Automotive Research & Testing Center

Automotive Research & Test Center

Yi-Feng Su

Yu-Sung Chen

Chia-Tseng Chen

Tsung-Hua Hsu

Chun-Hsiung Chen

Hsueh-Lung Liao

Jin-Yan Hsu

Ying-Ren Chen

Ming-Hung Li

Chi-Chun Yao

Tzu-Chien Hsu

Rong-Terng Juang

Yun-Ling Chang

Jia-Xiu Liu

Jui-Hung Wu

Jing-Fu Liu

Tian-Li Wang

Chu-Yuan Hsu

Shung-Huang Chen

Yu-Long Chang

Chia-Hao Yang

Yu-Hsiang Wu

Ming-Feng Hsieh

Zi-Rong Ding

Meng-Jiang He

A method for detecting an interior condition of a vehicle is provided to use a camera device and a radar device to acquire images and point cloud datasets with respect to an interior space of the vehicle. A computing device generates a synthesized image based on the images and the point cloud datasets, obtains a skeleton feature dataset and a facial feature dataset with respect to a living object in the synthesized image, and determines the interior condition of the vehicle based on the skeleton feature dataset and the facial feature dataset.

Method for detecting an interior condition of a vehicle, and system implementing the same

An object detection method includes steps that are to be performed for each piece of point cloud data received from a lidar module, of selecting a first to-be-combined image from among images received from a camera device that corresponds in time to the piece of point cloud data, selecting a second to-be-combined image from among the images that is the Nimage before the first to-be-combined image in the time order, combining the first to-be-combined image and the second to-be-combined image to generate a combined image, generating a result image by incorporating the piece of point cloud data into the combined image, and inputting the result image into a trained machine learning model in order to determine a class to which each object in the result image belongs.

Object detection method

A positioning system for positioning a to-be-positioned device includes three or more reference objects each providing individual unique feature information associated with a two-dimensional coordinate. A positioning device includes an image capturing unit obtaining image data of three of the reference objects, and a processing unit obtaining, based on the image data, three pixel positions corresponding respectively to the three reference objects in the image data, obtaining the two-dimensional coordinate of the location of the three reference objects, and estimating a positioning coordinate of the to-be-positioned device using a triangulation positioning method based on the three pixel positions, a focal length used for obtaining the image data and the two-dimensional coordinates.

Positioning system using triangulation positioning based on three pixel positions, a focal length and the two-dimensional coordinates

An automatic correction device of a vehicle display system and method thereof, comprising following steps: firstly, transform an image of road in front into projection information, to calculate a coordinate model, then detect facial features of a driver, to calculate a face rotation angle and a facial features 3-D position of said driver, to estimate a position field of view for said driver looking to front. Then, said position field of view is substituted into an image overlap projection transformation formula, to generate an overlap error correction parameter. Subsequently, utilize said overlap error correction parameter to correct and update said coordinate model. Finally, utilize a display unit to project said corrected coordinate model to front of said driver, so that projection position of said coordinate model overlaps said position field of view of said driver.

Automatic correction device of vehicle display system and method thereof

The present invention proposes a system and method for preventing a vehicle from rolling over in curved lane. The road images captured by the image capture devices are used to calculate road information. The road information together with the vehicular dynamic information, such as the speed and acceleration of the vehicle are used to predict the rollover angle and lateral acceleration of the vehicle moving on the curved lane. The height of the gravity center and critical rollover speed of the vehicle moving on the curved lane are worked out and used to define a vehicular rollover index. If the vehicular rollover index exceeds a preset value, the system warns the driver or directly controls the speed of the vehicle to prevent the vehicle from rolling over in the curved lane.

System and method for preventing vehicle from rolling over in curved lane

An autonomous driver assistance system is integrated with a vehicular control system to constantly detect ambient road environment of the vehicle, identify a vehicle ahead with same driving route to a destination, and follow the vehicle ahead by autonomous driving to the destination. Signals of direction indicators of the vehicle ahead can be recognized to determine a driving direction and driving state of the vehicle ahead beforehand, thereby reducing the chances of emergency brake and collision and increasing driving efficiency. Without expensive radar detection equipment, the present invention can be easily integrated with a vehicular control system to tackle the high installation cost and integration difficulty of conventional autonomous driver assistance apparatuses.

Autonomous driver assistance system and autonomous driving method thereof

An intuitive eco-driving assistance system is mounted on a vehicle and has an input module, a control module and an output module. The control module is electrically connected to the input module and the output module. The output module acquires images ahead of the vehicle and speed signals for the control module to recognize a speed limit, traffic lights and a speed and distance of any obstacle on the images. Furthermore, according to the driving limits of the road and actual vehicle speed, the output module prompts for an eco-driving instruction and the speed limit meeting the road condition visually or audibly. Accordingly, the issue of conventional vehicles being structurally complicated and costly for conserving energy, only passively prompting fuel consumption, and consuming more fuel can be solved without requiring any additional and complicated system.

Intuitive eco-driving assistance method and system

The present invention discloses an image-based barrier detection and warning system and a method thereof, wherein an image processing technology is used to establish ROI and verify whether a horizontal line signal exists, and wherein the image processing technology determines whether an object is a barrier via detecting contours of an object and detecting distance to the object, and wherein the system timely outputs warning signals and presents distance to a barrier when detecting the barrier. The image-based barrier detection and warning system enables the driver to watch the surroundings of the vehicle directly and clearly and learn the relative positions of barriers, whereby the driver can park more easily and safely.

Image-based barrier detection and warning system and method thereof

The present invention discloses a dual-vision driving safety warning device and a method thereof. The device of the present invention comprises an image capture unit, an image processing unit, a vehicle status sensing unit, a warning judgment logic, and at least one warning unit. The image capture unit includes at least two image capture devices installed in a user's vehicle and capturing the images of the front traffic environment. The image processing unit processes the images and uses the vehicle status signals detected by the vehicle status sensing unit to calculate the distance between the user's vehicle and a front vehicle in the image. The warning judgment logic sends out a control signal when the user's vehicle deviates from a driving lane or approaches a front vehicle too much. The warning unit receives the control signal and sends out a warning signal, such as a sound or a flash, to remind the driver.

Dual-vision driving safety warning device and method thereof

The present invention discloses a vehicular tilt-sensing method and an automatic headlight leveling system using the same. The method of the present invention comprises steps: using an image capture device to capture an image of the road and obtain at least one instantaneous lane marking line from the image; extending the instantaneous lane marking lines afar to obtain an instantaneous vanishing point; establishing an instantaneous horizontal line passing through the instantaneous vanishing point; calculating from the image the displacement between a datum horizontal line and the instantaneous horizontal line; and calculating the tilt angle with the displacement and the focal length of the image; using the tilt angle to generate a control signal to control level adjusting controllers to adjust headlights, whereby the headlights can provide optimized illumination to enhance night driving safety on a rugged road or in the case that the vehicle is unevenly loaded.

Vehicular tilt-sensing method and automatic headlight leveling system using the same

A vehicle rollover prevention safety driving system, comprising: at least an image sensor, used to fetch road images in front of said vehicle; an image processor, connected to said image sensor, and is used to identify a drive lane in road images, and calculate a drive lane curvature, an inclination angle of said road, and relative positions of said vehicle and a lane marking; a vehicle conditions sensing module, used to sense dynamic information of a vehicle turning angle, a vehicle inclination angle, and a vehicle speed; a microprocessor, connected to said image processor and said vehicle conditions sensing module, and it calculates a rollover prediction point and a rollover threshold speed, and it issues a corresponding warning signal or a control signal; and an accelerator and brake controller, connected to said microprocessor, and it controls deceleration of said vehicle according to said control signal.

Vehicle roll over prevention safety driving system and method

A method for detecting the lane departure of a vehicle includes an image recognition process and a deviation estimation process. The image recognition process includes the following steps: an image capturing step for capturing image frame data by using an image capturing unit; and a lane line recognition for analyzing the image frame data for determining the lane lines. By using a quadratic curve fitting equation, a plurality of lane line being detected so as to establish a road geometry estimation model. The road geometry estimation model is inputted into the deviation estimation process to detect the lane departure of the vehicle so as to alert the driver. Furthermore, an apparatus for detecting the deviation of the vehicle, comprising: an image capturing unit, a processing unit and a signal output unit.

Growing community of inventors

Changhua County, Taiwan

Yi-Feng Su