Abstract: A pose determination method and device, an electronic device and a storage medium are provided. The method includes that: a reference image matched with an image to be processed is acquired; key point extraction processing is performed on the image to be processed and the reference image to obtain a first key point in the image to be processed and a second key point corresponding to the first key point in the reference image respectively; and a target pose of an image acquisition device when the image to be processed is collected by the image acquisition device is determined according to a corresponding relationship between the first key point and the second key point and a reference pose corresponding to the reference image.

Abstract: A solar-aided coal-fired flexible power generation system and an operating method thereof are provided. The system includes a coal-fired thermal power generation system and a high-temperature heat storage system coupled with solar thermal power generation; wherein a heat storage medium heater is arranged in the boiler flue; the flow rates of heat storage medium entering the solar heat collection device and the heat storage medium heater are adjusted by the regulating valve and the pump, eliminating irradiation fluctuation influences and maintaining stable power; a heat storage medium tank is used for peak shaving to reduce steam turbine output under stable boiler combustion; the flow and temperature of the feedwater entering the heat storage medium and feedwater heat exchanger are adjusted to realize rapid load cycling. The present invention can realize solar and coal-fired generation coupling, reduce coal consumption, and greatly improve the flexibility and economy.

Abstract: A control method for optimizing generated power of a solar-aided coal-fired power system under off-design working conditions sets maximizing generated power without changing main steam flow rate as a control goal. A solar-coal feedwater flow distribution ratio is adjusted to adjust water flow rate heated by a solar heat collection system, so as to achieve the control goal. Control steps include reading relevant information; calculating the water flow rate range heated by the solar heat collection system, and an applicable solar-coal feedwater flow distribution ratio range; establishing a correspondence between the generated power and the solar-coal feedwater flow distribution ratio within this range; selecting a solar-coal feedwater flow distribution ratio corresponding to the maximum generated power; and adjusting the water flow rate entering the solar heat collection system to an optimized value. The present invention can flexibly control the solar-coal coupling and improve the economy.

Abstract: The method for vehicle appearance feature recognition includes: multiple region segmentation results of a target vehicle are obtained from an image to be recognized; global feature data and multiple pieces of region feature data are extracted from the image to be recognized based on the multiple region segmentation results; and the global feature data and the multiple pieces of region feature data are fused to obtain appearance feature data of the target vehicle.

Abstract: The method for vehicle appearance feature recognition includes: multiple region segmentation results of a target vehicle are obtained from an image to be recognized; global feature data and multiple pieces of region feature data are extracted from the image to be recognized based on the multiple region segmentation results; and the global feature data and the multiple pieces of region feature data are fused to obtain appearance feature data of the target vehicle.

Abstract: A method for object detection includes: obtaining a plurality of to-be-determined targets in a to-be-detected image; determining confidences of the plurality of to-be-determined targets separately belonging to at least one category, determining categories of the plurality of to-be-determined targets according to the confidences, and determining position offset values corresponding to the respective categories of the plurality of to-be-determined targets; using the position offset values corresponding to the respective categories of the plurality of to-be-determined targets as position offset values of the plurality of to-be-determined targets; and determining position information and a category of at least one to-be-determined target in the to-be-detected image according to the categories of the plurality of to-be-determined targets, the position offset values of the plurality of to-be-determined targets, and the confidences of the plurality of to-be-determined targets belonging to the categories thereof.

Abstract: Embodiments of the present application disclose a method and apparatus for generating a neural network structure, an electronic device, and a storage medium. The method comprises: sampling a neural network structure to generate a network block, the network block comprising at least one network layer; constructing a sampling neural network based on the network block; training the sampling neural network based on sample data, and obtaining an accuracy corresponding to the sampling neural network; and in response to that the accuracy does not meet a preset condition, regenerating a new network block according to the accuracy until a sampling neural network constructed by the new network block meets the preset condition, and using the sampling neural network meeting the preset condition as a target neural network.

Abstract: A camera optical lens is provided, including from an object side to an image side: a first lens having positive refractive power; a second lens having negative refractive power; a third lens having negative refractive power; a fourth lens having positive refractive power; and a fifth lens having negative refractive power. The camera optical lens satisfies following conditions: 0.70?f1/f?0.90; ?35.00?f3/f<?10.00; 4.0?R3/R4?12.00; 3.00?(R5+R6)/(R5?R6)?20.00; and 2.00?d7/d8?4.50. The above camera optical lens may meet design requirements for wide angle and ultra-thinness, while maintaining a high imaging quality.

Abstract: A solar aided coal-fired power generation system participating in primary frequency regulation and a control method thereof propose a system configuration with two regulation schemes by coupling medium-low-temperature solar collectors and a coal-fired generation unit. The two regulation schemes are a high-pressure feedwater bypass scheme and a low-pressure condensate bypass scheme. The present invention formulates a primary frequency regulation control logic, so as to efficiently and accurately participate in the primary frequency regulation, thereby keeping the power grid frequency rapidly stable. The present invention also formulates a working fluid outlet temperature control logic for the solar aided coal-fired thermal system, which adjusts a heat exchange working fluid flow of the solar collectors to ensure that the temperature in each section is stable during the primary frequency regulation.

Abstract: The method for vehicle appearance feature recognition includes: multiple region segmentation results of a target vehicle are obtained from an image to be recognized; global feature data and multiple pieces of region feature data are extracted from the image to be recognized based on the multiple region segmentation results; and the global feature data and the multiple pieces of region feature data are fused to obtain appearance feature data of the target vehicle.

Abstract: A method for object detection includes: obtaining a plurality of to-be-determined targets in a to-be-detected image; determining confidences of the plurality of to-be-determined targets separately belonging to at least one category, determining categories of the plurality of to-be-determined targets according to the confidences, and determining position offset values corresponding to the respective categories of the plurality of to-be-determined targets; using the position offset values corresponding to the respective categories of the plurality of to-be-determined targets as position offset values of the plurality of to-be-determined targets; and determining position information and a category of at least one to-be-determined target in the to-be-detected image according to the categories of the plurality of to-be-determined targets, the position offset values of the plurality of to-be-determined targets, and the confidences of the plurality of to-be-determined targets belonging to the categories thereof.

Abstract: A method for controlling a coal supply quantity during a transient load-varying process considering exergy storage correction of a boiler system of a coal-fired unit is provided. Temperatures and pressures of working fluid and metal heating surface of the boiler system of the coal-fired unit are measured and recorded in real-time, and converted into the exergy storage amount at different operating load points. During the transient operation process, the real-time exergy storage amount of the boiler system is compared with the exergy storage amount at the corresponding steady-state load point, and the real-time exergy storage variation is obtained; thereafter, the feed-forward control signal of coal supply quantity input is superposed to the existing coal supply quantity command of the boiler system, and the coal supply quantity signal of the boiler system based on the exergy storage correction is finally generated.

Abstract: A target object recognition method includes: performing target object detection on an object of an image to be detected to obtain target object prediction information of the object, where the target object prediction information is confidence information that the detected object is the target object; performing key point detection on the object of the image to be detected to obtain key point prediction information of the object, where the key point prediction information is confidence information that a key point of the detected object is a key point of the target object; fusing the target object prediction information with the key point prediction information to obtain comprehensive prediction information of the object; and recognizing the target object according to the comprehensive prediction information.

Abstract: Example detecting methods and apparatus are described.

Abstract: The present disclosure provides a glass lens and a lens module. The glass lens has an optical axis, and includes an optical portion and a connecting portion surrounding the optical portion. The connecting portion includes a first reference surface and a second reference surface opposite to the first reference surface. The optical portion includes a first optical surface located on one side of the first reference surface and a second optical surface located on one side of the second reference surface. The structure of the glass lens of the present disclosure can form a smaller optical portion without occupying space, and meanwhile, a matching structure can be disposed on the second reference surface of the connecting portion, which can effectively reduce the installation difficulty and positioning cost of the glass lens, and make the product have excellent optical performances meanwhile.

Abstract: A method for controlling a coal supply quantity during a transient load-varying process considering exergy storage correction of a boiler system of a coal-fired unit is provided. Temperatures and pressures of working fluid and metal heating surface of the boiler system of the coal-fired unit are measured and recorded in real-time, and converted into the exergy storage amount at different operating load points. During the transient operation process, the real-time exergy storage amount of the boiler system is compared with the exergy storage amount at the corresponding steady-state load point, and the real-time exergy storage variation is obtained; thereafter, the feed-forward control signal of coal supply quantity input is superposed to the existing coal supply quantity command of the boiler system, and the coal supply quantity signal of the boiler system based on the exergy storage correction is finally generated.

Abstract: An optimized control method for a primary frequency regulation based on art exergy storage correction of a thermodynamic system of a coal-fired unit is provided. Through measuring and recording temperatures and pressures of working fluids and metal heating surfaces of the coal-fired unit thermodynamic system in real-time, an exergy storage amount of the thermodynamic system is obtained. During a transient process, according to an exergy storage variation before and after acting of each regulation scheme, a maximum power output of each scheme is obtained. Thereafter, through comparing the maximum power output with a power regulation quantity required by a power grid, an optimal primary frequency regulation control scheme is selected, so as to maintain a fast and stable grid frequency. The present invention reduces a selection blindness of the primary frequency regulation schemes, so that an operation flexibility of the coal-fired power unit during the transient processes is greatly improved.

Abstract: A solar aided coal-fired power generation system participating in primary frequency regulation and a control method thereof propose a system configuration with two regulation schemes by coupling medium-low-temperature solar collectors and a coal-fired generation unit. The two regulation schemes are a high-pressure feedwater bypass scheme and a low-pressure condensate bypass scheme. The present invention formulates a primary frequency regulation control logic, so as to efficiently and accurately participate in the primary frequency regulation, thereby keeping the power grid frequency rapidly stable. The present invention also formulates a working fluid outlet temperature control logic for the solar aided coal-fired thermal system, which adjusts a heat exchange working fluid flow of the solar collectors to ensure that the temperature in each section is stable during the primary frequency regulation.

Abstract: A 3D object detection method includes: obtaining two-dimensional (2D) coordinates of at least one predetermined key point of a target object in an image to be processed; constructing a pseudo 3D detection body of the target object in a 2D space according to the 2D coordinates of the at least one predetermined key point; obtaining depth information of a plurality of vertices of the pseudo 3D detection body; and determining a 3D detection body of the target object in a 3D space according to the depth information of the plurality of vertices of the pseudo 3D detection body.

Abstract: A method and device for cross-modal information retrieval, and a storage medium are provided. The method includes: acquiring first modal information and second modal information; performing feature fusion on a modal feature of the first modal information and a modal feature of the second modal information, and determining a first fused feature corresponding to the first modal information and a second fused feature corresponding to the second modal information; and determining the degree of similarity between the first modal information and the second modal information on the basis of the first fused feature and the second fused feature.