A method for detecting, identifying and tracking infrared objects by a car
An object detection and infrared technology, which is applied in the direction of program control manipulators, manufacturing tools, manipulators, etc., can solve the problems of low infrared object recognition rate, weak anti-interference, affecting detection and tracking effects, etc., to achieve strong anti-interference, high Recognition rate, the effect of high recognition rate
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0038] see figure 1 , the car of the present invention detects, recognizes and tracks infrared objects, and adopts a target recognition and tracking closed-loop control algorithm, which uses X coordinates to track the rotation direction and Y coordinates to track the lifting direction; the image sensor recognizes the target on the car B and returns to its The initial coordinates of the center point (X 0 ,Y 0 ), the coordinates of the data center of the next frame measured by the image sensor are (X 1 ,Y 1 ), then the deviation △X, △Y can be obtained; input the deviation △X into the PD control of the applied force level to obtain the output value of the steering gear, and input the deviation △Y into the PD control of the applied force level to obtain the output of the motor value;
[0039] When the car is moving, the image sensor obtains the width and height of the object according to the center coordinates of the object in the image coordinate system, and knows the area of...
Embodiment 2
[0045] see figure 1 , figure 2 , the car in this embodiment detects, recognizes and tracks infrared objects, the difference from Embodiment 1 is that: due to the tilt of the object, the object will have a certain tilt angle in the XOY plane coordinate system of the camera, resulting in the returned area The data will change, coupled with the change of the distance, it will also change the area value returned by the camera.
[0046] figure 2 It is a schematic diagram of the area at the 0° moment and the non-0° moment at the same distance.
[0047] At the same distance, the area of the object at 0° time and non-0° time is different, and the object will have a certain inclination angle in the XOY plane coordinate system of the camera, which will cause the area data returned by it to change, coupled with the change of distance, It will change the area value returned by the camera at the same time; image 3 It is a schematic diagram of the conversion model. Since the inclin...
Embodiment 3
[0055] see Figure 1 ~ Figure 4 , the car in this embodiment detects, recognizes and tracks infrared objects, and the difference from Embodiment 2 is that in the PID controller, r(t) is the set target value, that is, the X and Y target values that need to be achieved ; c(t) is the actual output value, that is, the actual X and Y coordinate values obtained; e(t) is the system deviation value, that is, e(t)=r(t)-c(t); u(t) is The control quantity, that is, the formula for PID adjustment parameter setting:
[0056]
[0057] In the PID controller, the output of the controller is proportional to the set deviation value. When the system deviates, the adjustment of the proportion P can reduce the deviation. The adjustment is simple and quick, allowing for faster adjustments. However, if the P value is too large, it will reduce the stability of the system, causing instability and leaving a residual difference. Integral I can eliminate the remainder of P and improve the degre...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More