This paper gives a practical schema for using DSP boards to construct Vehicle License Plate Recognition (VLPR) modules that could be embedded in any Intelligent Transportation System (ITS). Using DSP can avoid the heavy investment in dedicated VLPR system and improve the computational power compared to PC software environment. Low cost, high computational power, and high flexibility of DSP provide the License Plate Recognition System (LPRS) an excellent cost-effective solution to execute the major part of the recognition tasks. This paper describes a successful implementation of VLPR system based on Texas Instruments (TI)'s TMS320DM642. The DSP board acquires video (which could be output to a monitor for surveillance) from a camera, captures images from the video, locates and recognizes the license plates in images, and then sends the recognized results and related images after compression to a host PC through the network. Finally, the overall software is optimized according to the features of DM642 chip. Experiments showed that the DSP VLPR system performs well on the local license plates, and that the processing speed and accuracy can meet the requirement of practical applications.
Swept volume solid modeling has been applied to many areas such as NC machining simulation and verification, robot workspace analysis, collision detection, and CAD. But self-intersections continue to be a challenging problem in the boundary representation of swept volume solids. A novel algorithm is presented in this paper to trim self-intersection regions in swept volume solids modeling. This trimming algorithm consists of two major steps: (1) roughly detecting self-intersection regions by checking intersections or overlapping of the envelop profiles; (2) splitting the whole envelop surfaces of the swept volume solid into separate non-self-intersecting patches to trim global self-intersections, and to trim local self-intersections, dividing local self-intersecting regions into patches and replacing self-intersecting patches with non-self-intersecting ones. Examples show that our algorithm is efficient and robust.
