Research On Optical Flow Routing Algorithm In Colonic Endoscopy Visual Navigation System

The research on intelligent medical devices and medical robots is currently an important area. Among its applications is the minimal invasive surgery(MIS), which has improved levels of traditional diagnosis and treatments. More and more forbidden zones of surgery could be reached and many kinds of diseases could be cured effectively. Endoscopy, an important technology of MIS, mainly uses endoscope as a diagnosis device. While colonoscopic diagnosis has become an effective therapy to cure colon illness, there exist some problems as perforation 、 hmorrhage. Therefore, robotics and computer technology for colonoscopy equipment has important significance and application prospects in for intelligence reform.In order to overcome the endoscopy perforation and improve intelligence level, this dissertation mainly studies the colon endoscopic visual navigation system of optical flow routing algorithm.The main contents of the dissertation are as follows:(1) In allusion to advantages and disadvantages of commonly used routing method for colonoscopy,this thesis studied optical flow based on autonomous robot obstacle avoidance system and put forward the basic idea of the optical flow and colonoscopy combines visual navigation.(2) On the basis of the traditional optical flow algorithm,the sparse LK optical flow method,a kind of improved differential algorithm, was studied. Analyzed the HS optical flow method, LK optical flow method, matching method and sparse LK optical flow method,comparative experiments in MATLAB 7.0 software platform, sparse LK optical flow method is verified on the running time and the precision is better than the other three.(3) Considering the sparse LK optical flow method in the interframe motion is larger,easily lead to optical flow loss, poor effect, this thesis proposes an improved sparse LK optical flow method:pyramid LK sparse optical flow method.Through analysis and comparison, to determine the 3 layers of pyramid LK sparse optical flow method as the main algorithm of this thesis.The improved optical flow method with the traditional LK optical flow method is used for performance comparison experiment.Results show that the pyramid LK sparse optical flow method in optical flow field calculation interval larger frame,has high precision, programs run by the time consumption is greatly reduced.(4) Formulated the balance strategy scheme based on optical flow method. According to the original balance strategy is only applicable to simple corridor environment,puts forward a kind of improved endoscopic path finding balance strategy.The strategy to use the central part of the image of the optical flow amplitude to determine whether there is the collision ahead of the gut wall,through the calculation of the experimental results show that the improved balancing strategy can make the colon endoscopy make decisions better action and using MATLAB 7.0 to build the colon CT image three-dimensional body reconstruction,based on the three-dimensional reconstruction of the colon were bodies on optical flow routing algorithm experiments to achieve the visual routing.