# US 2019/0317218 A1 · Ground environment detection method and apparatus > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2019/0317218 A1 - Document ID: US20190317218A1 - Status: Published application - Kind: A1 - Application number: 16/456,057 - Filed: 2019-06-28 - Published: 2019-10-17 - Earliest claimed: 2016-12-29 - Assignees: Huawei Technologies Co., Ltd. - Applicants: Huawei Technologies Co., Ltd. - Inventors: Tongtong CAO; Yunfeng SHAO; Jun YAO - Web page: https://patentgrep.com/patent/US20190317218A1 ## CPC - G01S 7/4802: {using analysis of echo signal for target characterisation; Target signature; Target cross-section} - G01S 7/4808: {Evaluating distance, position or velocity data} - G01S 17/42: Simultaneous measurement of distance and other co-ordinates (indirect measurement G01S17/46) - G01S 17/87: Combinations of systems using electromagnetic waves other than radio waves - G01S 17/93: for anti-collision purposes - G01S 17/931: of land vehicles - G06F 18/23213: with fixed number of clusters, e.g. K-means clustering - G06F 18/251: {of input or preprocessed data} - G06F 18/253: {of extracted features} - G06N 3/02: Neural networks - G06N 3/08: Learning methods - G06N 3/09: Supervised learning - G06V 10/22: by selection of a specific region containing or referencing a pattern; Locating or processing of specific regions to guide the detection or recognition - G06V 10/60: relating to illumination properties, e.g. using a reflectance or lighting model - G06V 10/763: {Non-hierarchical techniques, e.g. based on statistics of modelling distributions} - G06V 10/764: using classification, e.g. of video objects - G06V 10/803: {of input or preprocessed data} - G06V 10/806: {of extracted features} - G06V 10/82: using neural networks - G06V 20/56: exterior to a vehicle by using sensors mounted on the vehicle - G01S: RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS - G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING ## Abstract A ground environment detection method and apparatus are disclosed, where the method includes: scanning a ground environment by using laser sounding signals having different operating wavelengths, receiving a reflected signal that is reflected back by the ground environment, determining scanning spot information of each scanning spot of the ground environment based on the reflected signal, determining space coordinate information and a laser reflection feature of each scanning spot based on each piece of scanning spot information, partitioning the ground environment into sub-regions having different laser reflection features, and determining a ground environment type of each sub-region. Lasers having different operating wavelengths are used to scan the ground, and the ground environment type is determined based on the reflection intensity of the ground environment under different wavelengths of lasers, thereby improving a perception effect of a complex ground environment, and better determining a passable road surface. ## Claims ### Claim 1 A ground environment detection method, comprising: scanning a ground environment by using laser sounding signals having different operating wavelengths; receiving a reflected signal that is reflected back by the ground environment for the sounding signal; determining scanning spot information of each scanning spot of the ground environment based on the reflected signal, wherein the scanning spot information comprises a direction angle, a distance, and laser reflection intensity of the scanning spot relative to a laser radar; determining space coordinate information and a laser reflection feature of each scanning spot based on each piece of scanning spot information; partitioning the ground environment into sub-regions having different laser reflection features, wherein the laser reflection feature comprises reflectivity on lasers having different wavelengths; and determining a ground environment type of each sub-region. ### Claim 2 (depends on 1) The method according to claim 1, wherein the determining a ground environment type of each sub-region comprises: determining the ground environment type of each sub-region based on a laser reflection feature of each type of ground environment. ### Claim 3 (depends on 1) The method according to claim 1, wherein the determining a ground environment type of each sub-region comprises: inputting a laser reflection feature of each sub-region into a neural network to obtain the ground environment type of each sub-region that is output by the neural network, wherein a data model that is used by the neural network to distinguish between different types of ground environments is obtained by using a group of data, which uses data of reflectivity of different ground environments on the lasers having different wavelengths as an input and the ground environment type as an output as a sample data set for training. ### Claim 4 (depends on 1) The method according to claim 1, wherein the determining space coordinate information and a laser reflection feature of each scanning spot based on each piece of scanning spot information, and the partitioning the ground environment into sub-regions having different laser reflection features comprises: transforming location information of each scanning spot onto a same coordinate system based on the scanning spot information of each scanning spot and an installation position of each laser radar; determining the space coordinate information and the laser reflection feature of each scanning spot by fusing the scanning spot information of each scanning spot that is obtained by each laser radar; and performing region partition based on the space coordinate information and the laser reflection feature of each scanning spot to partition the ground environment into the sub-regions having different laser reflection features. ### Claim 5 (depends on 1) The method according to claim 1, wherein the determining space coordinate information and a laser reflection feature of each scanning spot based on each piece of scanning spot information, and the partitioning the ground environment into sub-regions having different laser reflection features comprises: separately performing region partition, based on the scanning spot information, on the scanning spot that is obtained by each laser radar, to generate sub-regions after clustering in which each laser radar has different laser reflection intensity; transforming location information of the sub-region after clustering of each laser radar onto a same coordinate system; fusing scanning spot information of each scanning spot in the sub-region after clustering of each laser radar based on location information of a transformed sub-region; and partitioning the ground environment into the sub-regions having different laser reflection features. ### Claim 6 (depends on 4) The method according to claim 4, wherein region partition is performed in a region growing manner or a K-means manner. ### Claim 7 A ground environment detection device, comprising: a laser radar, the laser radar configured to: scan a ground environment by using laser sounding signals having different operating wavelengths; and receive a reflected signal that is reflected back by the ground environment for the sounding signal; at least one processor; a non-transitory computer-readable storage medium coupled to the processor and storing programming instructions for execution by the processor, the programming instructions instruct the at least one processor to: determine scanning spot information of each scanning spot of the ground environment based on the reflected signal, wherein the scanning spot information comprises a direction angle, a distance, and laser reflection intensity of the scanning spot relative to a laser radar; determine space coordinate information and a laser reflection feature of each scanning spot based on each piece of scanning spot information, and partition the ground environment into sub-regions having different laser reflection features, wherein the laser reflection feature comprises reflectivity on lasers having different wavelengths; and determine a ground environment type of each sub-region. ### Claim 8 (depends on 7) The detection device according to claim 7, wherein the instructions instruct the at least one processor to: determine the ground environment type of each sub-region based on a laser reflection feature of each type of ground environment. ### Claim 9 (depends on 7) The detection device according to claim 7, wherein instructions instruct the at least one processor to: input a laser reflection feature of each sub-region into a neural network to obtain the ground environment type of each sub-region that is output by the neural network, wherein a data model that is used by the neural network to distinguish between different types of ground environments is obtained by using a group of data, which uses data of reflectivity of different ground environments on the lasers having different wavelengths as an input and the ground environment type as an output, as a sample data set for training. ### Claim 10 (depends on 7) The detection device according to claim 7, wherein the instructions instruct the at least one processor to: transform location information of each scanning spot onto a same coordinate system based on the scanning spot information of each scanning spot and an installation position of each laser radar; determine the space coordinate information and the laser reflection feature of each scanning spot by fusing the scanning spot information of each scanning spot that is obtained by each laser radar; and perform region partition based on the space coordinate information and the laser reflection feature of each scanning spot to partition the ground environment into the sub-regions having different laser reflection features. ### Claim 11 (depends on 7) The detection device according to claim 7, wherein the instructions instruct the at least one processor to: separately perform region partition, based on the scanning spot information, on the scanning spot that is obtained by each laser radar, to generate sub-regions after clustering in which each laser radar has different laser reflection intensity; transform location information of the sub-region after clustering of each laser radar onto a same coordinate system fuse scanning spot information of each scanning spot in the sub-region after clustering of each laser radar based on location information of a transformed sub-region; and partition the ground environment into the sub-regions having different laser reflection features. ### Claim 12 (depends on 10) The detection device according to claim 10, wherein the instructions instruct the at least one processor to perform region partition in a region growing manner or a K-means manner. ### Claim 13 A ground environment detection device, comprising: a laser scanning unit, the laser scanning unit configured to: scan a ground environment by using laser sounding signals having different operating wavelengths, and receive a reflected signal that is reflected back by the ground environment for the sounding signal; and a data processing unit, comprising at least one processor and a memory, wherein the memory is configured to store a computer execution instruction, and the at least one processor performs the computer execution instruction and is configured to: determine scanning spot information of each scanning spot of the ground environment based on the reflected signal; determine space coordinate information and a laser reflection feature of each scanning spot based on each piece of scanning spot information; partition the ground environment into sub-regions having different laser reflection features; and determine a ground environment type of each sub-region, wherein the scanning spot information comprises a direction angle, a distance, and laser reflection intensity of the scanning spot relative to the laser scanning unit, and wherein the laser reflection feature comprises reflectivity on lasers having different wavelengths. ### Claim 14 (depends on 13) The detection device according to claim 13, wherein the at least one processor is configured to: determine the ground environment type of each sub-region based on a laser reflection feature of each type of ground environment. ### Claim 15 (depends on 13) The detection device according to claim 13, wherein the at least one processor is configured to: input a laser reflection feature of each sub-region into a neural network to obtain the ground environment type of each sub-region that is output by the neural network, wherein a data model that is used by the neural network to distinguish between different types of ground environments is obtained by using a group of data, which uses data of reflectivity of different ground environments on the lasers having different wavelengths as an input and the ground environment type as an output, as a sample data set for training. ### Claim 16 (depends on 13) The detection device according to claim 13, wherein the at least one processor is configured to: transform location information of each scanning spot onto a same coordinate system based on the scanning spot information of each scanning spot and an installation position of each laser radar, and; determine the space coordinate information and the laser reflection feature of each scanning spot by fusing the scanning spot information of each scanning spot that is obtained by each laser radar; and perform region partition based on the space coordinate information and the laser reflection feature of each scanning spot to partition the ground environment into the sub-regions having different laser reflection features. ### Claim 17 (depends on 13) The detection device according to claim 13, wherein the at least one processor is configured to: separately perform region partition, based on the scanning spot information, on the scanning spot that is obtained by each laser radar, to generate sub-regions after clustering in which each laser radar has different laser reflection intensity; transform location information of the sub-region after clustering of each laser radar onto a same coordinate system; fuse scanning spot information of each scanning spot in the sub-region after clustering of each laser radar based on location information of a transformed sub-region; and partition the ground environment into the sub-regions having different laser reflection features. ### Claim 18 (depends on 16) The detection device according to claim 16, wherein the at least one processor performs region partition in a region growing manner or a K-means manner.