Granted Patent B2

US 9,842,266 · App. 14/614,746 · Granted Dec 12, 2017

Abstract

Claims (54)

1. A method for detecting electronic device use by a driver of a vehicle, the method comprising:

acquiring a first image including a vehicle from an associated non-multispectral image capture device positioned to view oncoming traffic, the first image including a windshield of the vehicle;

locating a first region of the vehicle in the first image;

processing pixels of the first region of the first image for computing a first feature vector describing a windshield region of the vehicle;

applying the first feature vector to a classifier for classifying the first image into respective classes including at least classes for candidate electronic device use and candidate electronic device non-use;

acquiring a second image including the vehicle from an associated non-multispectral image capture device positioned to view oncoming traffic, the second image including a front passenger side window or a driver side window of the vehicle;

locating a second region of the vehicle in the second image;

processing pixels of the second region of the second image for computing a second feature vector describing a side window region of the vehicle;

applying the second feature vector to a classifier for classifying the second image into respective classes including at least classes for candidate electronic device use and candidate electronic device non-use;

analyzing the first image to detect whether a passenger is present in the vehicle;

calculating a confidence score for each of the first and second images;

wherein the calculating the confidence score for the second image includes discounting the confidence score of the second image when a passenger is detected in the first image; and,

outputting the classification of the first image and the classification of the second image;

wherein processing the pixels in the images is performed by a process selected from a group consisting of:

a Successive Mean Quantization Transform (SMQT);

a Scale-Invariant Feature Transform (SIFT);

a Histogram of Gradients (HOG);

a Bag-of-Visual-Words Representation;

a Fisher Vector (FV) Representation; and,

a combination of the above.

2. The method of claim 1 , wherein processing the pixels of the located first region includes extracting the windshield region from the first image.

3. The method of claim 2 , further comprising defining a passenger side and a driver side within the windshield region, and extracting the driver side of the windshield region from the windshield region.

4. The method of claim 2 , further comprising defining a passenger side and a driver side within the windshield region, and extracting the passenger side of the windshield region from the windshield region.

5. The method of claim 1 , wherein the processing the pixels of the located second region includes extracting a passenger side window region from the image.

6. The method of claim 1 further comprising, before acquiring the images, training a classifier using at least a first sample image including a driver holding an electronic device and at least a second sample image including a driver not holding an electronic device, the first and second sample images including at least a corresponding first region or second region of a sample vehicle.

7. The method of claim 1 further comprising, in response to the vehicle being classified as a candidate electronic device user, performing further processing on at least one of the first or second images for determining whether the vehicle is a violator or non-violator.

8. The method of claim 1 , wherein the classification of the second image is discarded when a passenger is detected in the first image.

9. A system configured to perform image analysis for detecting electronic device use by a driver of a vehicle comprising:

at least one non-multispectral image capture device operably connected to a data processing device that captures a first image of a vehicle including a windshield region and a second image of the vehicle including a side window region; and

a processor-usable medium embodying computer code, said processor-usable medium being coupled to said data processing device, said computer code comprising instructions executable by said data processing device and configured for:

locating a windshield region of the vehicle in the first image;

processing pixels of the windshield region of the first image for computing a first feature vector describing the windshield region of the vehicle;

applying the first feature vector to a classifier for classifying the first image into respective classes including at least classes for candidate electronic device use and candidate electronic device non-use;

locating a side window region of the vehicle in the second image;

processing pixels of the side window region of the second image for computing a second feature vector describing the side window region of the vehicle;

applying the second feature vector to a classifier for classifying the second image into respective classes including at least classes for candidate electronic device use and candidate electronic device non-use;

analyzing the first image to detect whether a passenger is present in the vehicle;

calculating a confidence score for each of the first and second images;

wherein the calculating the confidence score for the second image includes discounting the confidence score of the second image when a passenger is detected in the first image; and,

outputting the classifications of the first and second images;

wherein processing the pixels in the images is performed by a process selected from a group consisting of:

a Successive Mean Quantization Transform (SMQT);

a Scale-Invariant Feature Transform (SIFT);

a Histogram of Gradients (HOG);

a Bag-of-Visual-Words Representation;

a Fisher Vector (FV) Representation; and,

a combination of the above.

10. The system as set forth in claim 9 , wherein said computer code comprising instructions executable by said data processing device is further configured for, after locating a windshield region of the vehicle in the first image, extracting the windshield region from the first image.

11. The system as set forth in claim 10 , wherein said computer code comprising instructions executable by said data processing device is further configured for defining a passenger side and a driver side within the windshield region, and extracting the driver side of the windshield region from the windshield region.

12. The system as set forth in claim 10 , wherein said computer code comprising instructions executable by said data processor device is further configured for defining a passenger side and a driver side within the windshield region, and extracting the passenger side of the windshield region from the windshield region.

13. The system as set forth in claim 9 , wherein said computer code comprising instructions executable by said data processing device is further configured for processing the pixels of the located side window region including extracting a passenger side window region from the second image.

14. The system as set forth in claim 9 , wherein said computer code comprising instructions executable by said data processing device is further configured for, prior to acquiring the images with the at least one image capture device, training a classifier using at least a first sample image including a driver holding an electronic device and at least a second sample image including a driver not holding an electronic device, the first and second sample images including at least a respective first region or second region of a sample vehicle.

15. The system as set forth in claim 9 , wherein said computer code comprising instructions executable by said data processing device is further configured for, in response to the vehicle being classified as a candidate electronic device user, performing further processing on the images for determining whether the vehicle is a violator or non-violator.

16. The system as set forth in claim 9 , wherein said computer code comprising instructions executable by said data processing device is further configured to discard the classification of the second image when a passenger is detected in the first image.

Assignments (8)