Vehicle counting and emission estimation
First Claim
Patent Images
1. A method comprising:
- receiving image data of vehicles on a path;
performing, using a processor, low level feature extraction on the image data;
selecting a regression strategy based on a traffic measurement for the path, wherein the regression strategy includes the low level feature extraction; and
estimating exhaust levels produced by the vehicles based on the low level feature extraction,wherein inputs to the regression strategy includes only the low level feature extraction when the traffic measurement is a low level.
3 Assignments
0 Petitions
Accused Products
Abstract
A computing device, for example, receives image data of vehicles on a path captured by a camera. The image is analyzed using a low level feature extraction on the image data. The computing device estimates exhaust levels produced by the vehicles based on the low level feature extraction or based on vehicle classifications and quantities determined from the low level feature extraction.
4 Citations
21 Claims
-
1. A method comprising:
-
receiving image data of vehicles on a path; performing, using a processor, low level feature extraction on the image data; selecting a regression strategy based on a traffic measurement for the path, wherein the regression strategy includes the low level feature extraction; and estimating exhaust levels produced by the vehicles based on the low level feature extraction, wherein inputs to the regression strategy includes only the low level feature extraction when the traffic measurement is a low level. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8, 9)
-
-
10. A method comprising:
-
receiving image data of vehicles on a path; performing, using a processor, low level feature extraction on the image data; and estimating exhaust levels produced by the vehicles based on the low level feature extraction, wherein performing low level feature extraction on the image data comprises; identifying, from the low level feature extraction, a quantity for a first vehicle class from the image data of vehicles on the path; and identifying, from the low level feature extraction and the quantity for the first vehicle class, a quantity for a second vehicle class from the image data of vehicles on the path; and concatenating data for the quantity for the first vehicle class to a feature vector for the low level feature extraction.
-
-
11. An apparatus comprising:
-
at least one processor; and at least one memory including computer program code for one or more programs; the at least one memory and the computer program code configured to, with the at least one processor, cause the apparatus to at least perform; receiving image data of vehicles on a path; performing low level feature extraction on the image data; identifying, based on the low level feature extraction, a quantity for a first vehicle class from the image data of vehicles on the path; identifying, based on the low level feature extraction and the quantity for the first vehicle class, a quantity for a second vehicle class from the image data of vehicles on the path; and concatenating data for the first vehicle class and data for the second vehicle class to define a feature vector. - View Dependent Claims (12, 13, 14, 15, 16, 17)
-
-
18. A non-transitory computer readable medium including instructions that when executed on a computer are operable to:
-
receiving image data of vehicles on a path; selecting a regression strategy from a plurality of regression strategies based on a traffic measurement for the path, wherein the traffic measurement includes a traffic speed or a traffic level, wherein the regression strategy includes a low level feature extraction; and estimating exhaust levels for the vehicles based on the regression strategy. - View Dependent Claims (19, 20)
-
-
21. A non-transitory computer readable medium including instructions that when executed on a computer are operable to:
-
receiving image data of vehicles on a path; selecting a regression strategy based on a traffic measurement for the path, wherein the regression strategy includes a low level feature extraction; and estimating exhaust levels for the vehicles based on the regression strategy, wherein inputs to the regression strategy include only the low level feature extraction when the traffic measurement is a low level.
-
Specification