-
公开(公告)号：US20190163968A1
公开(公告)日：2019-05-30
申请号：US16059013
申请日：2018-08-08
Inventor： Kai-Lung Hua , Shih-Che Chien , Feng-Chia Chang , Hsueh-Ling Tang , Chien-Hao Hsiao , Yu-Sung Hsiao
Abstract: A method for performing pedestrian detection with aid of light detection and ranging (LIDAR) is provided. The method includes: obtaining 3-dimensional (3D) point cloud data through the LIDAR; performing ground separation processing on the 3D point cloud data to remove ground information; performing object extraction processing on the 3D point cloud data to obtain 3D point cloud chart that includes pedestrian candidate point cloud group; performing 2-dimensional (2D) mapping processing on the 3D point cloud chart to obtain 2D chart; and extracting 3D feature and 2D feature from the 3D point cloud chart and the 2D chart, respectively, and utilizing the 3D feature and the 2D feature to determine location of the pedestrian. According to the method, image data obtained by the LIDAR may be enhanced, the method may distinguish between pedestrian far away and environment blocks, and pedestrian recognition in nighttime or in bad weather may be improved.
-
公开(公告)号：US11295160B2
公开(公告)日：2022-04-05
申请号：US16676453
申请日：2019-11-07
Inventor： Shih-Shinh Huang , Shih-Che Chien , Feng-Chia Chang , Yu-Sung Hsiao , Chien-Hao Hsiao
Abstract: An image adaptive feature extraction method includes dividing an image into a plurality of blocks, performing a feature extraction processing on the plurality of blocks, and obtaining a block feature from each of the plurality of blocks after the feature extraction processing; calculating each block feature by means of a support vector machine (SVM) classifier, wherein each block feature is calculated to obtain a hyperplane normal vector; setting a threshold value, determining the block feature according to the hyperplane normal vector, recording the block as an adaptive feature block when a value of the hyperplane normal vector is higher than the threshold value, and integrating each adaptive feature block to form an adaptive feature image. Because an image adaptive feature extraction process is performed before a pedestrian image detection is calculated, and effective feature data is then selected, computational efficiency is boosted and detection pedestrian error probability is reduced.
-
公开(公告)号：US10262223B2
公开(公告)日：2019-04-16
申请号：US15628111
申请日：2017-06-20
Inventor： Chun-Wei Hsieh , Shih-Che Chien , Feng-Chia Chang , Chien-Hao Hsiao
Abstract: A method of speeding up image detection, adapted to increase a speed of detecting a target image and enhance efficiency of image detection, comprises the steps of capturing an image; retrieving a plurality of characteristic points of the image; creating a region of interest (ROI) centered at the characteristic points each; creating a plurality of search point scan windows corresponding to the ROIs, respectively; calculating target hit scores of the characteristic points and the search point scan windows; comparing the target hit scores of the characteristic points and the search point scan windows to obtain an ROI most likely to have a target image; calculating centroid coordinates of the ROI by a centroid shift weight equation; and narrowing a scope of ROI search according to a location of the centroid coordinates and reducing a displacement between the search points.
-
公开(公告)号：US10769421B2
公开(公告)日：2020-09-08
申请号：US16059013
申请日：2018-08-08
Inventor： Kai-Lung Hua , Shih-Che Chien , Feng-Chia Chang , Hsueh-Ling Tang , Chien-Hao Hsiao , Yu-Sung Hsiao
Abstract: A method for performing pedestrian detection with aid of light detection and ranging (LIDAR) is provided. The method includes: obtaining 3-dimensional (3D) point cloud data through the LIDAR; performing ground separation processing on the 3D point cloud data to remove ground information; performing object extraction processing on the 3D point cloud data to obtain 3D point cloud chart that includes pedestrian candidate point cloud group; performing 2-dimensional (2D) mapping processing on the 3D point cloud chart to obtain 2D chart; and extracting 3D feature and 2D feature from the 3D point cloud chart and the 2D chart, respectively, and utilizing the 3D feature and the 2D feature to determine location of the pedestrian. According to the method, image data obtained by the LIDAR may be enhanced, the method may distinguish between pedestrian far away and environment blocks, and pedestrian recognition in nighttime or in bad weather may be improved.
-
公开(公告)号：US10408923B2
公开(公告)日：2019-09-10
申请号：US15379643
申请日：2016-12-15
Inventor： Chao-Wen Liang , Li-Tsun Wang , Shih-Che Chien , Yu-Sung Hsiao
Abstract: A laser radar device comprises a laser projecting system and a laser radar detecting system. The laser projecting system comprises a laser diode; and a light source orientation adjustment unit comprising a collimating lens and a Powell lens to modulate the angle at which the first incident laser beam is projected onto an object. The laser radar detecting system comprises at least two laser radar detection units disposed in the horizontal direction and vertical direction of the object, respectively. The laser radar detection units each comprise a wedge-shaped lens, an aspherical lens system and an optical detector. By designing optical parameters of the wedge-shaped lens and stacking the laser radar detection units in the horizontal direction and vertical direction, it is feasible to facilitate overall device manufacturing and processing, meet R&D needs, and adjust an optical system in its entirety easily.
-
Patent Agency Ranking
公开(公告)号：US10261181B2
公开(公告)日：2019-04-16
申请号：US15627935
申请日：2017-06-20
Inventor： Te-Yuan Chung , Ruoh-Rou Chang , Shih-Che Chien , Yu-Sung Hsiao
Abstract: A laser radar system capable of active polarization comprises a signal processing unit for sending a control signal; a laser emitting unit for emitting a first laser to a target after receiving the control signal, wherein the laser emitting unit comprises a liquid crystal polarization driver and a liquid crystal polarization component group, and the liquid crystal polarization driver controls a phase delay of the liquid crystal polarization component group to therefore change a polarized state of the first laser; and a laser receiving unit for receiving a second laser reflected off the target and analyzing polarization information of the second laser through the signal processing unit to evaluate surface characteristics of the target.
-
公开(公告)号：US11485331B2
公开(公告)日：2022-11-01
申请号：US16600555
申请日：2019-10-13
Inventor： Ming-Kai Gan , Bo-Chiuan Chen , Shih-Che Chien , Chien-Hao Hsiao , Yu-Sung Hsiao , Feng-Chia Chang
IPC: B60T8/171 , B60T8/58 , B60T8/86 , B60T8/1755
Abstract: A surface adaptation method suitable for a vehicle includes evaluating a plurality of longitudinal forces with respect to a plurality of sampling points, evaluating a plurality of wheel slips with respect to the plurality of sampling points, determining a maximum longitudinal force from the plurality of longitudinal forces, and determining a wheel slip threshold from the plurality of wheel slips. The wheel slip threshold corresponds to the maximum longitudinal force.
-
公开(公告)号：US20200160088A1
公开(公告)日：2020-05-21
申请号：US16676453
申请日：2019-11-07
Inventor： Shih-Shinh Huang , Shih-Che Chien , Feng-Chia Chang , Yu-Sung Hsiao , Chien-Hao Hsiao
Abstract: An image adaptive feature extraction method includes dividing an image into a plurality of blocks, performing a feature extraction processing on the plurality of blocks, and obtaining a block feature from each of the plurality of blocks after the feature extraction processing; calculating each block feature by means of a support vector machine (SVM) classifier, wherein each block feature is calculated to obtain a hyperplane normal vector; setting a threshold value, determining the block feature according to the hyperplane normal vector, recording the block as an adaptive feature block when a value of the hyperplane normal vector is higher than the threshold value, and integrating each adaptive feature block to form an adaptive feature image. Because an image adaptive feature extraction process is performed before a pedestrian image detection is calculated, and effective feature data is then selected, computational efficiency is boosted and detection pedestrian error probability is reduced.
-
公开(公告)号：US20190164005A1
公开(公告)日：2019-05-30
申请号：US16059051
申请日：2018-08-09
Inventor： Shih-Shinh Huang , Shih-Che Chien , Feng-Chia Chang , Chien-Hao Hsiao , Yu-Sung Hsiao
IPC: G06K9/46
Abstract: A method for extracting features of a thermal image is provided. The method includes: reading a thermal image, and dividing the thermal image into a plurality of block images; and extracting a histogram of oriented gradient (HOG) feature histogram from each of the plurality of block images, and transforming the HOG feature histogram of each of the plurality of block images into a symmetric weighting HOG (SW-HOG) feature histogram. The SW-HOG feature histogram is obtained by multiplying a histogram of gradient intensity distribution by a block weighting. The method increases weightings of blocks which cover human contours and reduces weightings of blocks of an internal region of a human appearance through analyzing thermal lightness difference of regions within blocks, to reduce the influence of clothes in the internal region and the influence of the background region.
-
公开(公告)号：US09773174B2
公开(公告)日：2017-09-26
申请号：US14969217
申请日：2015-12-15
Inventor： Shih-Shinh Huang , Shih-Che Chien , Feng-Chia Chang
CPC classification number: G06K9/00785 , G06K9/00825 , G06K9/4633 , G06K9/6215 , G06K9/6297 , G06T7/11 , G06T7/12 , G06T7/194 , G06T2207/10048 , G06T2207/20076 , G06T2207/20112 , G06T2207/30236 , G06T2207/30252
Abstract: A vehicle detection method includes (1) vehicle likelihood region identifying step; (2) vehicle component locating step; and (3) vehicle detecting step. To reduce complexity of calculation and enhance accuracy of detection, the method uses a vehicle likelihood region identifying algorithm to eliminate background regions from a total thermal image and keep vehicle likelihood regions therein for use in further analysis and processing, detects obvious vehicle components, such as vehicle windows and vehicle bottoms, in the thermal image to thereby identify vehicle component likelihood regions, describes a space geometric relationship of vehicle components with a Markov random field model, defines vehicle detection as problems with maximum a posteriori probability, estimates the most likely configuration with an optimization algorithm, so as to effectuate vehicle detection.
-
-
-
-
-
-
-
-
-
Search Results
13
records
(took 0.017 seconds)
