-
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：US20210107440A1
公开(公告)日：2021-04-15
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 , B60T8/1755 , B60T8/86 , B60T8/58
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：US10884108B2
公开(公告)日：2021-01-05
申请号：US15823750
申请日：2017-11-28
Inventor： Chao-Wen Liang , Shih-Che Chien , Yu-Sung Hsiao
Abstract: A light detection and ranging system comprises an optical transmitter for beam scanning on a scan region, and receiving reflected light from the scan region; and an optical receiver for directing the reflected light for signal conversion. The optical transmitter includes a beam refractive unit including optical refractive devices, rotatably disposed about a rotation axis, for directing a collimated laser beam from a first optical path towards a direction depending on rotation angles of the optical refractive devices; and a motion unit for actuating relative motion of the optical refractive devices so as to perform beam scanning towards directions on the scan region. The optical receiver includes an off-axis reflective unit, disposed in the first optical path, for directing the reflected light towards a second optical path; and a light detection unit, disposed in the second optical path, for performing signal conversion on the reflected light.
-
公开(公告)号：US10198657B2
公开(公告)日：2019-02-05
申请号：US15375438
申请日：2016-12-12
Inventor： Shih-Shinh Huang , Shih-Che Chien , Feng-Chia Chang , Chien-Hao Hsiao , Yu-Sung Hsiao
IPC: G06K9/00 , G06K9/46 , G06K9/62 , H04N5/33 , H04N19/90 , H04N19/103 , H04N19/136 , H04N19/176
Abstract: An all-weather thermal-image pedestrian detection method includes (a) capturing diurnal thermal images and nocturnal thermal images of a same pedestrian and non-pedestrian object in a same defined block to create a sample database of thermal images, wherein the sample database comprises pedestrian samples and non-pedestrian samples; (b) performing LBP encoding on the pedestrian samples and the non-pedestrian samples, wherein complementary LBP codes in the same defined block are treated as identical LBP codes; (c) expressing the LBP codes in the same defined block as features by a gradient direction histogram (HOG) to obtain feature training samples of the pedestrian samples and the non-pedestrian samples; (d) entering the feature training samples into a SVM to undergo training by Adaboost so as to form a strong classifier; and (e) effectuating pedestrian detection by searching the strong classifiers in thermal images with sliding window technique to detect for presence of pedestrians.
-
Patent Agency Ranking
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.
-
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.
-
-
-
-
-
-
-
-
-
Search Results
11
records
(took 0.018 seconds)
