Enhanced tracking and speed detection

1 . A computer-implemented method for tracking an object, the computer-implemented method comprising:

determining a motion of the object within a time frame based on data received from a sensing system, wherein:

the data includes current data from a current time frame and previous data from a previous time frame, and

the determining the motion of the object includes associating the current data with the previous data to find a match of the object in the current data and the previous data;

determining an estimation of the current data based on the previous data and the motion;

splitting the time frame into a plurality of sub-intervals; and

determining, using a tracking system, a position of the object in a next time frame based on sub-motions of the object within the plurality of sub-intervals.

2 . The computer-implemented method of claim 1 , wherein the associating the current data with the previous data includes:

creating abstract features in the current data and the previous data to associate a detection of the object in the current data to a detection of the object in the previous data; and

finding the match of the object in the current data and the previous data based on the abstract features.

3 . The computer-implemented method of claim 2 , wherein the determining the motion of the object is based on the detection of the object in the current data and the detection in the previous data to find an offset of the object from the previous data to the current data.

4 . The computer-implemented method of claim 3 , wherein the determining the motion is further based on tracking information of the object in the previous data.

5 . The computer-implemented method of claim 4 , further comprising shifting the current data and the motion by a sub-interval of the plurality of sub-intervals to align the tracking information and the abstract features in the current time frame with the position of the object in the next time frame.

6 . The computer-implemented method of claim 2 , further comprising integrating and weighting the previous data and the current data for use in the tracking system.

7 . The computer-implemented method of claim 6 , wherein integrating and weighting includes removing information of at least one of the current data or the previous data.

8 . The computer-implemented method of claim 6 , wherein integrating and weighting includes:

refining the abstract features based on the previous data and the current data to form refined data; and

combining the previous data and the refined data.

9 . The computer-implemented method of claim 1 , wherein the determining the estimation includes shifting the previous data by a sub-interval of the plurality of sub-intervals to align the previous data with the current data.

10 . The computer-implemented method of claim 9 , further comprising applying the sub-interval to the previous data one or more times to align the previous data with the current data.

11 . The computer-implemented method of claim 9 , further comprising obtaining one or more intermediate positions of the object in response to shifting by the sub-interval.

12 . The computer-implemented method of claim 9 , further comprising:

applying the sub-interval to the previous data one or more times to align the previous data with the current data; and

obtaining one or more intermediate positions of the object in response to shifting by the sub-interval.

13 . The computer-implemented method of claim 1 , wherein:

the object is located in a vicinity of a vehicle; and

at least one of the determining the motion, the splitting the time frame, or the determining the position is performed in the vehicle.

14 . A processing apparatus comprising:

storage hardware configured to store instructions; and

at least one processor configured to execute the instructions, wherein the instructions include:

determining a motion of an object within a time frame based on data received from a sensing system, wherein:

the data includes current data from a current time frame and previous data from a previous time frame, and

the determining the motion of the object includes associating the current data with the previous data to find a match of the object in the current data and the previous data;

determining an estimation of the current data based on the previous data and the motion;

splitting the time frame into a plurality of sub-intervals; and

determining, using a tracking system, a position of the object in a next time frame based on sub-motions of the object within the plurality of sub-intervals.

15 . A non-transitory computer-readable medium comprising instructions including:

determining a motion of an object within a time frame based on data received from a sensing system, wherein:

the data includes current data from a current time frame and previous data from a previous time frame, and

the determining the motion of the object includes associating the current data with the previous data to find a match of the object in the current data and the previous data;

determining an estimation of the current data based on the previous data and the motion;

splitting the time frame into a plurality of sub-intervals; and

determining, using a tracking system, a position of the object in a next time frame based on sub-motions of the object within the plurality of sub-intervals.