System and method for transforming video data into directional object count
The present invention is a computer-implemented system and method for transforming video data into directional object counts. The method of transforming video data is uniquely efficient in that it uses only a single column or row of pixels in a video camera to define the background from a moving object, count the number of objects and determine their direction. By taking an image of a single column or row every frame and concatenating them together, the result is an image of the object that has passed, referred to herein as a sweep image. In order to determine the direction, two different methods can be used. Method one involves constructing another image using the same method. The two images are then compared, and the direction is determined by the location of the object in the second image compared to the location of the object in the first image. Due to this recording method, elongation or compression of the objects can occur because of acceleration or deceleration of the objects and can be uniquely utilized to determine the speed or movement path of the objects. The second method of determining direction involves comparing the object in the image to an established marker. The transformations can also be used to produce labeled data for training machine learning models; bounding-boxes provided in sweep image can be transformed to bound boxes in video, and boxes in video can be transformed into boxes in the sweep image.
1 . A system for transforming a sequence of image data into moving object counts comprising:
a video camera including a video sensor, a video processor, and input/output for sequentially entering input images consisting of a single column containing a moving object region to be counted; and
a computer system receiving the input images consisting of a single column containing the moving object region to be counted from the video camera, creating a sweep image, and determining object counts by counting objects in the sweep image, the computer system further providing for machine learning and directional computation; and
a display that communicates the object count to an external system;
wherein the computer system applies sweep images for machine learning to search for the parameters that optimize sweep image-based transformation.
2 . The system according to claim 1 , wherein the computer system estimates an imaginary centerline.
3 . The system according to claim 1 , wherein data in the sweep image is used as training data.
4 . A system for transforming a sequence of image data into moving object counts comprising:
a video camera including a video sensor, a video processor, and input/output for sequentially entering input images consisting of a single column containing a moving object region to be counted; and
a computer system receiving the input images consisting of a single column containing the moving object region to be counted from the video camera, extracting 1-dimensional regions for each image and combining them into a 2-dimensional sweep image, and determining object counts by counting objects in the sweep image, the computer system further providing for machine learning and directional computation; and
a display that communicates the object count to an external system;
wherein the computer system applies sweep images for machine learning to search for the parameters that optimize sweep image-based transformation.
5 . A system for transforming a sequence of image data into moving object counts comprising:
a video camera including a video sensor, a video processor, and input/output for sequentially entering input images consisting of a single column containing a moving object region to be counted; and
a computer system receiving the input images consisting of a single column containing the moving object region to be counted from the video camera, extracting 1-dimensional regions for each image and combining them into a 2-dimensional sweep image, and determining object counts by counting objects in the sweep image, the computer system further providing for machine learning and directional computation; and
a display that communicates the object count to an external system;
wherein the computer system estimates an imaginary centerline and the imaginary centerline is determined by doing regression to optimize accuracy of direction of travel.
6 . A system for transforming a sequence of image data into moving object counts comprising:
a video camera including a video sensor, a video processor, and input/output for sequentially entering input images consisting of a single column containing a moving object region to be counted; and
a computer system receiving the input images consisting of a single column containing the moving object region to be counted from the video camera, extracting 1-dimensional regions for each image and combining them into a 2-dimensional sweep image, and determining object counts by counting objects in the sweep image, the computer system further providing for machine learning and directional computation; and
a display that communicates the object count to an external system;
wherein the computer system constructs the 2-dimensional sweep image by storing an identifier of each frame and wherein detected object location is then used to determine first and last frames when the object was passing over a back-projection of the 1-dimensional region, with frames of video then being used for training a machine learning model to optimize detection parameters from an original video.