Moving object detection
Systems and methods for detecting moving objects are provided. Systems illustratively include an image acquisition component, an image processing component, and a display component. Image acquisition components capture image data over a wide spatial area. Image processing components have dedicated algorithms for change detection and receive captured image data from image acquisition components. Image processing components utilize the captured data and the dedicated algorithms to perform image change detection. Display components receive processed image data from image processing components and provide visual indications that items of interest have been detected. Methods illustratively include obtaining first and second images covering a wide field-of-view. The second image is registered to and compared to the first image. Based at least in part on the comparison, a moving object within the wide field-of-view is detected. An indication of the moving object is provided.
1. A method for detecting a moving object, the method comprising:
receiving a first series of image data for a plurality of frames, each frame of the plurality of frames covering a separate portion of a wide field-of-view and the plurality of frames together covering all of the wide field-of-view;
receiving a second series of image data for the plurality of frames;
using a digital processing component to compare image data of multiple frames of the plurality of frames from the first series of image data to image data of the multiple frames from the second series of image data to detect the moving object within the wide field-of-view;
providing an indication of the moving object;
a processing component determining if the first series of image data contains overlaps or gaps, wherein overlaps comprise portions of images in the series of image data that contain overlapping content, and wherein gaps comprise sections of the wide field of view missing from the series of image data; and
the processing component automatically altering angular positions for a scan mirror to minimizing overlaps and gaps in the first series of image data.
2. The method of claim 1 , wherein the indication of the moving object is a visual mark on a display screen, and wherein the method further comprises:
recording an indication of spatial information for each of the frames within the plurality of frames, wherein spatial information comprises an indication of a physical position of each frame within the wide field-of-view.
3. The method of claim 2 , wherein the display screen includes a graphical representation of the wide field-of-view, wherein providing an indication of the moving object includes highlighting the moving object, and wherein the method further comprises:
retrieving a portion of the image data based at least in part on the spatial information.
4. The method of claim 2 , wherein the indication of the spatial information further comprises at least one of a position of a scan mirror and a frame number.
5. The method of claim 1 , further comprising:
using the digital processing component to detect a plurality of moving objects within the wide field of view; and
providing an indication of each of the plurality of moving objects.
6. The method of claim 2 , and further comprising:
recording an indication of time information for each of the frames of image data within the first series of image data and the second series of image data.
7. The method of claim 6 , and further comprising:
retrieving the first series of image data based at least in part on the time information.
8. The method of claim 6 , wherein the time information includes a time stamp.
9. The method of claim 1 , wherein comparing comprises a linear independence test, and wherein the method further comprises:
annotating the image data based on detection changes.
10. The method of claim 1 , wherein comparing comprising a vectorized test and wherein the method further comprises:
detecting changes in frames of image data on a continuous basis.
11. The method of claim 10 , wherein the method further comprises:
autostitching the plurality of frames of image data for the first series of image data together to form a first image of the wide field-of-view; and
autostitching the plurality of frames of image data for the second series of image data together to form a second image of the wide field-of-view.
12. The method of claim 1 , wherein comparing comprises an edge motion test, and wherein the method further comprises:
registering the second series of image data to the first series of image data.
13. A method for detecting a moving object, the method comprising:
receiving a first series of image data for a plurality of frames, each frame of the plurality of frames covering a separate portion of a wide field-of-view and the plurality of frames together covering all of the wide field-of-view, wherein receiving comprises autostitching the plurality of frames of image data for the first series of image data together to form a first image of the wide field-of-view;
receiving a second series of image data for the plurality of frames, wherein receiving comprises autostitching the plurality of frames of image data for the second series of image data together to form a second image of the wide field-of-view;
using a digital processing component to compare image data of multiple frames of the plurality of frames from the first series of image data to image data of the multiple frames from the second series of image data to detect the moving object within the wide field-of-view, wherein comparing comprises detecting changes in frames of image data on a continuous basis;
providing an indication of the moving object;
a processing component determining if the first series of image data contains overlaps or gaps, wherein overlaps comprise portions of images in the series of image data that contain overlapping content, and wherein gaps comprise sections of the wide field of view missing from the series of image data; and
the processing component automatically altering angular positions for a scan mirror to minimizing overlaps and gaps in the first series of image data.