Object recognition system and object recognition method

An object recognition system that recognizes an object around a movable body, the object recognition system comprising:

• a main body portion of a laser imaging detection and ranging that outputs a laser pulse to an area around the movable body and that acquires data on a reflection point around the movable body by detecting reflected light of the laser pulse reflected at the reflection point;
• a cover surface that protects the main body portion;
• and
• a data processing device that performs an object recognition process based on point group data obtained by processing the data on the reflection point, wherein
• the cover surface includes a scan range indicating a range that is passed by the laser pulse and the reflected light,
• the data processing device further performs an abnormality determination process for determining whether or not there is an abnormality in a predetermined section of the scan range,
• the data processing device predicts a relative moving distance indicating a distance by which a tracking target recognized through the object recognition process moves relatively to the movable body, in a range of a data set for expressing the point group data until lapse of a predetermined time from a present timing, based on a history of the point group data, in the abnormality determination process,
• the relative moving distance includes a vertical distance indicating a component that is perpendicular to an output central axis of the laser pulse and that is parallel to a vertical direction, and a horizontal distance indicating a component that is perpendicular to the output central axis and that is parallel to a horizontal direction,
• the data processing device calculates an estimated intensity of the reflected light based on a history of point group data constituting the tracking target, when the vertical distance or the horizontal distance is equal to or longer than a predetermined distance, in the abnormality determination process,
• the estimated intensity is an intensity of the reflected light that is predicted to constitute the point group data on the tracking target, in the range of the data set after lapse of the predetermined time and in a corresponding section indicating a section corresponding to the predetermined section,
• the data processing device determines whether or not a difference between the estimated intensity and an actual intensity of the reflected light is higher than a predetermined intensity, in the abnormality determination process,
• the actual intensity is an intensity of the reflected light that actually constitutes the point group data on the tracking target, in the range of the data set after lapse of the predetermined time and in the corresponding section, and
• the data processing device determines that there is an abnormality in the predetermined section when it is determined that the difference between the estimated intensity and the actual intensity is higher than the predetermined intensity, in the abnormality determination process;
• wherein
• the data processing device further performs a process of specifying a specific section indicating a section that is predicted to coincide with the corresponding section in the range of the data set after lapse of the predetermined time, in the range of the data set at the present timing, and a process of selecting data on an arbitrary coordinate in the specific section and evaluating an intensity of the reflected light constituting the arbitrary data, in the abnormality determination process, and
• the data processing device calculates an average of intensities of the reflected light respectively constituting all the data on coordinates in the specific section, determines whether or not a difference between the average and the intensity of the reflected light constituting the selected arbitrary data is larger than a predetermined deviation, and selects data on an arbitrary coordinate in the specific section other than the previously selected coordinate when it is determined that the difference between the average and the intensity of the reflected light constituting the selected arbitrary data is larger than the predetermined deviation, in the process of evaluating the intensity of the reflected light.