Institute for Information Industry

National Taipei University of Technology

Hua-chuang Automobile Information Technical Center Co., Ltd.

Chao-Wei Yu

Yen-Lin Chen

Meng-Tsan Li

Chuan-Yen Chiang

Augustine Tsai

Chien Lin

Hsin-Han Chiang

Hsiu-Chih Chen

Chieh-Min Chang

Ming Chen

Chung-Yuan Chang

Hong-Yi Liang

Kuan-Kai Liao

Xiu-Zhi Chen

Cheng-Lung Jen

Yang-Lang Chang

Wen-Yew Liang

A traffic condition prediction system and a traffic condition prediction method are disclosed. The method includes: determining a center of circle in a surveillance image of a target traffic scene; determining a first circle based on the center of circle and a first radius; extracting a plurality of first feature points along the circumference of the first circle according to a first preset sampling frequency; generating a scene feature of the target traffic scene at least based on the first feature points; determining whether the scene feature and a scene feature of another traffic scene are similar; and when determining that they are similar, predicting traffic condition of the target traffic scene through a prediction model used for predicting traffic condition of the other traffic scene. The scene feature of the target traffic scene and that of the other traffic scene are generated in a same way.

Traffic condition prediction system and traffic condition prediction method

A computing device divides a training image into a plurality of training blocks, and the training image includes a training object. The computing device calculates, for each of the training blocks, a correct confidence score of the training object covering the training block according to an image-marking data and a confidence-score-translating function, and the image-marking data includes a piece of location information of the training object in the training image. Then, the computing device trains a deep-learning model with the training image, the correct confidence scores and the image-marking data to generate the object-detecting model.

Computing device and method for generating an object-detecting model and object-detecting device

A feature determination apparatus and method adapted to multiple object sizes are provided. The apparatus individually supplies each of the object images to a convolution neural network having several convolution layers to generate multiple feature maps corresponding to each object image. The apparatus calculates a feature amount of each feature image of each object image. The apparatus determines an invalid layer start number of each object image according to a preset threshold and the feature amount corresponding to each object image. The apparatus determines a feature map extraction recommendation for each of a plurality of object sizes according to a size of each object image and the invalid layer start number of each object image.

Feature determination apparatus and method adapted to multiple object sizes

A method for detecting one or more objects adjacent to a vehicle includes capturing a image of an object adjacent to the vehicle; determining a driving area in the image; cutting the driving area to form an identification window; selecting an identification area in the identification window; accessing a plurality of object image data in a memory to compare the plurality of object image data with the identification area; and identifying a specific object in the identification area by the processor.

Method and system for detecting object(s) adjacent to vehicle

A vehicle detecting detection assisting method and a vehicle detection assisting system are provided. The vehicle detection assisting method includes the following steps. A scanning range of a lidar unit is obtained. A width of a lane is obtained. A trace of the lane is obtained. A dynamic region of interest in the scanning range is created according to the width and the trace.

Vehicle detection assisting method and vehicle detection assisting system

An image annotation method includes the following. Image frames are acquired. One or more target objects are identified and tracked from the image frames. Candidate key image frames are selected from the frames according to a first selection condition. First similarity indexes of the candidate key image frames are determined. Second similarity indexes of a plurality of adjacent frames are determined. The candidate key image frames as well as the adjacent frames that meet a second selection condition are selected as key image frames. The key image frames are displayed on a graphical user interface. Annotation information about the one or more target objects is display through the graphical user interface.

Method, electronic device and non-transitory computer readable storage medium for image annotation

A system of detection, tracking and identification of an evolutionary adaptation of a vehicle lamp includes an image capture device and a processor. The image capture device captures an image of a vehicle. The processor processes the image of the vehicle to generate a detection result of the vehicle lamp, analyzes and integrates vehicle lamp dynamic motion information and vehicle lamp multiple scale variation information based on the detection result, and then tracks the position of the vehicle lamp by applying a multiple scale vehicle lamp measurement model.

System and method of detection, tracking and identification of evolutionary adaptation of vehicle lamp

A multi-class object classifying method and system are disclosed herein, where the multi-class object classifying method includes the following steps: classes, first training images and second training images are received and stored, and first characteristic images and second characteristic images are respectively extracted from the first training images and the second training images; the first training images is used to generate classifiers through a linear mapping classifying method; a classifier and the second characteristic images are used to determine parameter ranges corresponding to the classes and a threshold corresponding to the classifier. When two of the parameter ranges overlap, the remaining parameter ranges except for the two overlapped parameter ranges are recorded; after another classifier is selected from the classifiers except for the classifier that has been selected, the previous steps is repeated until the parameter ranges don't overlap with each other and the parameter ranges are recorded.

Multi-class object classifying method and system

The present invention discloses a multi-touch sensing system capable of optimizing touch bulbs according to the variation of ambient lighting conditions and a method thereof. The system comprises an image capturing module, a computing module and a processing module. The image capturing module captures a touch image. The computing module converts the touch image into a histogram and selects a grayscale threshold to segment the histogram by dichotomy for generating a segmented image of touch bulbs, and then calculates a between-class variance and a total pixel variance of the segmented image to estimate the separability factor thereof. The processing module determines whether or not the separability factor conforms to a predetermined value; if yes, then the processing module performs an image binarization of the touch image to generate a binary image, or else the processing module repeats the aforementioned process until the separability factor conforms to a predetermined value.

Multi-touch sensing system capable of optimizing touch bulbs according to variation of ambient lighting conditions and method thereof

The present invention is directed to a guide system having a function of a real-time voice response for the visually impaired and a method thereof. The guide system responds road conditions in real time using two processing modules performing image processing and voice responses, respectively. The guide system includes an visual sensing module sensing an image, a memory storing multiple training samples and multiple pieces of audio response information, an image processing module performing an image detection process to the image so as to create at least a segmented image, performing an object detection process to the segmented image, and performing an object recognition process so as to create a recognition signal, a system processing module creating an audio signal based on the recognition signal such that a speech voice is hearable by a user.

Growing community of inventors

Pingtung County, Taiwan

Chao-Wei Yu