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
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
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...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 


