-
公开(公告)号：EP4423730A1
公开(公告)日：2024-09-04
申请号：EP22821605.7
申请日：2022-10-27
发明人： SHAAG, Nadav , SPRINGER, Ofer
CPC分类号： G06V20/58 , G06V10/806 , G06V10/82
-
-
3.发明公开
公开(公告)号：EP4441637A1
公开(公告)日：2024-10-09
申请号：EP22802507.8
申请日：2022-11-03
发明人： BUND, Tobias , ROMETSCH, Mario , THIEL, Robert
IPC分类号： G06F18/25 , G06N3/0455 , G06N3/0464 , G06V10/80 , G06V10/82 , G06V20/56
CPC分类号： G06F18/253 , G06V10/806 , G06V10/82 , G06N3/0455 , G06N3/0464 , G06V20/56
-
公开(公告)号：EP4401046A1
公开(公告)日：2024-07-17
申请号：EP23215421.1
申请日：2023-12-11
申请人： Deere & Company
发明人： SAUER, PATRICK , KHOT, AKSHAY
IPC分类号： G06V10/74 , G06V10/764 , G06V10/80 , G06V20/56 , G06V20/64 , G06V20/70 , A01B69/00 , A01D43/073 , A01D43/08 , G06N3/096 , G06T7/10 , G06T7/73
CPC分类号： G06V20/56 , G06V20/64 , G06V20/70 , G06V10/806 , G06V10/764 , G06V10/74 , A01D43/087 , A01D43/073 , A01B69/004 , G06T7/73
摘要： Eine Anordnung zur bildbasierten Erkennung der Position eines Ladebehälters (18), umfasst eine auf den Ladebehälter (18) gerichtete oder richtbare elektrooptische Einrichtung (126), die konfiguriert ist, ein Bildsignal bereitzustellen, das eine Entfernungsinformation beinhaltet, und eine elektronische Auswertungseinrichtung, die konfiguriert ist, anhand des Bildsignals ein Entfernungsbild hinsichtlich der räumlichen Lage der Kanten des Ladebehälters (18) und eine zweidimensionale Abschätzung der Position (144) der Ecken des Ladebehälters (18) innerhalb des Bildes zu erzeugen und anhand des Entfernungsbildes und der Abschätzung ein Positionssignal hinsichtlich der räumlichen Position der Ecken des Ladebehälters (18) bereitzustellen.
-
5.发明公开
公开(公告)号：EP4390859A1
公开(公告)日：2024-06-26
申请号：EP23215427.8
申请日：2023-12-11
发明人： SUN, Xian , FU, Kun , WANG, Peijin , CHANG, Hao , LU, Wanxuan , BI, Hanbo , HE, Qibin , RONG, Xuee
CPC分类号： Y02D10/00 , G06V10/82 , G06V10/806 , G06V10/993 , G06V20/10 , G06V10/26 , G06V10/803
摘要： A multimodal remote sensing image processing method based on sparse mixture-of-experts network pre-training is provided. The method includes: inputting a to-be-processed image set to a general coding unit to obtain an intermediate image set, where the intermediate image set includes multiple intermediate image groups, each of the intermediate image groups includes a target number of intermediate images; inputting the intermediate image set to a special coding unit to obtain a processed image set, where the special coding unit includes multiple coding module groups, each of the coding module groups includes multiple coding modules, and each of the intermediate image groups is inputted to a coding module in a coding module group having a same mode type as the coding module group; and inputting the processed image set to a decoding unit to obtain a processing result. With the method, the number of image processing of each of coding modules in the special coding unit is reduced, thereby improving the overall processing speed and reducing the processing time.
-
公开(公告)号：EP3970061B1
公开(公告)日：2024-09-25
申请号：EP20722267.0
申请日：2020-04-23
-
公开(公告)号：EP4430563A1
公开(公告)日：2024-09-18
申请号：EP22830642.9
申请日：2022-11-11
发明人： WANG, Ruoyu , FENG, Chen , TIAN, Dong
CPC分类号： G06T7/11 , G06T7/187 , G06T2207/1002820130101 , G06T2207/2008420130101 , G06T2207/2015620130101 , G06V20/64 , G06V10/82 , G06V10/26 , G06V20/56 , G06V10/806
-
公开(公告)号：EP4414746A1
公开(公告)日：2024-08-14
申请号：EP23198769.4
申请日：2023-09-21
CPC分类号： G01S13/867 , G01S7/417 , G01S7/411 , G01S7/4808 , G01S13/08 , G01S13/58 , G01S13/726 , G01S13/931 , G06F18/251 , G06F18/253 , G06V10/806 , G06V10/803 , G06V10/82 , G06V20/58
摘要： The present invention is related to a multi-Object Detection and Tracking method and system based on AI techniques. According to invention, a computer-implemented method is provided for object detection and tracking of at least one object in an ego vehicle environment. The method uses a hybrid neural network adapted to:
(i) input raw sensor data, generated by at least one camera sensor and at least one radar sensor of the ego vehicle, namely raw camera data and raw radar data,
(ii) process independently raw camera data and raw radar data to generate object detections, to extract respective features from respective raw sensor data, meaning visual features extracted from raw camera data and depth features extracted from raw radar data, and to extract feature embeddings for each detected object,
(iii) fusion of the extracted visual and depth features, and generate fused object detections,
(iv) generating, from the extracted embeddings, tracks for each detected object, and
(v) associating the generated fused object detections to tracks.
In addition, the invention provides a computing system for end-to-end multi-object detection and tracking.-
-
10.发明公开
公开(公告)号：EP4441635A1
公开(公告)日：2024-10-09
申请号：EP22813410.2
申请日：2022-11-10
发明人： BUND, Tobias , ROMETSCH, Mario , THIEL, Robert
IPC分类号： G06F18/21 , G06F18/25 , G06N3/0455 , G06V10/80
CPC分类号： G06V10/806 , G06V10/40 , G06V20/56 , G06F18/21 , G06F18/251 , G06F18/253 , G06N3/0455 , G06V10/82 , G06N3/0464
-
-
-
-
-
-
-
-
-
搜索结果
22 条记录 (耗时 0.01 秒)
