National Taiwan University

National Chung Shan Institute of Science and Technology

Academia Sinica

Automotive Research & Testing Center

Chung-shan Institute of Science and Technology, Armaments, Bureau, Ministry of National Defense

Li-Chen Fu

Pei-Yung Hsiao

Yi-Ming Chan

Min-Fang Lo

Wei-Wen Wang

Shao-Kang Hung

Ming-Yen Lin

Ing-Shouh Hwang

Hung-Yu Lin

Chia-Ming Wang

Cheng-Hsien Lin

Chao-Lin Wu

Kuo-Ching Chang

Yu-Sheng Liao

Kai-Wen Lee

Mei-Yung Chen

Shao-Chung Hu

Sheng-Chih Huang

Yi-Wen Liao

Cheng-Chang Ho

Yen-Yu Chou

Ting-En Tseng

An-Sheng Liu

Jin-Shin Lai

Po-Hao Hsiao

Pang-Ting Huang

Cheng-En Wu

Cheng-Ming Huang

Yi-Tzn Lin

Shih-Huang Tseng

Ching-Hu Lu

Li-An Chuang

Christopher Young

Chung-Dial Lim

Jia-Yuan Yu

A limb rehabilitation and training system includes a horizontal position adjuster movably mounted at a bottom side of a base, an expansion rotary member mounted at the horizontal position adjuster, a shoulder joint traction mechanism linked to the expansion rotary member through a first arm segment robotic arm and a height adjuster, and an upper-limb rehabilitation device linked to the shoulder joint traction mechanism. The upper-limb rehabilitation device is able to rapidly be adjusted to fit the left arm or right arm through the horizontal position adjuster, the expansion rotary member, the first arm segment robotic arm and a shoulder positioning-lifting rotary member and. Further, by means of the shoulder joint traction mechanism, the user's stiffened shoulder joint can be timely moved for a separation distance, achieving the function of loosening the joint and facilitating performance of successive rehabilitation treatment or training.

Limb rehabilitation and training system

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

A rehabilitation device with pace pattern projecting function and seat structure and a control method thereof are provided. The rehabilitation device includes a body with a moving module, a projection device, a first sensor and a control system. The projection device projects pace patterns on a walking plane. The first sensor detects a walking situation of a user on the walking plane. Based on the walking situation detected by the first sensor, the control system adjusts a distance between the rehabilitation device and the user by controlling the moving module and adjusts a position of the pace patterns on the walking plane by controlling the projection device. Moreover, a movable seat mechanism is also disposed on the rear of the rehabilitation device. The user can sit down on the movable seat mechanism and towards the front of the rehabilitation device to rest moderately.

Rehabilitation device with pace pattern projecting function and seat structure and control method thereof

A rehabilitation and training apparatus is built based on the empirical law by introducing physical therapists' experiences into the apparatus to simulate therapy with hands in the course of rehabilitation. The apparatus includes a multi-axis robotic arm having first to eighth arm segments, and a high-precision control system for controlling movements of the multi-axis robotic arm. The control system provides an active, a passive and an auxiliary mode; receives and computes information about a patient's movements and muscle force detected by potentiometers and force sensors provided in the multi-axis robotic arm; and accordingly, drives actuators to apply an aiding force or a resisting force to assist the patient in completing rehabilitation exercises. The apparatus also includes a humanized operating interface, via which a doctor or a physical therapist may obtain related rehabilitation data for assessment and adjustment of rehabilitation therapeutic courses. A method of controlling the apparatus is introduced.

Rehabilitation and training apparatus and method of controlling the same

A human image detection and tracking systems and methods are disclosed. A human image detection method comprises receiving a depth image data from a depth image sensor by an image processing unit, removing a background image of the depth image sensor and outputting a foreground image by the image processing unit, receiving the foreground image and operating a graph-based segment on the foreground image to obtain a plurality of graph blocks by a human image detection unit, determining whether a potential human region exists in the graph blocks, determining whether the potential human region is a potential human head region, determining whether the potential human head region is a real human head region, and regarding the position of the real human head region is the human image position by the human image detection unit if the potential human head region is the real human head region.

Human image tracking system, and human image detection and human image tracking methods thereof

A vision based pedestrian and cyclist detection method includes receiving an input image, calculating a pixel value difference between each pixel and the neighbor pixels thereof, quantifying the pixel value difference as a weight of pixel, proceeding statistics for the pixel value differences and the weights, determining intersections of the statistics as a feature of the input image, classifying the feature into human feature and non-human feature, confirming the human feature belonging to cyclist according to the spatial relationship between the human feature and the detected two-wheeled vehicle, and retaining one detection result for each cyclist by suppressing other weaker spatial relationships between the human feature and the detected two-wheeled vehicle.

Vision based pedestrian and cyclist detection method

A pedestrian detection system and method includes: dividing an image to a plurality of granules, and counting magnitude difference value of each granule in diagonal orientation to obtain features of HOGG. And the HOGG and the HOG captured can work together to improve the detection rate and reduce the false alarm rate, which is the ultimate goal of the vision based pedestrian detection.

Pedestrian detection systems and methods

The present invention provides a visual tracking system and its method comprising: a sensor unit, for capturing monitored scenes continuously; an image processor unit, for detecting when a target enters into a monitored scene, and extracting its characteristics to establish at least one model, and calculating the matching scores of the models; a hybrid tracking algorithm unit, for combining the matching scores to produce optimal matching results; a visual probability data association filter, for receiving the optimal matching results to eliminate the interference and output a tracking signal; an active moving platform, for driving the platform according to the tracking signal to situate the target at the center of the image. Therefore, the visual tracking system of the present invention can help a security camera system to record the target in details and maximize the visual information of the intruding target.

Visual tracking system and method thereof

A pedestrian detector includes an image-taking mechanism and an image analyzer. The image-taking mechanism is provided on a vehicle and used to take an image in front of the vehicle. The image analyzer is connected to the image-taking mechanism and used to receive the image from the image-taking mechanism and analyze the image to determine whether the image conforms to a pedestrian to determine whether there is a pedestrian in front of the vehicle.

Pedestrian detector

A locating and tracking system is provided. The locating and tracking system includes plural pressure sensing modules, each of which includes at least one pressure sensing unit detecting a pressure source and generating a signal; a data processing unit connected with the at least one pressure sensing unit, and processing the signal to generate a module information; a storage unit connected with the data processing unit, and storing the module information and an user information; a communication unit connected with the data processing unit, transmitting the module information, and receiving an outer information; and a power managing unit managing a power needed by the at least one pressure sensing unit, the data processing unit, the storage unit and the communication unit; a bottom board configured on a floor, and bearing the mentioned units; and a top board covering the mentioned units, and transferring the pressure source to the pressure sensing unit.

Pressure sensing based localization and tracking system

A rehabilitation device includes a moving body, a motor, a control system and a sensor module. The moving body has a housing and a moving mechanism. The motor, disposed in the housing, connects to the moving mechanism and drives the moving mechanism. The control system is disposed in the housing and coupled to the motor. The sensor module is disposed on the moving body and coupled to the control module. The control system controls the operation of the motor to move the moving body according to information detected by the sensor module.

Rehabilitation device

In a six-degree-of-freedom precision positioning system, magnetic force and fluid buoyancy are used to levitate a platform, and the non-contact magnetic force between electromagnets and magnets forms a main driving force for the platform. Therefore, no friction is present in the system and no lubricating mechanism is needed for the system. Moreover, in the system, electric current is converted by electromagnets and magnets into a magnetic driving force without using any transmission gears. Therefore, the backlash phenomenon that is not easily controllable in the conventional servo positioning systems is avoided. The system has simplified structure without the need of complicated fabrication, and utilizes the properties of fluid to achieve low power consumption, high precision positioning, and fast response.

Six-degree-of-freedom precision positioning system

Methods and systems for tracking users and providing services are provided. The system comprises a plurality of pressure sensors, a storage unit, at least one service providing unit having a service, and a signal processing unit. The pressure sensors detect pressure applied thereon at a specific time point, and correspondingly generate sensed signals. The signal processing unit receives the sensed signals from the pressure sensors, and stores the sensed signals to the storage unit. The signal processing unit calculates a current state of an object according to the sensed signals and historical sensed signals and historical states of the object in the storage unit, and determines one of the at least one service providing unit according to the current state to activate service thereof.

Methods and systems for tracking users and providing services

Disclosed is a novel scanning-probe type atomic force microscope wherein false deflection of the probe is reduced. The probe of the scanning-probe type atomic force microscope moves in both the horizontal direction and the vertical direction during the scanning, while the sample is kept in order to reduce the false deflection brought to the probe due to the scanning motion, two approaches are adopted. The first is to have a focused laser spot tracking an invariant point on the probe's cantilever, which moves three-dimensionally during the scanning. The second approach is to have the laser beam, which is reflected from the moving cantilever, hitting an invariant point of the PSD, when the sample is distanced from the probe and induces no deflection. A beam tracking system wherein the scanning probe is located approximately at the focal point of an objective lens and he optical system including a laser source, an optical module, a feedback module and the probe are driven by an approach mechanism to move in synchronization.

Growing community of inventors

Taipei, Taiwan

Li-Chen Fu