![\"\"](\"https:\/\/digilent.com\/blog\/wp-content\/uploads\/2017\/09\/ObjTracking-600x415.png\"){kind=tracking}
<\/p>\nComing in strong on our list of cool projects made with our boards is another interesting project that uses the Zybo board:<\/p>\n
“An object tracking vision system using a moving camera implemented in a Zynq heterogeneous device”, by Marcin\u00a0Kowalczyk, from AGH University of Science and Technology in Krakow, Poland.<\/p>\n
Autonomous object tracking with use of a moving camera is used for examples in issues connected with security, surveillance or in military applications. This particular project involved creating a\u00a0video system demonstration for tracking objects, assuming that the camera is mounted on a moving stand.<\/p>\n
The system consists of:<\/p>\n
\u2013 Camera –\u00a0Xiaomi Yi Action YDXJ01XY sports camera
\n\u2013 Computing platform – the Digilent Zybo board
\n\u2013 Sensors – PmodNAV, PmodGYRO, PmodACL
\n\u2013 Bluetooth module – PmodBT2
\n\u2013 Servomechanisms
\n\u2013 Servo controller
\n\u2013 Power supply
\n\u2013 Pointer – laser pointer<\/p>\n
The output of tracking module is the basis for the positioning of moving stand. The aim of the positioning is to keep a tracked object in the center of frame and mark it with a pointer. Below are the modules of the project can be visualized by the connection between them.<\/p>\n
<\/p>\n
<\/p>\n
It was decided by the team \u00a0to use Xiaomi Yi Action YDXJ01XY sports camera Regulator:<\/strong><\/p>\n In the designed system, camera is a sensor of regulation error. Regulator was created for system without and the block diagram of entire system:<\/p>\n Image processing:<\/strong><\/p>\n 2. Mean Shift algorithm:<\/p>\n Calibration of the sensors was needed in order to obtain proper results, and their integration and fusion as well.<\/p>\n Conclusions:<\/p>\n \u2013 Parallel realization of algorithm (hardware implementation) requires a lot more work than software \u2013 Testing each module separately, after realization, makes it easier to connect them into a complete![\"\"](\"https:\/\/digilent.com\/blog\/wp-content\/uploads\/2017\/09\/ObjTrackingcamera.png\"){kind=tracking}
Communication<\/strong>: it was implemented between all elements of the system. It can be divided into PC-Zynq part and Zynq-servo controller \u2019Maestro\u2019.<\/p>\n\n
\nSuitable pins (MIO 14 and 15) of ZYBO\u2019s MIO PMOD connector were connected to Maestro pins
\nresponsible for serial communication. Then pins were connected to another processor\u2019s peripheral for
\nserial communication – UART0<\/li>\n<\/ol>\n
\nsensors of moving stand position, thus control algorithm is currently based only on data from camera. For constructing a model, simulations were performed in MATLAB and Simulink, below is the block diagram of the servomechanism:<\/p>\n![\"\"](\"https:\/\/digilent.com\/blog\/wp-content\/uploads\/2017\/09\/ObjTrackingServo-600x151.png\"){kind=tracking}
<\/p>\n![\"\"](\"https:\/\/digilent.com\/blog\/wp-content\/uploads\/2017\/09\/ObjTrackingServo1-600x78.png\"){kind=tracking}
<\/p>\n\n
![\"\"](\"https:\/\/digilent.com\/blog\/wp-content\/uploads\/2017\/09\/ObjTrackingTD-600x449.png\"){kind=tracking}
<\/p>\n![\"\"](\"https:\/\/digilent.com\/blog\/wp-content\/uploads\/2017\/09\/ObjTrackingMS-600x336.png\"){kind=tracking}
<\/p>\n
\nimplementation (in processor).
\n\u2013 Mean-shift algorithm has good effects, when tracked object\u2019s color is much different from the
\nbackground\u2019s (if H component of HSV color space is used).
\n\u2013 Tracking by detection algorithm usually gives correct coordinates of object, but it does not use
\ninformation from previous frame. In result, there are possible situations, when in two consecutive
\nframes object is detected in other sides of image (e.g. in result of noises), what may result in
\nmechanical damage, related to sharp movement of servomechanisms.
\n\u2013 Selection of proper regulator and it\u2019s parameters is much easier based on mathematical model of
\ncontrolled system.
\n\u2013 Mathematical model does not have to perfectly reproduce operation of the real system. Effects
\nsuch as very short delays may be neglected.
\n\u2013 Breakdown of project into independent modules greatly simplifies work.<\/p>\n
\nsystem.<\/p>\n![\"\"](\"https:\/\/digilent.com\/blog\/wp-content\/uploads\/2017\/09\/DDC-76-600x399.jpg\")
![\"\"](\"https:\/\/digilent.com\/blog\/wp-content\/uploads\/2017\/09\/DDC-77-600x399.jpg\")
![\"\"](\"https:\/\/digilent.com\/blog\/wp-content\/uploads\/2017\/09\/Portrait-451x600.jpg\")
<\/p>\n
