Electronic device, method, and computer readable storage medium for detection of vehicle appearance
According to various embodiments, an electronic device include a display, an input circuit, at least one memory and at least one processor configured to obtain a first image; display, in response to cropping an area comprising a visual object corresponding to a potential vehicle appearance from the first image, fields for inputting an attribute for the area, wherein, the fields include a first field for inputting a vehicle type as the attribute and a second field for inputting a positional relationship between a subject corresponding to the potential vehicle appearance and a camera obtained the first image as the attribute; obtain information about the attribute, by receiving a user input for each of the fields including the first field and the second field through the input circuit; store a second image configured of the area in a data set for training a computer vision model for vehicle detection.
1 . A non-transitory computer readable storage medium storing one or more programs, the one or more programs comprising instructions which, when executed by an electronic device with a display and input circuitry, cause the electronic device to:
display, via the display, an electronic map;
receive, via the input circuitry, an input on a position of the electronic map;
based on the input, display, via the display, a road view image representing the position of the electronic map;
based on the road view image being identified as a first image including a visual object corresponding to a potential vehicle appearance, crop an area including the visual object from the first image, and display, via the display, user interface (UI) fields for inputting an attribute for the area, wherein the fields include a first UI field for inputting a vehicle type as the attribute and a second UI field for inputting a position relationship between a subject corresponding to the potential vehicle appearance and a camera obtained the first image as the attribute;
receive, via the input circuitry, a user input for each of the UI fields;
based on the user input, obtain information on the attribute including the vehicle type of the visual object and the position relationship between the subject and the camera;
based on obtaining the information, store a second image configured of the area in conjunction with the information in a data set;
identify feature points from the data set; and
provide the feature points to a computer vision model for training the computer vision model for vehicle detection.
2 . The non-transitory computer readable storage medium of claim 1 , wherein the displayed UI fields further comprise a third UI field for inputting illuminance when obtaining the first image via the camera as the attribute.
3 . The non-transitory computer readable storage medium of claim 2 , wherein the displayed UI fields further comprise a fourth UI field for inputting a color of the subject as the attribute.
4 . The non-transitory computer readable storage medium of claim 3 , wherein the displayed UI fields further comprise a fifth UI field for inputting whether the visual object represents a state in which a part of the subject is covered by an object positioned between the subject and the camera as the attribute.
5 . The non-transitory computer readable storage medium of claim 1 , wherein the one or more programs comprises instructions which, when executed by the electronic device, cause the electronic device to:
based on the road view image being identified as the first image including the visual object, recognize that the visual object is included in the first image;
based on the recognition, identify a first area including the visual object, wherein a width of the first area is wider than the width of the area;
detect, by executing Sobel operation on the first area, first vertical edges with respect to the left side of the first area based on the vertical center line of the first area and second vertical edges with respect to the right side of the first area based on the vertical center line;
identify the area having a portion corresponding to the maximum value among the accumulated values of the vertical histogram for the first vertical edges as the left boundary and a portion corresponding to the maximum value among the accumulated values of the vertical histogram for the second vertical edges as a right boundary, from the first area; and
crop the area from the first image.
6 . The non-transitory computer readable storage medium of claim 1 , wherein the computer vision model is trained to detect a visual object corresponding to an appearance of a vehicle in an image obtained via a camera of a moving vehicle by using the data set.
7 . The non-transitory computer readable storage medium of claim 1 , wherein the visual object in the first image displays a rear of a vehicle including at least one tail lamp.
8 . The non-transitory computer readable storage medium of claim 1 , the one or more programs comprising instructions which, when executed by the electronic device, cause the electronic device to:
based on the road view image being identified as a third image being not including a visual object corresponding to a potential vehicle appearance, display, via, the display, another road view image representing another position of the electronic map; and
based on the another road view image being identified as the first image including the visual object, crop the area from the first image, and display, via the display, the user interface (UI) fields.
9 . The non-transitory computer readable storage medium of claim 1 , when executed by the electronic device, cause the electronic device to:
based on the road view image being identified as the third image being not including a visual object corresponding to a potential vehicle appearance, change the position of the electronic map to the another position of the electronic map without a user input; and
display, via, the display, the another road view image representing the another position of the electronic map by changing the position of the electronic map to the another position of the electronic map.
10 . The non-transitory computer readable storage medium of claim 1 , the one or more programs comprising instructions which, when executed by the electronic device, cause the electronic device to:
based on the road view image being identified as a third image being not including a visual object corresponding to a potential vehicle appearance, display, another road view image representing the position of the electronic map by changing an orientation of the road view image; and
based on the another road view image being identified as the first image including the visual object, crop the area from the first image, and display, via the display, the UI fields.