Abstract: The present application discloses a method, an apparatus, a device for controlling traffic limitation and a storage medium, and belongs to the field of data processing. The method for controlling traffic limitation includes: acquiring, in response to a present request, a first timestamp of the present request; acquiring a pre-created traffic limitation instance, the traffic limitation instance including N storage blocks, a total number of instance requests, a traffic limitation request threshold number, an identifier of a storage block for a previous request, a second timestamp of the previous request and request waiting time; updating the traffic limitation instance based on a time interval between the first timestamp and the second timestamp, the unit time length, and the traffic limitation request threshold number; and determining whether to perform traffic limitation based on the request waiting time in the updated traffic limitation instance.

Abstract: The present application discloses a method, an apparatus, a device for controlling traffic limitation and a storage medium, and belongs to the field of data processing. The method for controlling traffic limitation includes: acquiring, in response to a present request, a first timestamp of the present request; acquiring a pre-created traffic limitation instance, the traffic limitation instance including N storage blocks, a total number of instance requests, a traffic limitation request threshold number, an identifier of a storage block for a previous request, a second timestamp of the previous request and request waiting time; updating the traffic limitation instance based on a time interval between the first timestamp and the second timestamp, the unit time length, and the traffic limitation request threshold number; and determining whether to perform traffic limitation based on the request waiting time in the updated traffic limitation instance.

Abstract: Disclosed is a method and device for regulating imaging accuracy of a motion-sensing camera. The method comprises: acquiring an infrared speckle pattern in a target infrared scene; recognizing an actual definition, an actual speckle regularity, and an actual central region brightness of the infrared speckle pattern; comparing the actual definition with a preset definition, the actual speckle regularity with a preset speckle regularity, and the actual central region brightness with a preset brightness; and adjusting an imaging focal length according to a comparison result, and completing regulation of the imaging accuracy. In this way, the method for regulating imaging accuracy of a motion-sensing camera of the present invention can obtain an infrared speckle pattern having required imaging accuracy.

Abstract: Disclosed is a method and device for regulating imaging accuracy of a motion-sensing camera. The method comprises: acquiring an infrared speckle pattern in a target infrared scene; recognizing an actual definition, an actual speckle regularity, and an actual central region brightness of the infrared speckle pattern; comparing the actual definition with a preset definition, the actual speckle regularity with a preset speckle regularity, and the actual central region brightness with a preset brightness; and adjusting an imaging focal length according to a comparison result, and completing regulation of the imaging accuracy. In this way, the method for regulating imaging accuracy of a motion-sensing camera of the present invention can obtain an infrared speckle pattern having required imaging accuracy.

Abstract: This application provides a depth-map-based ground detection method and apparatus. The method includes: screening first sample points according to depth values of points in a current depth map; determining space coordinates of the first sample points, and determining space heights of the first sample points according to current gravity acceleration information and the space coordinates; screening second sample points in the first sample points according to the space heights; determining an optimal ground equation according to space coordinates of the second sample points; and determining a ground point in the depth map by using the optimal ground equation. Because the accuracy of the sample points that undergo secondary screening is high, the ground detection precision is high. Because this application is not excessively dependent on a depth value, the calculation complexity is low, and operation can be performed on various hardware.

Abstract: A method of determining whether a ground is to be re-detected is provided. In an example, the method includes: an i-th gravitational acceleration vector corresponding to an i-th image frame is acquired from a collecting device; when the i-th gravitational acceleration vector changes relative to an (i?1)-th gravitational acceleration vector corresponding to an (i?1)-th image frame, a value is set to a flag bit of the i-th image frame; it is determined whether the collecting device tends to be stable after a motion according to a number of set flag bits in consecutive image frames; when the collecting device tends to be stable after the motion, a similarity between the i-th gravitational acceleration vector and a ground normal vector corresponding to a current ground equation is determined; and when the similarity is less than a similarity threshold, it is determined that the ground is to be re-detected.

Abstract: The present invention relates to a method for implementing a human skeleton tracking system based on depth data, specifically applied to a human skeleton tracking system based on depth data which is composed of a data acquisition unit, a limb segmentation unit, a skeleton point unit, and a tracking display unit. The units are in a relationship of sequential invocation. The limb segmentation unit uses scene depth data obtained after processing by the data acquisition unit to perform limb segmentation. The skeleton point unit uses the result obtained after segmentation by the limb segmentation unit to compute specific positions of respective skeleton points of a limb. The tracking display unit uses the positions of the skeleton points computed by the skeleton point unit to establish a skeleton model of the human body and perform tracking display.

Abstract: A method of determining whether a ground is to be re-detected is provided. In an example, the method includes: an i-th gravitational acceleration vector corresponding to an i-th image frame is acquired from a collecting device; when the i-th gravitational acceleration vector changes relative to an (i?1)-th gravitational acceleration vector corresponding to an (i?1)-th image frame, a value is set to a flag bit of the i-th image frame; it is determined whether the collecting device tends to be stable after a motion according to a number of set flag bits in consecutive image frames; when the collecting device tends to be stable after the motion, a similarity between the i-th gravitational acceleration vector and a ground normal vector corresponding to a current ground equation is determined; and when the similarity is less than a similarity threshold, it is determined that the ground is to be re-detected.

Abstract: This application provides a depth-map-based ground detection method and apparatus. The method includes: screening first sample points according to depth values of points in a current depth map; determining space coordinates of the first sample points, and determining space heights of the first sample points according to current gravity acceleration information and the space coordinates; screening second sample points in the first sample points according to the space heights; determining an optimal ground equation according to space coordinates of the second sample points; and determining a ground point in the depth map by using the optimal ground equation. Because the accuracy of the sample points that undergo secondary screening is high, the ground detection precision is high. Because this application is not excessively dependent on a depth value, the calculation complexity is low, and operation can be performed on various hardware.

Abstract: The present invention includes means of using a customized coprocessor to replace a main processor to process or interact with a data processing unit in a complex scene and reducing clock frequencies of the main processor and related modules, thereby achieving low power consumption of the three-dimensional measurement chip. The present invention includes: step 1: determining a system structure of a three-dimensional measurement processing chip; step 2: classifying data processing units according to scene requirements; step 3: adding coprocessors on a system bus; step 4: designing a customized coprocessor or small data control unit; step 5: designing a semi-customized coprocessor or small data control unit; step 6: optimizing software codes and reducing a clock frequency; step 7: verifying the chip to confirm that the chip satisfies design requirements. The present invention is applicable to a plurality of integrated circuits or any internetwork system consisting of a plurality of integrated circuits.

Abstract: The present invention relates to a method for implementing a human skeleton tracking system based on depth data, specifically applied to a human skeleton tracking system based on depth data which is composed of a data acquisition unit, a limb segmentation unit, a skeleton point unit, and a tracking display unit. The units are in a relationship of sequential invocation. The limb segmentation unit uses scene depth data obtained after processing by the data acquisition unit to perform limb segmentation. The skeleton point unit uses the result obtained after segmentation by the limb segmentation unit to compute specific positions of respective skeleton points of a limb. The tracking display unit uses the positions of the skeleton points computed by the skeleton point unit to establish a skeleton model of the human body and perform tracking display.

Abstract: The present invention includes means of using a customized coprocessor to replace a main processor to process or interact with a data processing unit in a complex scene and reducing clock frequencies of the main processor and related modules, thereby achieving low power consumption of the three-dimensional measurement chip. The present invention includes: step 1: determining a system structure of a three-dimensional measurement processing chip; step 2: classifying data processing units according to scene requirements; step 3: adding coprocessors on a system bus; step 4: designing a customized coprocessor or small data control unit; step 5: designing a semi-customized coprocessor or small data control unit; step 6: optimizing software codes and reducing a clock frequency; step 7: verifying the chip to confirm that the chip satisfies design requirements. The present invention is applicable to a plurality of integrated circuits or any internetwork system consisting of a plurality of integrated circuits.