In a surveillance environment the presence of noise complicates the detection of intruding objects. This paper reports a new method that suppresses this noise to stabilize the detection process. The traditional approach has detected trespassers by examining regions of changing intensity. The misinterpretation occurs more frequently by changes in intensity caused by the noise. Our approach reduces the probability of the misinterpretation by extracting the contours and texture of the intruding objects. We then label regions that correspond to this extracted information. Finally, based on the size. shape, distribution and continuity of the regions we differentiate the intruding objects from noise. In this way,intruders will reliably be detected even when the environment changes.

View full abstract

As the first step in the development of a vision sensor for an autonomous driving system a real-time, 33ms per frame, highway road image processing system is proposed. The system is aimed to extract by linear approximation the three lane markers from a set of continuous monochromatic video pictures of the road. These pictures were taken from a passenger car driving on a two lane highway at a speed of 100km per hour. The processing algorithm first measures vertical vibrations in the picture caused by the pitching motion of the car. Additionally, the interpolation of the results of the previous frame into the current frame calculation makes the system robust against noise and frequent breaks in the marking lines.

View full abstract

A 3-D measurement device using slit-ray projection has been developed, which measures the accurate range and luminance data at a high speed. The device consists of a laser light source, a polygon mirror. an f-θ lens. PSD (position sensitive device), and parallel signal processing unit with 32bit MPUs. This device can obtain the range and luminance data in 1.1ms by 1.000 points simultaneously. The measurement resolusion is 50μm in along the X and Y axes and 25μm along in Z axis. This device has been applied to an inspection system for electronic components mounted on a PCB. The system can detect missing, shifted components and lack of solder.

View full abstract

At Sony's Compact Disc (hereafter called CD) factory, inspection of the CD label is done by human visual inspectors. But now, in order to automate that inspection, a system for the detection and prevention of errors has been developed and installed in line with the label printing machine. One of the features of this system is that 100% in-line inspection is possible by processing four images for each CD in about 0.8 seconds. For this a high speed algolithm which matches the test image to a mastered image stored in computer memory was developed.

View full abstract