Object recognition apparatus, vehicle control apparatus, object recognition method, and vehicle control method
There are provided an object recognition apparatus that raises the recognition accuracy for a surrounding object and a vehicle control apparatus, and an object recognition method and a vehicle control method. An object recognition apparatus receives object data, which is a state value of the object, from a first sensor for detecting a surrounding object; compares estimation data obtained through estimation of a state value of the object, based on recognition data calculated in a past period, with the object data, and determines whether or not the object data is data in a low-resolution state; then, in accordance with the determination result, calculates the state value of the object by use of object data and estimation data and then generates the state value as recognition data, so that the recognition accuracy for an object is raised.
1. An object recognition apparatus comprising:
an estimation processor that in response to an object being detected by a sensor for detecting surrounding objects, estimates a change in a state value of the object, based on past recognition data detected by the sensor and calculated in the past, and then generates estimation result as estimation data;
a low-resolution-state determination processor that compares the estimation data estimated by the estimation processor with object data that is a state value of the object obtained by the sensor at a current time, so as to determine whether or not the object data is data in a low-resolution state where two or more objects cannot be separated from one another;
a recognition processor that generates recognition data by combining the estimation data and the object data, and
a correlation processor that determines whether or not there exists correlation that the estimation data and the object data are related to the same object, and generates determination result as correlation data,
wherein in a case where the low-resolution-state determination processor determines that the object data obtained at the current time is in the low-resolution state, the recognition processor reduces a weight to the recognition data in combining the object data that was determined to be in the low-resolution state, and then generates the recognition data,
wherein based on the correlation data generated by the correlation processor, the low-resolution-state determination processor determines whether or not the object data is data in the low-resolution state, and
wherein in the case where there exists the estimation data having no correlation with the object data, the correlation processor again determines whether or not the estimation data having no correlation has correlation with the object data; in the case where the object data that has been determined to have correlation with the estimation data is determined to have correlation with the estimation data having no correlation with the object data, the low-resolution-state determination processor determines that the object data is data in the low-resolution state.
2. The object recognition apparatus according to claim 1 ,
wherein the recognition processor applies the weight to the object data and the estimation data so as to calculate the state value of the object, and
wherein in the case where it is determined that the object data is in the low-resolution state, the recognition processor decreases the weight for the object data and then calculates the state value of the object.
3. A vehicle control apparatus having the object recognition apparatus according to claim 1 , wherein the object recognition apparatus is mounted in a vehicle.
4. The vehicle control apparatus according to claim 3 , wherein there is provided a display that is mounted in the vehicle and displays recognition data outputted by the recognition processor.
5. The vehicle control apparatus according to claim 3 , wherein there is provided a vehicle controller that is mounted in the vehicle and controls the vehicle, based on recognition data to be outputted by the recognition processor.
6. An object recognition method comprising:
receiving, from a sensor for detecting a surrounding object, object data that is a state value of the object;
estimating a change in the state value of the object, based on past recognition data detected by the sensor and calculated in the past, and then generating estimation result as estimation data;
comparing the estimation data with the object data obtained by the sensor at a current time, so as to determine whether or not the object data is data in a low-resolution state where the two or more objects cannot be separated from one another;
generating recognition data by combining the estimation data and the object data, and
determining whether or not there exists correlation that the estimation data and the object data are related to the same object, and generating determination result as correlation data,
wherein in generating the recognition data, in a case where it is determined that the object data is in the low-resolution state, reducing a weight to the recognition data in combining the object data that was determined to be in the low-resolution state and then generating the recognition data, and
wherein in comparing the estimation data, based on the correlation data, determining whether or not the object data is data in the low-resolution state.
7. A vehicle control method comprising:
the object recognition method, according to claim 6 , that is utilized in recognizing the object in the surrounding of a vehicle; and
displaying the recognition data outputted by the object recognition method on a display.
8. A vehicle control method comprising:
the object recognition method, according to claim 6 , that is utilized in recognizing the object in the surrounding of a vehicle; and
controlling the vehicle by use of the recognition data outputted by the object recognition method.