Measurement apparatus, measurement method, and feature identification apparatus
It is an object to measure a position of a feature around a road. An image memory unit stores images in which neighborhood of the road is captured. Further, a three-dimensional point cloud model memory unit 709 stores a point cloud showing three-dimensional coordinates obtained by laser measurement which is carried out simultaneously to the image-capturing of the images as a road surface shape model. A model projecting unit 172 projects a point cloud on the image, and an image displaying unit 341 displays the point cloud superimposed with the image on the displaying device. Using an image point inputting unit 342 , a pixel on a feature of a measurement target is specified by a user as a measurement image point. A neighborhood extracting unit 171 extracts a point which is located adjacent to the measurement image point and superimposed on the feature for the measurement target from the point cloud. A feature position calculating unit 174 outputs three-dimensional coordinates shown by the extracted point as three-dimensional coordinates of the feature for the measurement target.
1. A measurement apparatus comprising: an image memory to store an image captured by a camera; a three-dimensional point cloud model memory to store a point cloud which is formed by a point cloud measured by a laser device and of which a three-dimensional position is known as a three-dimensional point cloud model;
a processor programmed to discriminate a three dimensional position of a measurement image point;
an image displaying unit to display and superimpose the image and a three-dimensional point cloud model, which corresponds to the image out of the three-dimensional point cloud model stored in the three-dimensional point cloud model memory, on a screen of a displaying device, and to prompt a user to specify a position within the image wherein the processor is further programmed to receive the position within the image specified by the user as the measurement image point from an inputting device,
detect based on whether a point of the point cloud is displayed within the image, a corresponding point corresponding to the measurement image point from the point cloud of the three-dimensional point cloud model stored by the three-dimensional point cloud model memory; and discriminate a three-dimensional position of the measurement image point using a three-dimensional position of the detected corresponding point
wherein the processor is further programmed to:
calculate a vector showing direction from a center of the camera to the imputed measurement image point and calculate a particular plane including the detected corresponding point,
obtain a three-dimensional position of the detected corresponding point as a first candidate showing a three-dimensional position of the measurement image point, and
calculate an intersecting point of the particular plane and the vector as a second candidate showing the three-dimensional position of the measurement image point, wherein the measurement apparatus further comprises: a position displaying unit to display the first candidate and the second candidate on the screen of the displaying device and to prompt the user to specify one of the first candidate and the second candidate; and
a result memory unit to store one of the first candidate and the second candidate specified by the user as the three-dimensional position of the measurement image point.
2. The measurement apparatus of claim 1 , wherein in response to a point of the point cloud displayed within the image existing at the position in the image shown by the measurement image point, the processor detects the point as the corresponding point corresponding to the measurement image point.
3. The measurement apparatus of claim 1 , wherein in response to a point of the point cloud displayed within the image not existing at the position in the image shown by the measurement image point, the processor detects a point which is closest to the measurement image point as the corresponding point corresponding to the measurement image point.
4. The measurement apparatus of claim 1 , further comprising:
a result memory to assume the discriminated three-dimensional position as a three-dimensional position of a feature for a measurement target, and storing the three-dimensional position by relating to a type of the feature for the measurement target.
5. The measurement apparatus of claim 1 , wherein the processor is further programmed to
calculate a vector showing direction from a center of the camera to the inputted measurement image point,
calculate a particular plane including the detected corresponding point
receive a type of a feature for a measurement target from the user and input the type of the feature, and,
discriminate either of the detected corresponding point, and the intersecting point of the particular plane and the vector as a three-dimensional position of the measurement image point based on the type of the feature.
6. A measuring method comprising: storing in memory an image captured by a camera; storing in a three-dimensional point cloud memory a point cloud which is formed b7 a point cloud and of which a three-dimensional position is known as a three-dimensional point cloud model; discriminating via a processor, a three dimensional position of a measurement image point;
displaying and superimposing the image and a three-dimensional point cloud model which corresponds to the image out of the three-dimensional point cloud model stored in the three-dimensional point cloud memory and of which the three-dimensional position is known, on a screen of a displaying device;
prompting a user to specify a position within the image;
receiving and inputting the position within the image specified by the user as the measurement image point;
detecting, via a processor and based on whether a point of the point cloud is displayed within the image, a corresponding point corresponding to the measurement image point from the point cloud of the three-dimensional point cloud model stored by the three-dimensional point cloud model memory;
discriminating, via a processor, a three-dimensional position of the measurement image point using a three-dimensional position of the corresponding point; and
generating, via the processor, measurement position data showing the three-dimensional position of the discriminated measurement image point,
wherein the processor is further programmed to:
calculating a vector showing direction from a center of the camera to the imputed measurement image point; calculating a particular plane including the detected corresponding point,
obtaining a three-dimensional position of the detected corresponding point as a first candidate showing a three-dimensional position of the measurement image point, and
calculating an intersecting point of the particular plane and the vector as a second candidate showing the three-dimensional position of the measurement image point; displaying the first candidate and the second candidate on the screen of the displaying device and prompting the user to specify one of the first candidate and the second candidate; and
storing one of the first candidate and the second candidate specified by the user as the measurement position data showing the three-dimensional position of the measurement image point.
7. The measuring method of claim 6 , further comprising:
calculating a vector showing direction from a center of the camera to the measurement image point;
calculating a particular plane including the detected corresponding point;
prompting the user to specify a type of a feature for a measurement target and to input the type of the feature specified by the user;
discriminating, via the processor, either of the detected corresponding point, and an intersecting point of the particular plane and the vector as a three-dimensional position of the measurement image point based on the type of the feature; and
generating measurement position data showing the three-dimensional position of the measurement image point discriminated.