US 11,927,672 B2
Obstacle detection method and apparatus and storage medium
Bin Wang, Shenzhen (CN); and Leilei Shinohara, Shenzhen (CN)
Assigned to SUTENG INNOVATION TECHNOLOGY CO., LTD., Shenzhen (CN)
Filed by SUTENG INNOVATION TECHNOLOGY CO., LTD., Shenzhen (CN)
Filed on Mar. 1, 2023, as Appl. No. 18/116,245.
Application 18/116,245 is a continuation of application No. 17/835,907, filed on Jun. 8, 2022, granted, now 11,624,831.
Claims priority of application No. 202110641220.2 (CN), filed on Jun. 9, 2021; and application No. 202110641243.3 (CN), filed on Jun. 9, 2021.
Prior Publication US 2023/0204779 A1, Jun. 29, 2023
Int. Cl. G01S 17/89 (2020.01); G01S 17/931 (2020.01); G06V 20/58 (2022.01)
CPC G01S 17/89 (2013.01) [G01S 17/931 (2020.01); G06V 20/58 (2022.01)] 9 Claims
OG exemplary drawing
 
7. A data processing apparatus, comprising:
a MEMS solid-state LiDAR, a mechanical LiDAR, or a camera, configured to obtain detected data of an obstacle;
a storage module, configured to store the detected data of the obstacle;
a first obtaining module, configured to obtain K idle calculation blocks in real time, wherein K is greater than or equal to 1;
a calculation module, configured to: invoke first K pieces of detected data from a cache stack in a preset priority sequence of detected data, input the detected data into the K idle calculation blocks, and sequentially process K pieces of detected data on the K idle calculation blocks in the preset priority sequence, wherein each piece of detected data is corresponding to one detection range, a distance between a detection range corresponding to each piece of detected data and a preset target detection range is obtained, and a priority of each piece of detected data is determined with reference to obstacle information in each piece of detected data, to obtain the preset priority sequence; the obstacle information corresponding to each piece of detected data includes at least one of the following: number information of the obstacle, movement speed information of the obstacle, and distance information of the obstacle and the sensor;
an integration module, configured to: integrate sensing calculation results of the K pieces of detected data in real time based on a boundary relationship between detection ranges of the K pieces of detected data, and output a sensing result which comprises displaying, on a display, the sensing result; thereby ensuring real-time performance of obstacle detection;
a dividing module, configured to: before the calculation module invokes first K pieces of detected data from a cache stack in a preset priority sequence of detected data, and inputs the detected data into the K idle calculation blocks for sensing calculation, divide, into M pieces of detected data, one point cloud data frame obtained by a sensor, wherein M≥K; and
the storage module, configured to store data information of the detected data and priority information corresponding to the detected data into the cache stack each time one piece of detected data is obtained.