Platform screen door can not only prevent the passengers fell or jumped the track danger, to passengers bring comfortable waiting environment, but also has the function of environmental protection and energy saving. But platform screen door and train the full-length gap region is insecure in the system design of a hidden, such as passengers for some reason (grab the train) in the interstitial region retention, is sandwiched between the intercity safety door and the door, and such as the region lacks security detection and alarm system, once the passengers in the gap region retention (caught), bring more serious threat to the safety of passengers and traffic safety. This paper from the point of view of the design presents the physical, infrared, laser three safety protection device setting schemes. Domestic intelligence of between rail transit shield door and train security clearance processing used is screen door system standard configuration, the obstacle detection function for avoid passengers stranded in the clearance has strong prevention function. Laser detection research and development projects can access to prevent shield door and train gap clamp safety measures. Rail safety protection method are studied applying laser detection technique. According to the laser reflection equation of foreign body, the characteristics of laser detection of foreign bodies are given in theory. By using statistical analysis method, the workflow of laser detection system is established. On this basis, protection methods is proposed. Finally the simulation and test results show that the laser detection technology in the rail traffic safety protection reliability and stability, And the future laser detection technology in is discussed the development of rail transit.
Dimensional mismatch between a low-resolution (LR) surveillance face image and its high-resolution (HR) template makes recognition very difficult. A novel method called coupled cross-regression (CCR) is proposed to deal with this problem. Instead of processing in the original observing space directly, CCR projects LR and HR face images into a unified low-embedding feature space. Spectral regression is employed to improve generalization performance and reduce computational complexity. Meanwhile, cross-regression is developed to utilize HR embedding to increase the information of the LR space, thus improving the recognition performance. Experiments on the FERET and CMU PIE face database show that CCR outperforms existing structure-based methods in terms of recognition rate as well as computational complexity.
Precise ground target localization is an interesting problem and relevant not only for military but also for civilian
applications, and this is expected to be an emerging field with many potential applications. Ground Target Location
Using Loitering Munitions (LM) requires estimation of aircraft position and attitude to a high degree of accuracy, and
data derived by processing sensor images might be useful for supplementing other navigation sensor information and
increasing the reliability and accuracy of navigation estimates during this flight phase. This paper presents a method for
high accuracy ground target localization using Loitering Munitions (LM) equipped with a video camera sensor. The
proposed method is based on a satellite or aerial image matching technique. In order to acquire the target position of
ground intelligently and rapidly and to improve the localization accuracy estimating the target position jointly with the
systematic LM and camera attitude measurement errors, several techniques have been proposed. Firstly, ground target
geo-location based on tray tracing was used for comparison against our approach. By proposed methods the calculation
from pixel to world coordinates can be done. Then Hough transform was used to image alignment and a median filter
was applied for removing small details which are visible from the sensed image but not visible from the reference image.
Finally, A novel edge detection method and an image matching algorithm based on bifurcation extraction were proposed.
This method did not require accurate knowledge of the aircraft position and attitude and high performance sensors,
therefore it is especially suitable for LM which did not have capability to carry accurate sensors due to their limited play
weight and power resources. The results of simulation experiments and theory analyzing demonstrate that high accuracy
ground target localization is reached with low performance sensors, and achieve timely. The method is used in
reconnaissance and surveillance missions, or applicable in any other environment with a relevantly structured clutter.
Color harmonization is an artistic technique to adjust a set of colors in order to enhance their visual harmony so that they are aesthetically pleasing in terms of human visual perception. We present a new color harmonization method that treats the harmonization as a function optimization. For a given image, we derive a cost function based on the observation that pixels in a small window that have similar unharmonic hues should be harmonized with similar harmonic hues. By minimizing the cost function, we get a harmonized image in which the spatial coherence is preserved. A new matching function is proposed to select the best matching harmonic schemes, and a new component-based preharmonization strategy is proposed to preserve the hue distribution of the harmonized images. Our approach overcomes several shortcomings of the existing color harmonization methods. We test our algorithm with a variety of images to demonstrate the effectiveness of our approach.