A Fast Recognition Method for Moving Objects
A technology for moving objects and recognition methods, applied in character and pattern recognition, image data processing, instruments, etc., can solve problems such as misjudgment, and achieve the effect of reducing the amount of calculation, reducing the amount of calculation, and improving the speed.
Inactive Publication Date: 2018-05-08
CHINARS GEOINFORMATICS GUANG DONG +1
View PDF3 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
There are two problems with this method. When the shielded area is too small, some noise will still remain, and misjudgment may still occur; when the shielded area is too large, the information of moving objects may also be shielded. up
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment 1
[0039] The method for fast identification of moving objects of the present invention is specifically described below in conjunction with examples:
[0040]In order to visually determine human-captured video when continuously monitoring marine life using underwater cameras, it is necessary to replay and process the huge video to confirm the possibility of human error in the event of a miss. In addition, it is necessary to quickly view the findings of a problem after repeating the same validation for that vision work again. In this process, if relying solely on manpower, the workload is very large, so the information processing capability of the computer vision function of computer image processing technology is generally used; figure 2 shown.
[0041] The flow chart of detecting moving objects through image analysis is as follows image 3 Shown: In order to determine the occurrence of biological species, changes above a certain size were extracted in this example.
[0042] ...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention discloses a method for quickly identifying a moving object. Corresponding reference pictures are acquired in different time periods, and the number of scanning lines of the picture is determined according to the size of the moving object to be identified, the size of the scanning grid is determined, and the reference picture is scanned. Grid division: real-time acquisition of data images corresponding to the scene, the data image is divided according to the size of the scanning grid, and then the grid covered by the noise is determined and shielded according to the shape of the noise; the real-time data image after the noise masking is compared with the corresponding Analyze and compare the reference pictures of the time period, determine the changing line segment, determine the changing grid according to the changing line segment, determine the spatial continuity according to the changing grid, and extract the trajectory of the moving object according to the spatial continuity. The invention divides the picture into a grid firstly, not only can determine the shielding area according to the actual noise shape, but also can greatly reduce the calculation amount in the moving body recognition, so that the moving track information of the moving body can be provided timely and accurately.
Description
technical field [0001] The invention relates to the field of mobile object identification, and more particularly, to a fast identification method for mobile objects. Background technique [0002] In the video hydrological monitoring system, in addition to collecting the image data required to extract water level information, the camera can also be used to identify moving objects that appear within the camera's viewing angle, making real-time monitoring of some prohibited fishing areas such as rivers and lakes monitoring becomes possible. In order to carry out 24-hour continuous monitoring of a specific viewing angle range, the cameras used can still have good imaging effects under starlight (almost complete darkness) conditions. [0003] The traditional method of scanning moving objects is to use a clear image as a template, and then scan the entire image of the collected data. There is no doubt that scanning the entire picture will require a large amount of calculations, ...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G06K9/00G06T7/20
Inventor 范海生
Owner CHINARS GEOINFORMATICS GUANG DONG