National Taipei University of Technology

National Taiwan University

Acer Inc.

Shih-Chia Huang

Sy-Yen Kuo

Bo-Hao Chen

Ming-Kai Jiau

Sheng-Kai Chou

Yan-Tsung Peng

Fan-Chieh Cheng

Yi-Sheng Chiu

Yi-Jui Cheng

Chih-An Hsu

Jian-Hui Ye

Yu-Hsiang Jian

Wei-Jheng Wang

Chih-Hsian Lin

Ben-Hsiang Do

A transportation services providing method and an user device and a server using the same are provided. The transportation services providing method includes following steps: providing a service platform connecting with at least one community website; collecting a status message, related to an event information and posted on the community website, so as to show the collected status messages on the service platform; obtaining an event location of the event information; and establishing a transportation service link on the status message, where the transportation service link provides a transportation service interface indicating the event location and a plurality of transportation requirement settings.

Transportation services providing method and user device and server using the same

A dispatch system for autonomous vehicle is provided. The dispatch system includes a plurality of autonomous vehicles respectively including a communication unit and a control unit. The communication unit obtains a vehicle location information of itself, and communicates with other autonomous vehicles. The control unit obtains a vehicle available information of itself. One of the autonomous vehicles is selected as a dispatch control center for controlling scheduling of all autonomous vehicles. When the dispatch control center receives a transportation request massage, the dispatch control center performs an optimized scheduling assignment and thus generates a scheduling signal. The scheduling signal is transmitted to the other autonomous vehicles by the communication unit, so as to assign one of the autonomous vehicles as a designated vehicle for transportation.

Dispatch system for autonomous vehicles

The invention discloses an image restoration method and an imager processing apparatus using the same. The method includes the following steps: receiving a haze image comprising a plurality of pixels; detecting whether a color cast phenomenon occurs on the haze image; if yes, calculating a plurality of Laplacian distribution values respectively corresponding to the color channels; determining a maximum distribution value and a minimum distribution value among the Laplacian distribution values, and generating a self-adaptive parameter by comparing the maximum distribution value and the minimum distribution value; adjusting the transmission map by the self-adaptive parameter so as to generate a adjusted transmission map; calculating a plurality of color parameters respectively corresponding to the color channels according to the Laplacian distribution values; and restoring the haze image by using the color parameters and the adjusted transmission map so as to obtain a restored image.

Image restoration method and image processing apparatus using the same

A video editing method for a video editing device is provided. The method includes: obtaining an editing segment of a video, wherein the editing segment follows a first segment of the video and precedes a second segment of the video, the first segment includes a first picture, the second segment includes a second picture, and a short-term reference index of the second picture points to the first picture; setting a header of a third picture in the first segment, such that the first picture is moved from a short-term reference picture list to a long-term reference picture list when the header of the third picture is decoded; changing the short-term reference index of the second picture into a long-term reference index, wherein the long-term reference index points to the first picture in the long-term reference picture list; and encoding the video. Accordingly, the speed of editing the video is increased.

Video editing method and video editing device

A method for improving image quality for display device has steps of inputting an image; computing a probability density function based on the image; generating a first luminance histogram; computing a weighing distribution function based on the first luminance histogram; generating a second luminance histogram through pixel redistribution of the first luminance histogram; computing a cumulative density function based on the second luminance histogram; computing a gamma conversion function based on the cumulative density function based on the second luminance histogram; and adjusting luminance distribution of the input image based on the gamma conversion function.

Method for improving image quality

A method and a system for image haze removal are provided. The method includes the following steps: receiving an input hazy image including input pixels; determining a hybrid dark channel for each of the input pixels according to a first minimum dark channel of a corresponding large local patch and a second minimum dark channel of a corresponding small local patch; determining a transmission map for each of the input pixels according to the hybrid dark channel prior, the corresponding hybrid dark channel, and atmospheric light associated with the input hazy image in each color channel; determining a color spectrum adjustment parameter corresponding to each of the color channels; recovering scene radiance for each of the input pixels in each of the color channels according to the corresponding color spectrum adjustment parameter, the transmission map, and the corresponding atmospheric light to produce and output a de-hazed image.

Method and system for image haze removal based on hybrid dark channel prior

A method for moving object detection based on a Principal Component Analysis-based Radial Basis Function network (PCA-based RBF network) includes the following steps. A sequence of incoming frames of a fixed location delivered over a network are received. A plurality of Eigen-patterns are generated from the sequence of incoming frames based on a Principal Component Analysis (PCA) model. A background model is constructed from the sequence of incoming frames based on a Radial Basis Function (RBF) network model. A current incoming frame is received and divided into a plurality of current incoming blocks. Each of the current incoming blocks is classified as either a background block or a moving object block according to the Eigen-patterns. Whether a current incoming pixel of the moving object blocks among the current incoming blocks is a moving object pixel or a background pixel is determined according to the background model.

Method and apparatus for moving object detection using principal component analysis based radial basis function network

A method and an image processing apparatus for image visibility restoration are provided. The method includes the following steps. After an incoming hazy image is received, each of the incoming pixels is classified as either belonging to a localized light region or a non-localized light region. The localized light region is partitioned into patches according to each patch size in associated with image sizes in a training data set. Localized light patches are determined based on a FLD model and a designated patch size is accordingly determined. Adaptive chromatic parameters and dual dark channel priors corresponding to the designated patch size and a small patch size are determined. The incoming hazy image is restored according to the adaptive chromatic parameters, atmospheric light and a transmission map determined based on the dual dark channel priors to produce and output a de-hazed image.

Method and image processing apparatus for image visibility restoration using fisher's linear discriminant based dual dark channel prior

A method for moving object detection based on a Fisher's Linear Discriminant-based Radial Basis Function Network (FLD-based RBF network) includes the following steps. A sequence of incoming frames of a fixed location delivered over a network are received. A plurality of discriminant patterns are generated from the sequence of incoming frames based on a Fisher's Linear Discriminant (FLD) model. A background model is constructed from the sequence of incoming frames based on a Radial Basis Function (RBF) network model. A current incoming frame is received and divided into a plurality of current incoming blocks. Each of the current incoming blocks is classified as either a background block or a moving object block according to the discriminant patterns. Whether a current incoming pixel of the moving object blocks among the current incoming blocks is a moving object pixel or a background pixel is determined according to the background model.

Method and apparatus for moving object detection using fisher's linear discriminant based radial basis function network

The invention discloses an image processing method and an imager processing apparatus using the same. The method includes the following steps: receiving an training image; finding a minimum difference among the differences; determining whether the minimum difference is larger than a first threshold; if no, generating a first output value according to the first pixel, the background candidates and a plurality of weightings corresponding to the background candidates; updating a first background candidate corresponding to the minimum difference; updating a first weighting related to the first background candidate; if yes, adding the first pixel as a new background candidate to the background candidates and adding a new weighting corresponding to the new background candidate to the weightings; and detecting whether a moving object existing in an incoming image according to the background candidates and the weightings.

Image processing method and image processing apparatus using the same

A face annotation method and a face annotation system adapted for a current owner to annotate contacts in online social networks (OSNs) are provided. The face annotation method includes: providing a Hierarchical Database Access (HDA) architecture for each member according to various social network contexts; providing a Fused Face Recognition (FFR) unit which uses an Adaboost algorithm to fuse a plurality types of base classifiers; and constructing a Face Recognizer by integrating the HDA architecture and the corresponding FFR unit for the owner and each member via respective types of the social network contexts; and selecting suitable personalized Face Recognizers and merging multiple personalized Face Recognizer results by using at least two collaborative FR strategies.

Face annotation method and a face annotation system

A face annotation method and a face annotation system are provided. The face annotation method is adapted for a current owner to annotate contacts in online social networks. The face annotation method comprising: providing a pyramid database access control module which consists of a plurality of pyramid database units and performs a first batch of access control procedure and a non-first batch of access control procedure, wherein the pyramid database unit is constructed according to social relationship information; providing a multiple-kernel learning face recognition module implemented through the use of a MKL classifier unit which uses a MKL algorithm to achieve a face identification; and if the MKL-FR model is not able to identify query faces, providing a multiple-kernel learning face recognition fusion module to perform a collaborative face recognition strategy by utilizing a user who features a highest priority rule within a collaborative face recognition framework.

Face annotation method and face annotation system

A method and image processing apparatus for image visibility restoration are provided. The method includes the following steps: receiving an input hazy image including input pixels; obtaining edge information of each of the input pixels according to a median filtering operation and a dark channel; determining a transmission map according to each of the input pixels and atmospheric light associated with the input hazy image in each color channel; obtaining a refined transmission map according to the edge information and the transmission map; adjusting the refined transmission map by performing a gamma correction operation thereon to obtain an enhanced transmission map; determining a color difference value corresponding to each of the color channels; recovering scene radiance for each of the input pixels in each of the color channels according to the corresponding color difference value, the enhanced transmission map, and the atmospheric light to produce and output a de-hazed image.

Method and image processing apparatus for image visibility restoration

The present disclosure proposes a method of moving object detection in variable bit-rate video steams based on probabilistic neural networks, and the method features a background generation module and a moving object detection module. The background generation module produces a model of background images which express properties of variable bit-rate video streams. The moving object detection module distinguishes a moving object in both low and high bit-rate video steams in an efficient manner. The detection result is generated by calculating the output value of the probabilistic neural networks.

Probabilistic neural network based moving object detection method and an apparatus using the same

A method for moving object detection based on a Cerebellar Model Articulation Controller (CMAC) network includes the following steps. A time series of incoming frames of a fixed location delivered over a network is received. A CMAC network is constructed from the time series of incoming frames, where the CMAC network includes an input space, an association memory space, a weight memory space, and an output space. A current frame is received and divided into a plurality of current blocks. Each of the current blocks is classified as either a background block or a moving object block according to the CMAC network. Whether a target pixel of the moving object blocks is a moving object pixel or a background pixel is determined according to an output of the CMAC network in the output space.

Growing community of inventors

Taipei, Taiwan

Shih-Chia Huang