Embedded double-DSP (digital signal processing) information data processing device and method

Abstract

An embedded double-DSP (digital signal processing) information data processing device comprises a first DSP processor and a second DSP processor which are in parallel; two parallel DSP processors are connected to an image collection front-end module; and an interface module is externally and respectively arranged at each rear end of the two DSP processors. According to the data processing method employing the device, the image collection front-end module respectively outputs the collected image data to the first DSP processor and the second DSP processor; the first DSP processor or / and the second DSP processor respectively process(es) the input image data at the same time; and the processing result of one DSP processor is transmitted to another DSP processor to carry out data overlap on a image, and the result is transmitted to an interface module. The embedded double-DSP information data processing device has stronger flexibility for an intelligent transportation field, and a user can adopt a proper work mode for the characteristics of a traffic scene and an application field.

Description

technical field [0001] The invention relates to a data processing device, in particular to an embedded double DSP information data processing device for intelligent traffic. [0002] The present invention also relates to a data processing method using the above-mentioned data processing device. Background technique [0003] A digital signal processor (Digital Signal Processor, DSP) is a device that processes information with digital signals. Its working principle is to convert the received analog signal into a digital signal and then process it into a real signal. [0004] In the field of intelligent transportation, the DSP processor has always played a very important role. In addition to completing the preprocessing and image output of the captured images on the spot, it can also record the video of the traffic scene. Common systems generally adopt a single DSP architecture. Under this architecture, DSP needs to undertake tasks such as image acquisition front-end control, ...

AI Technical Summary

Problems solved by technology

[0005] 1) There are restrictions on the application

Due to the heavy tasks of the single DSP system, too many transactions need to be processed, and the system processing capacity is limited, it is not suitable for high-speed and complex pre-processing algorithms;

[0006] 2) The system is not easy to stabilize

Because a single DSP system needs to handle too many transactions, it is difficult to design a relatively stable system, and it is not conducive to system maintenance in the later stage of the system;

[0007] 3) Does not support parallel processing

[0008] 4) The video stream is not continuous

Under a single DSP architecture, if it is necessary to output captured image frames and save the video stream at the same time, in general, in order to ensure the stable operation of the system, and also limited by the system cache and processing capacity, only continuous image frames A specific frame is taken out as a capture frame, which will cause the video stream to be discontinuous and have obvious frustration, which is not conducive to traffic applications

[0009] 5) Does not support user secondary development

Images