Biography:

In the past Daisuke Deguchi has collaborated on articles with David Wong. One of their most recent publications is Regression of feature scale tracklets for decimeter visual localization☆. Which was published in journal Image and Vision Computing.

More information about Daisuke Deguchi research including statistics on their citations can be found on their Copernicus Academic profile page.

Daisuke Deguchi's Articles: (4)

Regression of feature scale tracklets for decimeter visual localization☆

Highlights•A decimeter-level vehicle localization system using monocular vision is proposed.•Regression of feature scale tracklets allows interpolation between database images.•Visual estimates are combined with a motion model using a Kalman filter.•Localization accuracy is within 1 m for 98% of a real-world dataset.

New calculation method of image similarity for endoscope tracking based on image registration in endoscope navigation

AbstractThis paper presents a new calculation method of image similarity for camera motion tracking in a flexible endoscope navigation system. An endoscope navigation system is a tool which provides navigation information that is acquired from pre-operative images to a medical doctor during an endoscopic examination in real time. In this system, one of the fundamental functions is to track endoscope camera motion. Since it is difficult to attach a positional sensor at the tip of a flexible endoscope, especially bronchoscope, due to space limitation, an image registration technique becomes a strong tool for camera motion tracking. The previous method used image similarity computed by summing gray-level differences up for all pixels of real and virtual endoscopic images. The method could not properly estimate the position and orientation of the endoscope due to averaging, since image similarity does not change significantly. We proposed a new image similarity measure which uses characteristic structure in computation. This method divides the original image into a set of small subblocks and selects only the subblocks in which characteristic shapes are observed. Then, an image similarity value is calculated only within the selected subblocks. We applied the proposed method to eight pairs of X-ray CT images and real bronchoscopic videos. In the experimental results, the proposed method showed much improvement in continuous tracking performance. Nearly 1000 consecutive frames were tracked correctly.

A method for bronchoscope tracking by combining a position sensor and image registration

AbstractThis paper describes a method for tracking a bronchoscope by combining a position sensor and image registration. A bronchoscopy guidance system is a tool for providing navigation information acquired from pre-operative images to a physician during a bronchoscopic examination in real time. In this system, one of the fundamental functions is to track the bronchoscope camera motion. Recently, a very small electro-magnetic position sensor has become available. It is possible to insert the sensor into the bronchoscope's instrument channel for obtaining bronchoscope camera motion. However, the accuracy of its output is not enough for bronchoscope tracking. Combination of the sensor and image registration between real and virtual bronchoscopic images are quite useful for improving the tracking accuracy. Also, this combination enables us to realize a real-time bronchoscope guidance system. We examined the proposed method with a rubber bronchial model. In the experiments, the proposed system enabled us to track the bronchoscope camera motion in 2.5 frames per second.

Selective image similarity measure for bronchoscope tracking based on image registration

AbstractWe propose a selective method of measurement for computing image similarities based on characteristic structure extraction and demonstrate its application to flexible endoscope navigation, in particular to a bronchoscope navigation system. Camera motion tracking is a fundamental function required for image-guided treatment or therapy systems. In recent years, an ultra-tiny electromagnetic sensor commercially became available, and many image-guided treatment or therapy systems use this sensor for tracking the camera position and orientation. However, due to space limitations, it is difficult to equip the tip of a bronchoscope with such a position sensor, especially in the case of ultra-thin bronchoscopes. Therefore, continuous image registration between real and virtual bronchoscopic images becomes an efficient tool for tracking the bronchoscope. Usually, image registration is done by calculating the image similarity between real and virtual bronchoscopic images. Since global schemes to measure image similarity, such as mutual information, squared gray-level difference, or cross correlation, average differences in intensity values over an entire region, they fail at tracking of scenes where less characteristic structures can be observed. The proposed method divides an entire image into a set of small subblocks and only selects those in which characteristic shapes are observed. Then image similarity is calculated within the selected subblocks. Selection is done by calculating feature values within each subblock. We applied our proposed method to eight pairs of chest X-ray CT images and bronchoscopic video images. The experimental results revealed that bronchoscope tracking using the proposed method could track up to 1600 consecutive bronchoscopic images (about 50 s) without external position sensors. Tracking performance was greatly improved in comparison with a standard method utilizing squared gray-level differences of the entire images.

Advertisement
Join Copernicus Academic and get access to over 12 million papers authored by 7+ million academics.
Join for free!

Contact us