This article explains how Model-Based Design with Simulink and the Video and Image Processing Blockset can be used to design an Infrared video tracking system, and then how to implement the design on TI's TMS320C6713 DSP, and verify its on-target performance in real time.
The core element of Model-Based Design is an accurate system model -- an executable specification that includes all software and hardware implementation requirements. The model can be used to generate code for final system verification and deployment.
This approach makes it easy to express a design concept, simulate the model to verify algorithms, automatically generate the code to deploy it on a hardware target, and verify exactly the same operation on silicon.
The model-based approach reduces development cycle of a product and thus reduces time to market as code conversion can be done after successful simulation, and hardware implementation can directly verify simulation results. Apart from DSPs, the model-based approach can also be extended to simulate and implement designs on FPGAs.
Building the Infrared Video Tracker system model
Using Simulink and the Video and Image Processing Blockset, we first develop a floating-point model for the Infrared Video Tracker. It is a dual mode video tracker -- i.e. it can act as an automatic tracker or the user can specify which object(s) to track.
Figure 1: Video Tracker Model
View full size
In the automatic version, frame differencing was used to estimate the motion between two frames, while adaptive thresholding was used for the manual tracking system. We input a video stream to the simulation environment using the From Multimedia File block from the Video and Image Processing Blockset. During simulation, the video data is processed in the Main Processing Block subsystem, which outputs the tracked objects to the To Video Display block for visualization (see Figure 1).
Next: Object tracking, Implementing and verifying the application on TI hardware
|
