System and method of predicting human interaction with vehicles
Systems and methods for predicting user interaction with vehicles. A computing device receives an image and a video segment of a road scene, the first at least one of an image and a video segment being taken from a perspective of a participant in the road scene and then generates stimulus data based on the image and the video segment. Stimulus data is transmitted to a user interface and response data is received, which includes at least one of an action and a likelihood of the action corresponding to another participant in the road scene. The computing device aggregates a subset of the plurality of response data to form statistical data and a model is created based on the statistical data. The model is applied to another image or video segment and a prediction of user behavior in the another image or video segment is generated.
1. A computer-implemented method comprising:
storing a plurality of images, each image displaying one or more users;
generating training data from the plurality of images, the generating comprising, for each image:
sending the image to a plurality of human observers, each human observer presented with a request to answer a question about a state of mind of a user in the image,
receiving, from each of the plurality of human observers, a response representing a judgment by the human observer of the state of mind of the user in the image,
generating summary statistics describing the state of mind of the user in the image based on the received responses from the plurality of human observers, and
storing the summary statistics in association with the image as part of the training data;
training a model using the training data, the model configured to receive an input image showing a user and predict summary statistics describing a state of mind of the user in the input image; and
executing the trained model to predict a state of mind of a user in a new image.
2. The computer-implemented method of claim 1 , wherein the image is manipulated by adjusting values of pixels of the image before presenting to a human ob server.
3. The computer-implemented method of claim 1 , wherein the state of mind of the user in the image indicates whether the user is likely to perform a predetermined action.
4. The computer-implemented method of claim 1 , wherein the state of mind of the user in the image represents a measure of awareness of the user regarding an object.
5. The computer-implemented method of claim 1 , wherein the response from a human observer comprises a rating on an ordinal scale.
6. The computer-implemented method of claim 1 , wherein the model is one of:
a random forest regressor,
a support vector regressor,
a simple neural network,
a deep convolutional neural network,
a recurrent neural network,
or a long short-term memory (LSTM) neural network.
7. The computer-implemented method of claim 1 , wherein the summary statistics is associated with at least one of a content of a response, a time associated with entering a response, and a position of an eye of a human observer associated with the response, the position being measured with respect to a display associated with the image.
8. A non-transitory computer readable storage medium storing instructions that when executed by one or more processors, cause the one or more processors to perform steps comprising:
storing a plurality of images, each image displaying one or more users;
generating training data from the plurality of images, the generating comprising, for each image:
sending the image to a plurality of human observers, each human observer presented with a request to answer a question about a state of mind of a user in the image,
receiving, from each of the plurality of human observers, a response representing a judgment by the human observer of the state of mind of the user in the image,
generating summary statistics describing the state of mind of the user in the image based on the received responses from the plurality of human observers, and
storing the summary statistics in association with the image as part of the training data;
training a model using the training data, the model configured to receive an input image showing a user and predict summary statistics describing a state of mind of the user in the input image; and
executing the trained model to predict a state of mind of a user in a new image.
9. The non-transitory computer readable storage medium of claim 8 , wherein the image is manipulated by adjusting values of pixels of the image before presenting to a human observer.
10. The non-transitory computer readable storage medium of claim 8 , wherein the state of mind of the user in the image indicates whether the user is likely to perform a predetermined action.
11. The non-transitory computer readable storage medium of claim 8 , wherein the state of mind of the user in the image represents a measure of awareness of the user regarding an object.
12. The non-transitory computer readable storage medium of claim 8 , wherein the response from a human observer comprises a rating on an ordinal scale.
13. The non-transitory computer readable storage medium of claim 8 , wherein the model is one of:
a random forest regressor,
a support vector regressor,
a simple neural network,
a deep convolutional neural network,
a recurrent neural network,
or a long short-term memory (LSTM) neural network.
14. The non-transitory computer readable storage medium of claim 8 , wherein the summary statistics is associated with at least one of a content of a response, a time associated with entering a response, and a position of an eye of a human observer associated with the response, the position being measured with respect to a display associated with the image.
15. A computing system comprising:
one or more processors; and
a non-transitory computer readable storage medium, storing instructions that when executed by the one or more processors, cause the one or more processors to perform steps comprising:
storing a plurality of images, each image displaying one or more users;
generating training data from the plurality of images, the generating comprising, for each image:
sending the image to a plurality of human observers, each human observer presented with a request to answer a question about a state of mind of a user in the image,
receiving, from each of the plurality of human observers, a response representing a judgment by the human observer of the state of mind of the user in the image,
generating summary statistics describing the state of mind of the user in the image based on the received responses from the plurality of human observers, and
storing the summary statistics in association with the image as part of the training data;
training a model using the training data, the model configured to receive an input image showing a user and predict summary statistics describing a state of mind of the user in the input image; and
executing the trained model to predict a state of mind of a user in a new image.
16. The computing system of claim 15 , wherein the summary statistics is associated with at least one of a content of a response, a time associated with entering a response, and a position of an eye of a human observer associated with the response, the position being measured with respect to a display associated with the image.
17. The computing system of claim 15 , wherein the state of mind of the user in the image indicates whether the user is likely to perform a predetermined action.
18. The computing system of claim 15 , wherein the state of mind of the user in the image represents a measure of awareness of the user regarding an object.
19. The computing system of claim 15 , wherein the response from a human observer comprises a rating on an ordinal scale.