A real-time object tracking method suitable for public transportation scenarios
A target tracking and public transportation technology, applied in the field of real-time target tracking, can solve the problems of insensitivity to size and shape changes of targets, inability to meet the tracking requirements of public transportation scenes, and small environmental impact, so as to minimize scale changes and improve accuracy rate and real-time performance, and the effect of minimizing the impact
Active Publication Date: 2019-05-10
南京行者易智能交通科技有限公司
View PDF9 Cites 2 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0015] To sum up, the existing tracking algorithms cannot solve some technical problems at the same time: they are less affected by the environment, insensitive to changes in the size and shape of the target, and the speed meets real-time requirements, so they cannot meet the tracking requirements in public transportation scenarios
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 Construction
[0031] The present invention will be further described in detail below in conjunction with the accompanying drawings and specific embodiments.
[0032] attached figure 1 It is a schematic flow chart of the target tracking algorithm of the present invention, in conjunction with this figure, the method mainly includes the following steps:
[0033] In the first step, the initial position of the tracked target on the current frame i is given by the detector;
[0034] The initial position of the tracking target on the current frame i is known, and a rectangular frame is given by the detector to mark the tracking target.
[0035] The second step is to train the correlation filter tracker;
[0036] Use the circular matrix in the area around the position P(i) to collect positive and negative samples, use the ridge regression of the kernel space to train the correlation filter tracker, and use the diagonalizable nature of the circular matrix in Fourier space to convert the operation...
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 real-time target tracking method suitable for public transportation scenes. The method comprises steps that S1, the initial position P(i) of a tracked target on a current ithframe is obtained by a detector; S2, a relevant filtering tracker is trained with the P(i); S3, an image of the target at the i+1th frame is obtained; S4, correlation calculation is carried out witha relevant filter and the (i+1)th frame to obtain the target prediction position P'(i+1); S5, the scale change rate is evaluated, and whether target prediction value correction is required is determined based on the threshold; and S6, Kalman filtering is utilized to carry out prediction value correction to obtain the position P(i+1) of the target in the (i+1)th frame. The method is advantaged in that dimension change rate evaluation is carried out, tracking accuracy and timeliness are improved, the target prediction value is further corrected through Kalman filtering, and influence of scale change is minimized.
Description
technical field [0001] The invention relates to the field of computer vision research, in particular to a real-time target tracking method applicable to public transportation scenes. Background technique [0002] Object tracking is one of the hotspots in the field of computer vision research and has been widely used. The tracking and focusing of the camera, the automatic target tracking of the drone, etc. all need to use the target tracking technology. In addition, there are specific object tracking, such as human body tracking, vehicle tracking in traffic monitoring systems, face tracking and gesture tracking in intelligent interactive systems, etc. Simply speaking, target tracking is to establish the positional relationship of the object to be tracked in a continuous video sequence, and obtain the complete trajectory of the object. Given the coordinate position of the object in the first frame of the image, calculate the exact location of the object in the next frame of ...
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): G06T7/246G06T7/277G06T7/262
CPCG06T7/246G06T7/262G06T7/277G06T2207/10016G06T2207/20056G06T2207/20081G06T2207/30241
Inventor 朱旭光
Owner 南京行者易智能交通科技有限公司