System of vehicles equipped with imaging equipment for high-definition near real-time map generation
Described are street level intelligence platforms, systems, and methods that can include a fleet of swarm vehicles having imaging devices. Images captured by the imaging devices can be used to produce and/or be integrated into maps of the area to produce high-definition maps in near real-time. Such maps may provide enhanced street level intelligence useful for fleet management, navigation, traffic monitoring, and/or so forth.
1. A method, comprising:
receiving video depicting street segments from vehicle-mounted smartphones;
bucketizing the video into buckets that are separately associated with segments of the video capturing a street segment from the street segments by one of the vehicle-mounted smartphones;
identifying (i) a selected segment of the street segments for which no video is received during a time interval and (ii) adjacent segments that are adjacent to the selected segment;
calculating a number of pedestrians for each of the adjacent segments during the time interval using image recognition and pedestrian counts for the adjacent segments by dividing the number of pedestrians for each of the adjacent segments by a number of video frames associated with the adjacent segments; and
estimating a pedestrian count for the selected segment according to an average of the pedestrian counts associated with the adjacent segments.
2. The method of claim 1 , wherein video depicting a particular street segment from the street segments is received irregularly.
3. The method of claim 1 , wherein estimating the pedestrian count includes generating histograms of the pedestrian counts observed for the adjacent segments on an hourly basis.
4. A system, comprising:
a processor; and
a memory storing instructions that, when executed by the processor, cause the processor to:
receive video depicting street segments from vehicle-mounted smartphones;
bucketize the video into buckets that are separately associated with segments of the video capturing a street segment from the street segments by one of the vehicle-mounted smartphones;
identify (i) a selected segment of the street segments for which no video is received during a time interval and (ii) adjacent segments that are adjacent to the selected segment;
calculate a number of pedestrians for each of the adjacent segments during the time interval using image recognition and pedestrian counts for the adjacent segments by dividing the number of pedestrians for each of the adjacent segments by a number of video frames associated with the adjacent segments; and
estimate a pedestrian count for the selected segment according to an average of the pedestrian counts associated with the adjacent segments.
5. A non-transitory computer-readable medium storing instructions that, when execute by an electronic processor, cause the electronic processor to:
receive video depicting street segments from vehicle-mounted smartphones;
bucketize the video into buckets that are separately associated with segments of the video capturing a street segment from the street segments by one of the vehicle-mounted smartphones;
identify (i) a selected segment of the street segments for which no video is received during a time interval and (ii) adjacent segments that are adjacent to the selected segment;
calculate a number of pedestrians for each of the adjacent segments during the time interval using image recognition and pedestrian counts for the adjacent segments by dividing the number of pedestrians for each of the adjacent segments by a number of video frames associated with the adjacent segments; and
estimate a pedestrian count for the selected segment according to an average of the pedestrian counts associated with the adjacent segments.