摘要：【中文】公开了一种基于语义SLAM的建图方法和装置及电子设备。根据一实施例，一种基于语义SLAM的建图方法可包括：通过相机获得当前帧图像；利用语义分割算法对所述当前帧图像进行处理以获得其语义信息；利用参考帧以最小化重构语义误差的方式来优化所述当前帧对应的相机位姿；以及，基于优化的相机位姿确定所述参考帧上的不具有深度信息的未成熟点与所述当前帧上的对应点的深度信息，以形成具有深度信息的成熟点。这样，可以基于语义信息优化图像帧对应的相机位姿，从而更加稳定地获得准确的地图点云。 【EN】A drawing establishing method and device based on semantic SLAM and electronic equipment are disclosed. According to one embodiment, a mapping method based on semantic SLAM can include: obtaining a current frame image through a camera; processing the current frame image by using a semantic segmentation algorithm to obtain semantic information of the current frame image; optimizing a camera pose corresponding to the current frame by utilizing a reference frame in a mode of minimizing a reconstructed semantic error; and determining, based on the optimized camera pose, depth information for an immature point on the reference frame that does not have depth information and a corresponding point on the current frame to form a mature point with depth information. Therefore, the camera pose corresponding to the image frame can be optimized based on the semantic information, and accurate map point cloud can be obtained more stably.

摘要：【中文】公开了一种轨迹确定方法、装置和电子设备。在本申请中，根据第一移动轨迹生成至少一条第二移动轨迹，例如，在第一移动轨迹周边确定出与第一移动轨迹相似的至少一条第二移动轨迹，然后获取第一移动轨迹所在的位置区域内的预设道路轨迹，再根据预设道路轨迹和至少一条第二移动轨迹来确定可移动设备的第三移动轨迹，第三移动轨迹包括与预设道路轨迹相似一条移动轨迹，由于可移动设备往往是在预设道路轨迹上移动的，如此可以得到可移动设备在预设道路轨迹上的真实的移动轨迹。 【EN】A track determination method, a track determination device and electronic equipment are disclosed. In the application, at least one second movement track is generated according to the first movement track, for example, at least one second movement track similar to the first movement track is determined around the first movement track, then a preset road track in a position area where the first movement track is located is obtained, and then a third movement track of the mobile device is determined according to the preset road track and the at least one second movement track, wherein the third movement track comprises a movement track similar to the preset road track, and as the mobile device often moves on the preset road track, a real movement track of the mobile device on the preset road track can be obtained.

摘要：【中文】公开了一种地图校正方法、装置和电子设备。确定可移动设备的第一移动轨迹以及预设视觉尺度，根据第一移动轨迹和预设视觉尺度生成具有视觉尺度的至少一条第二移动轨迹。例如，在第一移动轨迹周边确定出与第一移动轨迹相似的至少一条具有视觉尺度的第二移动轨迹，然后获取第一移动轨迹所在的位置区域内的预设道路轨迹。根据预设道路轨迹以及至少一条第二移动轨迹确定可移动设备的、具有视觉尺度的第三移动轨迹。由于可移动设备往往是在预设道路轨迹上移动的，如此可以得到可移动设备在预设道路轨迹上的真实的移动轨迹，也即第三移动轨迹，之后根据第三移动轨迹的视觉尺度校正可移动设备移动时生成的地图，从而可以使得校正后的地图是客观标准的。 【EN】A map correction method, apparatus and electronic device are disclosed. The method comprises the steps of determining a first movement track and a preset visual scale of the movable equipment, and generating at least one second movement track with the visual scale according to the first movement track and the preset visual scale. For example, at least one second movement track with a visual scale similar to the first movement track is determined around the first movement track, and then a preset road track in a position area where the first movement track is located is obtained. And determining a third movement track with a visual scale of the movable equipment according to the preset road track and the at least one second movement track. Because the movable equipment often moves on the preset road track, the real moving track of the movable equipment on the preset road track, namely the third moving track, can be obtained, and then the map generated when the movable equipment moves is corrected according to the visual scale of the third moving track, so that the corrected map is in an objective standard.

摘要：【中文】公开了一种视觉定位方法、装置以及电子设备，该方法包括：获取用于定位车辆的至少一幅图像；确定所述至少一幅图像中的至少一个第一天际线特征；从数据库中确定与所述至少一个第一天际线特征相匹配的第二天际线特征，所述数据库用于记录天际线特征与相机的位姿信息之间的对应关系；基于所述数据库中记录的与所述第二天际线特征相对应的位姿信息定位所述车辆。采用该方法能实现稳定定位，尤其适用于在开阔道路等场景下准确地获得车辆的位置信息。 【EN】Disclosed are a visual positioning method, a device and an electronic device, wherein the method comprises the following steps: acquiring at least one image for locating the vehicle; determining at least one first antenna feature in the at least one image; determining a second skyline feature matched with the at least one first skyline feature from a database, wherein the database is used for recording the corresponding relation between the skyline feature and the pose information of the camera; locating the vehicle based on pose information recorded in the database corresponding to the second skyline feature. The method can realize stable positioning, and is particularly suitable for accurately obtaining the position information of the vehicle in scenes such as open roads and the like.

摘要：【中文】本申请公开了一种位姿信息确定方法、确定装置、电子设备和计算机可读的存储介质。根据一实施例，一种位姿信息确定方法包括匹配图像获取设备获取的当前帧图像中的标识物与矢量化地图中的标识物；当所述当前帧图像中的标识物与所述矢量化地图中的所述标识物匹配成功时，确定当前帧图像中的匹配成功的标识物的观测包围框；基于所述观测包围框与所述矢量化地图中的标识物的表示，确定所述图像获取设备的位姿信息。采用上述位姿信息确定方法，可以通过匹配当前帧图像中的标识物的表示与矢量化地图中的标识物的表示，从而优化图像获取设备的位姿信息。 【EN】The application discloses a pose information determination method, a pose information determination device, electronic equipment and a computer-readable storage medium. According to one embodiment, a pose information determination method includes matching a marker in a current frame image acquired by an image acquisition device with a marker in a vectorized map; when the marker in the current frame image is successfully matched with the marker in the vectorized map, determining an observation surrounding frame of the successfully matched marker in the current frame image; determining pose information for the image capture device based on the observation bounding box and the representation of the marker in the vectorized map. By adopting the pose information determining method, the pose information of the image acquisition equipment can be optimized by matching the representation of the marker in the current frame image with the representation of the marker in the vectorized map.

摘要：【中文】本申请提供一种标识物表示的获取方法，包括对获取的当前帧图像进行目标检测，获得当前帧图像中的当前帧标识物；对与所述当前帧标识物匹配的点云进行参数拟合，获得所述当前帧标识物的表示；基于历史帧标识物的表示，对所述当前帧标识物的表示进行优化，所述历史帧标识物是与当前帧标识物匹配的先前预定数目帧中的标识物。本申请还包括一种标识物表示的获取装置和电子设备及机动车。本申请利用语义分析图像序列中的当前帧图像中的标识物以及基于所获取的点云和标识物，匹配所述点云和所述当前帧标识物，获得所述点云中的点之间的约束关系，充分利用了标识物的结构信息，减少了拟合次数，优化了标识物表示，简化和加快了SLAM过程。 【EN】The application provides a marker representation acquisition method, which comprises the steps of carrying out target detection on an acquired current frame image to obtain a current frame marker in the current frame image; performing parameter fitting on the point cloud matched with the current frame marker to obtain the representation of the current frame marker; the representation of the current frame identifier is optimized based on a representation of a history frame identifier, which is an identifier in a predetermined number of frames prior to the matching of the current frame identifier. The application also comprises an acquisition device and electronic equipment for the marker representation and a motor vehicle. The method and the device have the advantages that the point cloud and the current frame marker are matched by utilizing the marker in the current frame image in the semantic analysis image sequence and based on the acquired point cloud and the marker, the constraint relation between the points in the point cloud is acquired, the structural information of the marker is fully utilized, the fitting times are reduced, the marker expression is optimized, and the SLAM process is simplified and accelerated.

摘要：【中文】本申请公开了一种异构双目SLAM方法，包括：对第一单目相机和第二单目相机分别构建第一单目SLAM和第二单目SLAM，其中所述第一单目相机和所述第二单目相机是异构相机；利用位于所述第一单目相机和所述第二单目相机双目的共同视野内的特征点分别矫正所述第一单目SLAM和所述第二单目SLAM的尺度；以及对矫正后的所述第一单目SLAM和所述第二单目SLAM进行数据融合，构建双目SLAM。还公开了一种异构双目SLAM装置、电子设备和非暂时性存储介质。通过本申请的异构双目SLAM方法，能够更精确地构建双目SLAM，并获得更宽的视角和更深的景深，能够检测位于不同景深的物项，提高了双目SLAM的精确度和准确度。 【EN】The application discloses a heterogeneous binocular SLAM method, which comprises the following steps: respectively constructing a first monocular SLAM and a second monocular SLAM for a first monocular camera and a second monocular camera, wherein the first monocular camera and the second monocular camera are heterogeneous cameras; respectively correcting the scales of the first monocular SLAM and the second monocular SLAM by utilizing feature points positioned in a dual-purpose common visual field of the first monocular camera and the second monocular camera; and carrying out data fusion on the corrected first monocular SLAM and the corrected second monocular SLAM to construct a binocular SLAM. Also disclosed are a heterogeneous binocular SLAM apparatus, an electronic device and a non-transitory storage medium. By the heterogeneous binocular SLAM method, the binocular SLAM can be constructed more accurately, a wider visual angle and a deeper depth of field can be obtained, objects in different depth of field can be detected, and accuracy and precision of the binocular SLAM are improved.

摘要：【中文】本发明提供了一种工艺腔室，涉及半导体工艺技术领域，所述腔室包括：腔体以及设置在所述腔体内的进气机构；所述腔体的侧壁的内表面为圆周面，所述腔体底部设置有排气口，所述进气机构设置在所述腔体的顶部；其中，所述进气机构包括：多个第一输气管路，且所述第一输气管路均与所述进气机构连通；多个所述第一输气管路输出的气流形成围绕所述腔体的轴线的环形气流。本发明还提供了一种半导体加工设备。采用本发明的工艺腔室，其基片表面上各处的工艺气体浓度一致，提高了基片表面上各个区域的成膜均匀性。 【EN】The invention provides a process chamber, which relates to the technical field of semiconductor processes, and comprises: the air inlet mechanism is arranged in the cavity; the inner surface of the side wall of the cavity is a circumferential surface, the bottom of the cavity is provided with an exhaust port, and the air inlet mechanism is arranged at the top of the cavity; wherein, the air intake mechanism includes: the first air transmission pipelines are communicated with the air inlet mechanism; the air flow output by the first air transmission pipelines forms annular air flow around the axis of the cavity. The invention also provides semiconductor processing equipment. By adopting the process chamber, the concentration of the process gas on each part of the surface of the substrate is consistent, and the film forming uniformity of each area on the surface of the substrate is improved.

摘要：【中文】本发明提供了一种易碎管件的固定组件，包括：支撑件和限位件；所述限位件固定在所述支撑件上，且二者形成有容纳所述易碎管件的管凸台并在所述易碎管件的轴向和径向上进行限位的空间，用于防止所述易碎管件倾倒。本发明还提供一种包括上述易碎管件的固定组件的半导体加工设备，可以同时提高工艺质量和保证易碎管件的安全。 【EN】The invention provides a fixing component of a fragile pipe fitting, which comprises: a support member and a limiting member; the locating part is fixed on the support piece, and the two is formed with and holds the pipe boss of breakable pipe fitting and is in the axial of breakable pipe fitting and radially carry out spacing space, be used for preventing breakable pipe fitting emptys. The invention also provides semiconductor processing equipment comprising the fixing assembly of the fragile pipe fitting, which can simultaneously improve the process quality and ensure the safety of the fragile pipe fitting.

摘要：【中文】本发明提供了一种基于IEEE1588协议的高精度时间同步系统，若干个PTP设备节点经由PTP以太网交换机互联组成时间同步系统，PowerPC微处理器的以太网控制器MAC层集成PTP协议单元，对数据包MAC层进行时戳标记，发送和接收报文，并提供IEEE1588网络授时服务；GPS时钟源接收硬件单元，接收外部GPS时间信息，作为IEEE1588的时间同步的基准，本发明同步精度优于100ns，不需要专业测试设备，降低系统成本，避免从时钟在Sync报文的间隙内发生突变，并通过动态补偿的方式使同步精度得到了保障，达到了高精度的时间同步。 【EN】The invention provides a high-precision time synchronization system based on an IEEE1588 protocol, wherein a plurality of PTP equipment nodes are interconnected through a PTP Ethernet switch to form the time synchronization system, an Ethernet controller MAC layer of a PowerPC microprocessor integrates a PTP protocol unit, a data packet MAC layer is subjected to timestamp marking, a message is sent and received, and IEEE1588 network time service is provided; the GPS clock source receiving hardware unit receives external GPS time information as the standard of IEEE1588 time synchronization, the synchronization precision of the invention is superior to 100ns, no professional test equipment is needed, the system cost is reduced, the sudden change of the slave clock in the clearance of the Sync message is avoided, the synchronization precision is ensured by a dynamic compensation mode, and the high-precision time synchronization is achieved.