a central reflection element. A center of the central reflection element has a central characteristic point. A distance sensor emits a distance sensing signal to the central reflection element, so as to obtain a central real coordinate. Intrinsic and extrinsic parameters of a camera is used to establish a transformation equation which transforms the central real coordinate into a central image coordinate. Finally, a calibration image of the calibration board device is retrieved, and the central characteristic point is searched, and the central image coordinate is projected on the calibration image whereby the central image coordinate is calibrated to aim at the central characteristic point on the calibration image, thereby generating extrinsic and intrinsic parameter parameters calibrated.

Calibration method for merging object coordinates and calibration board device using the same

A pedestrian detecting system includes a depth capturing unit, an image capturing unit and a composite processing unit. The depth capturing unit is configured to detect and obtain spatial information of a target object. The image capturing unit is configured to capture an image of the target object and recognize the image, thereby obtaining image feature information of the target object. The composite processing unit is electrically connected to the depth capturing unit and the image capturing unit, wherein the composite processing unit is configured to receive the spatial information and the image feature information and to perform a scoring scheme to detect and determine if the target object is a pedestrian. The scoring scheme performs weighted scoring on a spatial confidence and an appearance confidence to obtain a composite scoring value to determine if the target object is the pedestrian.

Pedestrian detecting system

An integrated circuit and a method of fabricating the integrated circuit are provided. In various embodiments, the integrated circuit includes a substrate and a polysilicon resistor. The polysilicon resistor is disposed on the substrate. The polysilicon resistor has at least one positive TCR portion and at least one negative TCR portion. The positive TCR portion is adjacent to the negative TCR portion, and the positive TCR portion is in direct contact with the negative TCR portion.

Integrated circuit and method of fabricating the same

An object detection method with a rising classifier effect is embedded in an object detection device and has steps of acquiring image information; determining a position of an obstacle in the image information, wherein the image information is detected for generation of an extracted range corresponding to the obstacle; recognizing an extracted contour of the obstacle, wherein the extracted contour of the obstacle associated with the extracted range is obtained by using an algorithm for Poisson gradient vector flow based active deformable contour model and a multi-mesh algorithm with different grid sizes; and forming a maximum border of the extracted contour of the obstacle for a classifier to recognize a type of the obstacle according to the maximum border of the obstacle. Accordingly, the object detection method is advantageous in complete extraction, higher recognition rate, faster computation and feasibility to be integrated with vehicle systems.

Object detection method with a rising classifier effect and object detection device with the same

Growing community of inventors

Changhua County, Taiwan

Kuo-Ching Chang