Aggregating mapping tile data
Implementations relate to updating agricultural records that include inferences gathered by one or more sensors deployed at an agricultural location. The records are matched to mapping tiles of a mapping application and the mapping tile records are updated according to the updated data that was received. Implementations further include identifying parent tiles to each of the updated records, where a parent tile is an aggregation of multiple mapping tiles that can be utilized by a mapping application to render an interface that allows a user to view the data with varying degrees of granularity.
1. A method, implemented by one or more processors, comprising:
receiving an agricultural record, wherein the agricultural record includes a geographic location within an agricultural field and one or more agricultural inferences generated from sensor data that captures agricultural conditions at the geographic location;
identifying, based on the geographic location, a map tile record, wherein the map tile record corresponds to the geographic location, wherein the map tile record includes a first parent map tile record and a grandparent map tile record, wherein the first parent map tile record includes aggregated agricultural inferences aggregated from a plurality of adjacent map tile records and the grandparent map tile record includes aggregated agricultural inferences aggregated based on the first parent map tile record and a second parent map tile record, wherein the first parent map tile record and the second parent map tile record relate to a common map tile record;
updating the map tile record based on the one or more agricultural inferences;
updating the aggregated agricultural inferences of the first parent map tile record based on the one or more agricultural inferences of the updated map tile record;
generating a request to update the grandparent map tile record;
updating the grandparent map tile record based on a cluster of requests to update the grandparent map tile record, the cluster of requests clustered based on the first parent map tile record and the second parent map tile record, and the grandparent map tile record is updated based on the aggregated agricultural inferences of the first parent map tile record and the second parent map tile record; and
causing a mapping application to render a map that depicts the map tile record visually annotated in accordance with corresponding agricultural inferences.
2. The method of claim 1 , further including:
clustering multiple requests to update parent tiles based on map tile records that share a common parent map tile record; and
for each of the clusters:
identifying the common parent map tile record;
aggregating the agricultural inferences of map tiles of the cluster to generate aggregated agricultural conditions; and
updating the common parent map tile record based on the aggregated agricultural conditions.
3. The method of claim 1 , wherein the agricultural record was generated from one or more images captured by one or more imaging devices deployed at the geographic location.
4. The method of claim 1 , wherein the one or more agricultural inferences includes crop yield at the geographic location.
5. The method of claim 1 , further including a third map tile record that has a third parent map tile record that relates to the grandparent map tile record.
6. The method of claim 5 , further including:
clustering the requests to update the grandparent map tile record, wherein the requests include the first parent map tile record, the second parent map tile record, and the third parent map tile record; and
for each of the clusters:
identifying a common grandparent map tile record;
aggregating aggregated agricultural conditions of the parent map tile records included in the clustered requests to update the grandparent map tile record; and
updating the common grandparent map tile record based on the aggregation.
7. The method of claim 1 , wherein the one or more agricultural inferences includes leaf count at the geographic location.
8. The method of claim 1 , wherein causing the mapping application to render a map that depicts the map tile record includes rendering a plurality of map tile records as a heat map with respective colors that correspond to respective agricultural inferences.
9. A system comprising one or more processors and memory storing instructions that, in response to execution of the instructions by the one or more processors, cause the one or more processors to:
receive an agricultural record, wherein the agricultural record includes a geographic location within an agricultural field and one or more agricultural inferences generated from sensor data that captures agricultural conditions at the geographic location;
identify, based on the geographic location, a map tile record, wherein the map tile record corresponds to the geographic location, wherein the map tile record includes a first parent map tile record and a grandparent map tile record, wherein the first parent map tile record includes aggregated agricultural inferences aggregated from a plurality of adjacent map tile records and the grandparent map tile record includes aggregated agricultural inferences aggregated based on the first parent map tile record and a second parent map tile record, wherein the first parent map tile record and the second parent map tile record relate to a common map tile record;
update the map tile record based on the one or more agricultural inferences;
update the aggregated agricultural inferences of the first parent map tile record based on the one or more agricultural inferences of the updated map tile record;
generate a request to update the grandparent map tile record;
update the grandparent map tile record based on a cluster of requests to update the grandparent map tile record, the cluster of requests clustered based on the first parent map tile record and the second parent map tile record, and the grandparent map tile record is updated based on the aggregated agricultural inferences of the first parent map tile record and the second parent map tile record; and
cause a mapping application to render a map that depicts the map tile record visually annotated in accordance with corresponding agricultural inferences.
10. The system of claim 9 , wherein the instructions further include instructions to:
cluster multiple requests to update parent tiles based on map tile records that share a common parent map tile record; and
for each of the clusters:
identify the common parent map tile record;
aggregate the agricultural inferences of map tiles of the cluster to generate aggregated agricultural conditions; and
update the common parent map tile record based on the aggregated agricultural conditions.
11. The system of claim 9 , wherein the agricultural record was generated from one or more images captured by one or more imaging devices deployed at the geographic location.
12. The system of claim 9 , wherein the one or more agricultural inferences includes crop yield at the geographic location.
13. The system of claim 9 , further including a third map tile record that has a third parent map tile record that relates to the grandparent map tile record.
14. The system of claim 13 , wherein the instructions further include instructions to:
cluster the requests to update the grandparent map tile record, wherein the requests include the first parent map tile record, the second parent map tile record, and the third parent map tile record; and
for each of the clusters:
identify a common grandparent map tile record;
aggregate aggregated agricultural conditions of the parent map tile records included in the clustered requests to update the grandparent map tile record; and
update the common grandparent map tile record based on the aggregation.
15. The system of claim 9 , wherein the one or more agricultural inferences includes leaf count at the geographic location.
16. The system of claim 9 , wherein causing the mapping application to render a map that depicts the map tile record includes rendering a plurality of map tile records as a heat map with respective colors that correspond to respective agricultural inferences.
17. A non-transitory computer-readable medium for performing sparse depth estimation, the non-transitory computer-readable medium comprising instructions that, in response to execution of the instructions by a processor, cause the processor to:
receive an agricultural record, wherein the agricultural record includes a geographic location within an agricultural field and one or more agricultural inferences generated from sensor data that captures agricultural conditions at the geographic location;
identify, based on the geographic location, a map tile record, wherein the map tile record corresponds to the geographic location, wherein the map tile record includes a first parent map tile record and a grandparent map tile record, wherein the first parent map tile record includes aggregated agricultural inferences aggregated from a plurality of adjacent map tile records and the grandparent map tile record includes aggregated agricultural inferences aggregated based on the first parent map tile record and a second parent map tile record, wherein the first parent map tile record and the second parent map tile record relate to a common map tile record;
update the map tile record based on the one or more agricultural inferences;
update the aggregated agricultural inferences of the first parent map tile record based on the one or more agricultural inferences of the updated map tile record;
generate a request to update the grandparent map tile record;
update the grandparent map tile record based on a cluster of requests to update the grandparent map tile record, the cluster of requests clustered based on the first parent map tile record and the second parent map tile record, and the grandparent map tile record is updated based on the aggregated agricultural inferences of the first parent map tile record and the second parent map tile record; and
cause a mapping application to render a map that depicts the map tile record visually annotated in accordance with corresponding agricultural inferences.
18. The non-transitory computer-readable medium of claim 17 , further including instructions to:
cluster multiple requests to update parent tiles based on map tile records that share a common parent map tile record; and
for each of the clusters:
identify the common parent map tile record;
aggregate the agricultural inferences of map tiles of the cluster to generate aggregated agricultural conditions; and
update the common parent map tile record based on the aggregated agricultural conditions.
19. The non-transitory computer-readable medium of claim 17 , further including a third map tile record that has a third parent map tile record that relates to the grandparent map tile record.
20. The non-transitory computer-readable medium of claim 19 , further including instructions to:
cluster the requests to update the grandparent map tile record, wherein the requests include the first parent map tile record, the second parent map tile record, and the third parent map tile record; and
for each of the clusters:
identify a common grandparent map tile record;
aggregate aggregated agricultural conditions of the parent map tile records included in the clustered requests to update the grandparent map tile record; and
update the common grandparent map tile record based on the aggregation.