Search

Over the last few years, human computer interaction has become an active research area, which releases people from inactive, inconvenient communication with machine. In this paper, an automotive infotainment system with intelligent applications is presented. The proposed system combines the interactive gesture control for controlling in-car applications which can enhance safety and driving performace, as well as increase the level of comfort in modern vehicles.

Wiener filter is one of the most fundamental noise-reduction approaches among numerous techniques. The speech recognition in an in-vehicle environment needs a non-stationary noise cancellation to eliminate the background noise. However, few efforts have been reported to show the effectiveness of Wiener filter. Not much has been evaluated how the Wiener filter really works for reducing the non-stationary noise in real-time. In this paper, a real-time adaptive Wiener filter with two microphones is implemented to reduce noisy speech when noise signals and desired speech are incoming simultaneously. Furthermore, in order to build a real-time noise canceller, this paper also gives an analysis of different matrix sizes of the Wiener filter so as to enable the possibility of real-time implementation. The performance of the proposed design is measured by as much as 20dB noise reduction, and the proposed adaptive Wiener matrix update speed achieves a 28.6 ms/frame, with a matrix size of 200.

Image binarization involves converting gray-level images into binary ones, which has significantly impacted on intelligent portable devices in recent years. Given the limited memory space and computational power of portable devices, reducing the computational complexity of algorithms which work on embedded systems is of priority concern. This paper proposes a 2-D intelligent block detection algorithm with more accurate region segmentation for document image binarization. by combining merits of global and local algorithms, the proposed approach provides an effective outcome and a low computational cost. as demonstrated by the experimental results, the proposed algorithm is slower than Otsui¦s method but 275 times faster than local methods.

This paper presents the architecture and implementation of a real-time adaptive Wiener filter for non-stationary noise cancellation in a car environment. The Wiener filter has been implemented in a Xilinx Virtex-5 chip and the target device is chosen as xc5vlx110t. The proposed design can filter each 32 samples within 918 micro seconds. The peak sampling rate is estimated to be 88.6KHz. The performance of proposed design is measured as 15.85dB noise reduction.

License plate recognition system (LPR) plays an important role in many applications such as access control, traffic control, and the detection of stolen vehicles. A LPR system can be classified into the detection and recognition parts. Improvement of the detection part will be discussed in this paper. Binarization of plate images is one of the major tasks of detection which consumes huge processing time and impacts on the recognition rate. This paper proposes an efficient binarization algorithm with intelligent block size detection. Based on image characteristics, the plate image is automatically divided into several blocks with various sizes. Then, a threshold surface is constructed to derive the binary image. Experimental results show that the proposed method not only provides promising binarization result, but also low computation cost.

Skin color is an important feature for face detection and recognition in color images. In order to obtain the possible face regions in color images, the skin color models are always constructed by statistical analysis. Owing to low accuracy of the static models, researches have discussed several dynamic models to correct input image such as illumination compensation, white balance, edge points addition, etc. Unfortunately, it is possible that some objects whose color is the same as the definition exist, and the previous methods can not separate real skin item from skin color background. Thus, to enhance skin color separation, this paper presents a honeycomb model to recognize the real human skin and the skin color items. First, the possible skin color is estimated from the pixels of database, and the honeycomb structure is built in HSV color space according to the training samples. Then, the personal skin is captured in one of the honeycomb cells. The performance of the new skin color detector technique has been tested under complex lighting source and background environments. It is observed that the proposed model can effectively improve the segmentation results. Especially, the honeycomb model is capable of separating the human face which connected with other face or skin color background.

Recently, VNC (virtual network computing) has become one of the popular remote access techniques for Internet applications such as remote distant learning and collaborative application systems. However, there is no any multimedia functions have been implemented to enhance the performance. In this paper, we presents a framework based on remote frame buffer (RFB) and real-time protocol (RTP) to provide real-time video and audio transmissions for multimedia applications. The framework can be applied to build distance collaborative environments with multimedia and RTP (real-time transport) features efficiently.

In this paper, given a set of timing-driven routing trees for all the interconnection nets, a new multilevel timing-constrained full-chip routing (MTFR) in a dynamic hierarchical quad-grid model is proposed to complete full-chip routing in reasonable time. The experimental results show that the proposed MTFR approach uses less CPU time to obtain 100% timing-constrained routing results for all the tested benchmark circuits.

In this paper, based on timing-constrained Steiner-point location flexibility in any Y-type wire, a dynamic SA-based timing-constrained flexibility-driven SRT (DSTF/spl I.bar/SRT) approach with the congestion weighs is firstly proposed to obtain a better timing-constrained flexibility-driven SRT by reassigning the feasible locations of the Steiner points in a SRT. Furthermore, the concept of dynamic tree reconstruction is applied to timing-constrained congestion-driven global routing. The experimental results show that our proposed TCGR/spl I.bar/DTR algorithm can obtain a better timing-constrained congestion-driven global routing result than the HBA+TRR [Hu, 2000] and TCGR [Yan, 2004] algorithm for the tested benchmark circuits.

In this paper, the floorplan-aware topology of hierarchical power quad-grids is proposed to dynamically meet the local requirement of high current densities inside the floorplan and an iterative linear voltage/current scaling (ILVCS) approach is proposed to meet the current electromigration and voltage IR-drop constraints phase by phase. The experimental results show that our proposed ILVCS approach based on hierarchical power quad-grids can obtain 23%/spl sim/44% improvement on total wiring area than the power grids by the wire sizing method for the tested examples.

The dynamic structure of a hierarchical stair contour is firstly proposed to maintain an incremental floorplan contour for the placement of a sequence of given blocks. Based on the LB-packing process of any given block in a compact floorplan, a double-bound list (DBL) is further proposed to represent the geometrical adjacent relations in a compact floorplan. Finally, an SA-based approach based on the combination of one rectangular-packing process and one LB-packing process as one perturbation operation is proposed to allocate and integrate the possible decaps of all the blocks into the original floorplan. Experimental results show that our proposed SA-based allocation approach based on DBL representation obtains very promising results for MCNC benchmark circuits.

A probabilistic congestion prediction approach in a dynamic hierarchical quad-grid model is proposed to be applied in timing-constrained congestion-driven global routing (TCGR). Experimental results show that the TCGR algorithm (Yan, J.T. and Lin, S.H., Asia-Pacific Design Automation Conf., p.683-6, 2004) with the proposed probabilistic congestion prediction can use less CPU time to obtain a better timing-constrained congestion-driven global routing result for the tested benchmark circuits.

As the complexity of VLSI circuits increases, the routability problem becomes more and more important in modern VLSI design. In general, the flexibility improvement of the edges in one routing tree has been exploited to release the routing congestion and increase the routability in the routing stage. In this paper, given an initial routing tree, based on the definition of the routing flexibility in a SRT and the timing-constrained location flexibility of the Steiner-point in one Y-type wire, the simulated-annealing-based approach is proposed to obtain a better timing-constrained flexibility-driven SRT by reassigning the feasible locations of the Steiner-points in a SRT. The experimental results show that our proposed STFSRT algorithm can obtain 43%/spl sim/173% improvement on the measure of total routing flexibility for the tested benchmark circuits.