Abstract:
A target detection method and apparatus, in which the method includes: obtaining a target candidate region in a to-be-detected image; determining at least two part candidate regions from the target candidate region by using an image segmentation network, where each part candidate region corresponds to one part of a to-be-detected target; and extracting, from the to-be-detected image, local image features corresponding to the part candidate regions; and learning the local image features of the part candidate regions by using a bidirectional long short-term memory LSTM network, to obtain a part relationship feature used to describe a relationship between the part candidate regions; and detecting the to-be-detected target in the to-be-detected image based on the part relationship feature. As a result, image data processing precision in target detection can be improved, application scenarios of target detection can be diversified, and target detection accuracy can be improved.
Abstract:
A scheduling information transmission method, device, and communications system are provided. The method includes: generating a channel attribute parameter and a serving grant (SG), where the channel attribute parameter and the SG are used for data scheduling of uplink multiple input multiple output (MIMO); and delivering the channel attribute parameter and the SG to a user equipment (UE) through a target channel, where the channel attribute parameter is used by the UE to determine a primary-stream enhanced dedicated channel transport format combination indicator (E-TFCI) and a secondary-stream E-TFCI. In the scheduling information transmission method, device, and communications system that are provided in embodiments of the present invention, the determined E-TFCIs can better adapt to different channel conditions, which improves data transmission performance.
Abstract:
A neural network model training method includes: constructing a first neural network architecture, where the first neural network architecture includes M basic unit layers, each of the M basic unit layers includes a plurality of basic units, and the plurality of basic units includes at least a first-type basic unit and a second-type basic unit; and obtaining a target model through training based on datasets respectively corresponding to a plurality of tasks and the first neural network architecture, where the target model includes a plurality of task paths, at least some of the plurality of task paths include N basic units selected from some of the M basic unit layers, and N
Abstract:
The present invention provides a method and a device for power control of a High Speed Dedicated Physical Control Channel (HS-DPCCH). If a User Equipment (UE) is in a soft handover state and configured to a multi-flow transmission mode, the UE obtains a first HS-DPCCH power offset and an HS-DPCCH adjustment step size that are corresponding to each cell group in all cell groups of the UE. The UE determines a second HS-DPCCH power offset of the cell group according to the HS-DPCCH adjustment step size and the first HS-DPCCH power offset. The UE adjusts current transmit power of the HS-DPCCH according to the second HS-DPCCH power offset of the cell group.
Abstract:
A method and an apparatus for selecting a transport format are provided. The method includes: receiving a transport format parameter of a user equipment sent by a base station, where the transport format parameter of the user equipment includes a primary stream grant value and an association between the primary stream and the secondary stream; determining a maximum transport block length of the primary stream according to a preset value of the maximum transmit power of the user equipment and the association between the primary stream and the secondary stream; determining an actual transport block length of the primary stream according to a size relationship between a theoretical transport block length of the primary stream and the maximum transport block length; and determining a transport block length of the secondary stream.
Abstract:
The present invention provides a method and a device for power control of a High Speed Dedicated Physical Control Channel (HS-DPCCH). If a User Equipment (UE) is in a soft handover state and configured to a multi-flow transmission mode, the UE obtains a first HS-DPCCH power offset and an HS-DPCCH adjustment step size that are corresponding to each cell group in all cell groups of the UE. The UE determines a second HS-DPCCH power offset of the cell group according to the HS-DPCCH adjustment step size and the first HS-DPCCH power offset. The UE adjusts current transmit power of the HS-DPCCH according to the second HS-DPCCH power offset of the cell group.
Abstract:
A method and an apparatus for selecting a transport format are provided. The method includes: receiving a transport format parameter of a user equipment sent by a base station, where the transport format parameter of the user equipment includes a primary stream grant value and an association between the primary stream and the secondary stream; determining a maximum transport block length of the primary stream according to a preset value of the maximum transmit power of the user equipment and the association between the primary stream and the secondary stream; determining an actual transport block length of the primary stream according to a size relationship between a theoretical transport block length of the primary stream and the maximum transport block length; and determining a transport block length of the secondary stream.
Abstract:
A network topology determining apparatus includes: an obtaining module, configured to obtain a connection relationship between a plurality of network elements in a network and a network grade of each network element, where the network grade is used to indicate an importance degree of the network element in the network; a first determining module, configured to determine a plurality of subnets based on the connection relationship between the plurality of network elements and the network grade of each network element; a second determining module, configured to determine location information of each network element in a descending order of the network grades of the network elements in the network based on a connection relationship between network elements in each subnet; and an establishment module, configured to establish a network topology based on the connection relationship between the plurality of network elements and the location information of each network element.
Abstract:
A pedestrian tracking method includes obtaining, within a detection period, an upper body detection box of a to-be-tracked pedestrian appearing in a to-be-tracked video; obtaining a detection period whole body box of the to-be-tracked pedestrian based on the upper body detection box; and obtaining, within the tracking period based on the detection period whole body box, a tracking period whole body box corresponding to an upper body tracking box. It can be learned that the to-be-tracked pedestrian may be tracked using the tracking period whole body box. An aspect ratio of the detection period whole body box may change. Therefore, even if the to-be-tracked pedestrian appears in an abnormal posture within the detection period, an accurate tracking period whole body box of the to-be-tracked pedestrian can still be obtained.
Abstract:
An interference cancelation feedback method is provided. A channel quality indicator CQI of a serving cell is generated according to a received signal, where the received signal includes a serving cell signal and an interference cell signal, where an interference cell interferes with the serving cell of user equipment; interference cancelation indication information is generated, where the interference cancelation indication information is used to indicate a situation of interference cancelation performed on the received signal by the user equipment; the channel quality indicator CQI of the serving cell is fed back to a network side; and the interference cancelation indication information is fed back to the network side, where the interference cancelation indication information and the channel quality indicator CQI of the serving cell are used by the network side to schedule the user equipment.