-
公开(公告)号：US20220230322A1
公开(公告)日：2022-07-21
申请号：US17336702
申请日：2021-06-02
Applicant: DALIAN UNIVERSITY OF TECHNOLOGY
Inventor： Wen DONG , Xin YANG , Haiyang MEI , Xiaopeng WEI , Qiang ZHANG
Abstract: The invention belongs to scene segmentation's field in computer vision and is a depth-aware method for mirror segmentation. PDNet successively includes a multi-layer feature extractor, a positioning module, and a delineating module. The multi-layer feature extractor uses a traditional feature extraction network to obtain contextual features; the positioning module combines RGB feature information with depth feature information to initially determine the position of the mirror in the image; the delineating module is based on the image RGB feature information, combined with depth information to adjust and determine the boundary of the mirror. This method is the first method that uses both RGB image and depth image to achieve mirror segmentation in an image. The present invention has also been further tested. For mirrors with a large area in a complex environment, the PDNet segmentation results are still excellent, and the results at the boundary of the mirrors are also satisfactory.
-
公开(公告)号：US20220212339A1
公开(公告)日：2022-07-07
申请号：US17564588
申请日：2021-12-29
Applicant: DALIAN UNIVERSITY OF TECHNOLOGY
Inventor： Xin YANG , Boyan WEI , Baocai YIN , Qiang ZHANG , Xiaopeng WEI , Zhenjun DU
IPC: B25J9/16
Abstract: The present invention belongs to the technical field of computer vision and provides a data active selection method for robot grasping. The core content of the present invention is a data selection strategy module, which shares the feature extraction layer of backbone main network and integrates the features of three receptive fields with different sizes. While making full use of the feature extraction module, the present invention greatly reduces the amount of parameters that need to be added. During the training process of the main grasp method detection network model, the data selection strategy module can be synchronously trained to form an end-to-end model. The present invention makes use of naturally existing labeled and unlabeled labels, and makes full use of the labeled data and the unlabeled data. When the amount of the labeled data is small, the network can still be more fully trained.
-
公开(公告)号：US20150053172A1
公开(公告)日：2015-02-26
申请号：US14529187
申请日：2014-10-31
Applicant: Dalian University of Technology
Inventor： Wuqiang LONG , Kunpeng QI , Jiangping TIAN , Qiang ZHANG , Kai SHENG , Ping YI , Yicong WANG , Yao FU
CPC classification number: F02M29/00 , F02B1/12 , F02B3/06 , F02B23/0651 , F02B23/0672 , F02B23/0693 , F02B2275/14 , F02F3/24 , Y02T10/123 , Y02T10/125
Abstract: A diesel combustion system including an injector and a combustion chamber. The combustion chamber is formed by a cylinder head, a cylinder liner, and a piston. The combustion chamber includes an upper layer and a lower layer. The diameter D1 of the upper layer is larger than the diameter D2 of the lower layer. A junction of the upper layer and the lower layer is provided with an impinging block for rebounding the diesel fuel spray. The impinging block includes an impinging surface, an upper guide surface, and a lower guide surface. When in use, part of the diesel fuel spray is rebounded by the impinging surface, and part of the diesel fuel spray is diffused along the upper guide surface and the lower guide surface of the impinging block to achieve double-layered split flow of the diesel fuel.
Abstract translation: 一种包括喷射器和燃烧室的柴油燃烧系统。 燃烧室由气缸盖，气缸套和活塞形成。 燃烧室包括上层和下层。 上层的直径D1大于下层的直径D2。 上层和下层的接合处设置有用于回弹柴油喷雾的冲击块。 撞击块包括撞击表面，上引导表面和下引导表面。 当使用时，部分柴油喷射被冲击表面反弹，部分柴油喷雾沿着撞击块的上引导表面和下引导表面扩散，以实现柴油双层分流 汽油。
-
公开(公告)号：US20220148292A1
公开(公告)日：2022-05-12
申请号：US17257704
申请日：2020-03-13
Applicant: DALIAN UNIVERSITY OF TECHNOLOGY
Inventor： Xin YANG , Xiaopeng WEI , Qiang ZHANG , Haiyang MEI , Yuanyuan LIU
IPC: G06V10/774 , G06V10/77 , G06V10/80 , G06V10/70 , G06V10/776 , G06V10/44
Abstract: The invention discloses a method for glass detection in a real scene, which belongs to the field of object detection. The present invention designs a combination method based on LCFI blocks to effectively integrate context features of different scales. Finally, multiple LCFI combination blocks are embedded into the glass detection network GDNet to obtain large-scale context features of different levels, thereby realize reliable and accurate glass detection in various scenarios. The glass detection network GDNet in the present invention can effectively predict the true area of glass in different scenes through this method of fusing context features of different scales, successfully detect glass with different sizes, and effectively handle with glass in different scenes. GDNet has strong adaptability to the various glass area sizes of the images in the glass detection dataset, and has the highest accuracy in the field of the same type of object detection.
-
Patent Agency Ranking
公开(公告)号：US20210216806A1
公开(公告)日：2021-07-15
申请号：US16963140
申请日：2020-05-13
Applicant: DALIAN UNIVERSITY OF TECHNOLOGY
Inventor： Xin YANG , Xiaopeng WEI , Qiang ZHANG , Yuhao LIU , Yu QIAO
Abstract: The invention belongs to the field of computer vision technology, and provides a fully automatic natural image matting method. For image matting of a single image, it is mainly composed of the extraction of high-level semantic features and low-level structural features, the filtering of pyramid features, the extraction of spatial structure information, and the late optimization of the discriminator network. The invention can generate accurate alpha matte without any auxiliary information, saving the time for scientific researchers to mark auxiliary information and the interaction time when users use it.
-
公开(公告)号：US20180128158A1
公开(公告)日：2018-05-10
申请号：US15865296
申请日：2018-01-09
Applicant: DALIAN UNIVERSITY OF TECHNOLOGY
Inventor： Wuqiang LONG , Hua TIAN , Jiangping TIAN , Yao FU , Jingchen CUI , Kai SHENG , Ping YI , Kunpeng QI , Qiang ZHANG , Yicong WANG
CPC classification number: F02B23/0651 , F02B1/12 , F02F1/242 , F02F3/28 , Y02T10/125
Abstract: A diesel combustion system including a piston, an annular impinging block, and a combustion chamber. The combustion chamber is divided by the annular impinging block into an upper chamber and a lower chamber. The annular impinging block includes a lower guide surface that is adjacent to the lower chamber and that extends from a trough line connected to the piston to a crest line. The ratios among the inner diameter of the top of the piston, the outer diameter of the top of the piston, the diameter of the trough line, and the diameter of the crest line define the shape of the combustion chamber which leads to increased rate of combustion, reduced soot emission, and increased fuel efficiency.
-
公开(公告)号：US20240028036A1
公开(公告)日：2024-01-25
申请号：US18373623
申请日：2023-09-27
Applicant: DALIAN UNIVERSITY OF TECHNOLOGY
Inventor： Xin YANG , Xiaopeng WEI , Yang WANG , Qiang ZHANG
CPC classification number: G05D1/0088 , G05D1/0248 , G05D1/0214 , G06V10/82 , G06V10/80 , G06V20/58
Abstract: The present invention provides a robot dynamic obstacle avoidance method based on a multimodal spiking neural network. The present invention realizes a robot obstacle avoidance method in a dynamic environment by fusing laser radar data and processed event camera data and combining with the intrinsic learnable threshold of the spiking neural network for a scenario comprising dynamic obstacles. It solves the difficulty of failure of obstacle avoidance due to the difficulty in perceiving the dynamic obstacles in the obstacle avoidance task of a robot. The present invention helps the robot to fully perceive the static information and the dynamic information of the environment, uses the learnable threshold mechanism of the spiking neural network for efficient reinforcement learning training and decision making, and realizes autonomous navigation and obstacle avoidance in the dynamic environment. An event data enhanced model is combined to better adapt to the dynamic environment for obstacle avoidance.
-
公开(公告)号：US20240257304A1
公开(公告)日：2024-08-01
申请号：US18004800
申请日：2022-06-15
Applicant: DALIAN UNIVERSITY OF TECHNOLOGY
Inventor： Qian LIU , Bing WU , Qiang ZHANG , Xiaopeng WEI
IPC: G06T3/4053 , B25J9/16 , G06T3/4046
CPC classification number: G06T3/4053 , B25J9/163 , B25J9/1694 , G06T3/4046
Abstract: The present disclosure relates to a tactile pattern Super Resolution (SR) reconstruction method and acquisition system, which belong to the field of tactile perception. First, a High Resolution (HR) tactile pattern sample is obtained by using a Low Resolution (LR) tactile sensor; then, a deep learning-based tactile SR model is trained by using a tactile SR data set; and finally, reconstructing the tactile data of a contact surface to be measured as an SR tactile pattern by using the tactile SR model. The present disclosure uses the existing taxel-based LR tactile sensor and adopts a deep learning-based tactile SR reconstruction technology, which can effectively restore the shape of the contact surface, improves the resolution of the tactile sensor, and meanwhile, maintains the characteristics of the sensor being light, flexible, and easy to be integrated into devices, such as a robot.
-
公开(公告)号：US20220215662A1
公开(公告)日：2022-07-07
申请号：US17557933
申请日：2021-12-21
Applicant: DALIAN UNIVERSITY OF TECHNOLOGY
Inventor： Xin YANG , Xiaopeng WEI , Yu QIAO , Qiang ZHANG , Baocai YIN , Haiyin PIAO , Zhenjun DU
IPC: G06V20/40 , G06T7/10 , G06V10/46 , G06V10/82 , G06T3/40 , G06T7/215 , G06T9/00 , G06K9/62 , G06V10/72 , G06V10/764 , G06V10/778 , G06V10/774 , G06V10/776
Abstract: The present invention belongs to the technical field of computer vision, and provides a video semantic segmentation method based on active learning, comprising an image semantic segmentation module, a data selection module based on the active learning and a label propagation module. The image semantic segmentation module is responsible for segmenting image results and extracting high-level features required by the data selection module; the data selection module selects a data subset with rich information at an image level, and selects pixel blocks to be labeled at a pixel level; and the label propagation module realizes migration from image to video tasks and completes the segmentation result of a video quickly to obtain weakly-supervised data. The present invention can rapidly generate weakly-supervised data sets, reduce the cost of manufacture of the data and optimize the performance of a semantic segmentation network.
-
-
-
-
-
-
-
-
Search Results
9
records
(took 0.015 seconds)
