Unlock instant, AI-driven research and patent intelligence for your innovation.

Centroid Correction and State Distinguishable Particle Filter Method Based on FPGA

A particle filtering and particle technology, applied in the field of electronic information, can solve the problems of consumption, multiple storage space and computing units, and achieve the effect of saving storage resources, saving FPGA storage resources, and high accuracy

Active Publication Date: 2019-08-06
SHANGHAI UNIV
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

When the number of random particles generated is large enough, the range of errors can be reduced, but at the cost of consuming more storage space and computing units

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 more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Centroid Correction and State Distinguishable Particle Filter Method Based on FPGA
  • Centroid Correction and State Distinguishable Particle Filter Method Based on FPGA
  • Centroid Correction and State Distinguishable Particle Filter Method Based on FPGA

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0032] see Figure 1 to Figure 5 , the FPGA-based centroid correction and state-distinguishable particle filter method is characterized in that the operation steps are as follows: 1) select the target, 2) calculate the target feature, 3) generate random particles, 4) count the particle histogram, 5) calculate Particle center of mass position, 6) calculate particle weight, 7) output target position, 8) judge tracking status, 9) display target status and position.

Embodiment 2

[0033] Embodiment 2: This embodiment is basically the same as Embodiment 1, and the special features are as follows:

[0034] 1. The step 1) select the target: manually select the target of interest, the size and position of the tracking frame are the size and initial position of the target, and start tracking.

[0035] 2, the step 2) calculates the target feature: the RGB image is converted into an HSV image, and the H component is extracted as the target feature, and the statistical range is all pixels in the tracking frame; use RAM to count the color histogram of the target, and the RAM The address is the value range of the H component, and the value stored in each address indicates the number of times the H component appears in the tracking frame, that is, how many pixels in the tracking frame are equal to the H component value.

[0036] 3. The step 3) generates random particles: when the target is in the tracking state in the monitoring screen, since the motion of the tar...

Embodiment 3

[0044] see figure 1 , an FPGA-based centroid-corrected and state-recognizable particle filter algorithm with 8 particles, the specific implementation steps are as follows:

[0045] In order to reduce the impact of light on the tracking algorithm, the color space of the input image is converted to HSV color space, and the H component is extracted to participate in the calculation of the tracking algorithm, thereby reducing the amount of calculation.

[0046] The switching of each step is realized by the state machine. If the current step meets certain conditions, jump to the next state.

[0047] 1. Select the target: Specify the specific buttons on the infrared remote control to move up, down, left, and right, zoom in and out the tracking frame, start tracking, and end tracking. FPGA recognizes the infrared remote control signal, controls the tracking frame and tracking status. When it is confirmed that the target is within the tracking frame, press the start key to enter th...

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

No PUM Login to View More

Abstract

The invention provides an FPGA-based mass center correction and status differentiation particle filtering algorithm. The algorithm comprises the operation steps of 1, selecting a target; 2, calculating characteristics of the target; 3, generating a random particle; 4, performing statistics on a particle histogram; 5, calculating the mass center position of the particle; 6, calculating the weight of the particle; 7, outputting the position of the target; 8, judging a tracking status; 9, displaying the status and the position. On the premise that storage space is saved, the tracking precision and the calculation efficiency are improved, and the tracking accuracy and real-time performance are ensured.

Description

technical field [0001] The invention relates to advanced technologies such as digital image processing and target tracking algorithms, in particular to a particle filter algorithm based on FPGA-based centroid correction and recognizable states, which belongs to the field of electronic information. Background technique [0002] Particle filter algorithm and CamShift algorithm are two classic target tracking algorithms based on color histogram statistics. The CamShift algorithm has low complexity, small amount of computation, and is easy to implement, but its tracking accuracy is poor and its tracking error rate is high. The complexity of the particle filter algorithm is high, and its calculation amount increases with the increase of the number of particles, but its tracking accuracy is high and the error rate is low. The parallel computing mechanism of FPGA accelerates the particle filter algorithm by hardware, which improves the efficiency of the algorithm and the real-time...

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
no application Login to View More
IPC IPC(8): G06T7/277G06T1/20
CPCG06T1/20
Inventor 王姝慧陆小锋黄睿钟宝燕裴栋彬颜柯崔微王桥元
Owner SHANGHAI UNIV