Object detection device and object detection method

1 . A target detection device that detects a target based on a plurality of observation values output from a plurality of types of sensors, the target detection device comprising a processor configured to:

process fusion and output a prediction value of the target after fusion;

estimate a false detection for every target based on the observation value and the prediction value and outputs a false detection estimation result;

calculate a false detection rate for every sensor based on the false detection estimation result, the false detection rate being determined using an average or statistical process of false detection estimation results over a plurality of time steps; and

correct a predetermined reliability of the sensor defined in advance as a distance-dependent function based on the false detection rate, and output the corrected reliability,

wherein the processor is further configured to process the fusion based on the prediction value, the false detection estimation result, and the corrected reliability.

2 . The target detection device according to claim 1 , wherein the processor is further configured to process the fusion and output a state vector, a covariance matrix, or an existence probability.

3 . The target detection device according to claim 1 , wherein the processor is further configured to estimate a non-detection rate and a false detection rate for each target using the prediction value.

4 . The target detection device according to claim 3 , wherein the processor is further configured to calculate frequency of non-detection for each sensor based on presence or absence of the observation value existing within an estimation range of the observation value, calculate frequency of false detection for each sensor based on a number of observation values existing within the estimation range of the observation value, and estimate false detection for each target using the frequency of non-detection and the frequency of false detection.

5 . The target detection device according to claim 4 , wherein the processor is further configured to:

determine a presence of a non-detection and use the non-detection as an estimation value of the non-detection rate when the observation value does not exist within the estimation range; and

count the number of false detections and use the number of false detections as an estimation value of the false detection rate when at least one observation value exists within the estimation range.

6 . The target detection device according to claim 5 , wherein the processor is further configured to use an estimation value of the non-detection and an estimation value of the false detection as the false detection estimation result to calculate an average value of the false detection and a frequency of the non-detection of a plurality of targets for each sensor and calculate the false detection rate for each sensor.

7 . The target detection device according to claim 1 , wherein the processor is further configured to estimate the false detection for each target using the prediction value after fusion in a temporally previous step.

8 . The target detection device according to claim 1 , wherein the processor is further configured to correct the predetermined reliability by calculating a coefficient by performing a command conversion on the false detection rate, and multiplying the coefficient on the reliability of the sensor defined in advance as a correction coefficient.

9 . The target detection device according to claim 1 , wherein the processor is further configured to correct the predetermined reliability of the sensor by calculating a coefficient from the false detection rate by indexing a table lookup from a stored array indexing false detection rate and distance.

10 . The target detection device according to claim 1 , wherein the processor is further configured to detect an abnormality of the sensor based on the false detection rate of each sensor.

11 . The target detection device according to claim 1 , wherein the processor is further configured to detect a scene of the sensor based on the false detection rate of each sensor.

12 . The target detection device according to claim 1 , wherein the processor is further configured to:

group the prediction value and the observation value,

generate group information indicating a correspondence status between the prediction value and the observation value,

estimate the false detection for each target with reference to the group information, and

process the fusion with reference to the group information.

13 . A target detection device including a processor configured to:

receive a plurality of pieces of output data from a plurality of types of sensors and detect a target based on the plurality of pieces of output data;

estimate a false detection of the target based on a detection result of the target after fusion, the false detection being determined using an average or statistical process of false detection estimation results over a plurality of time steps; and

estimate a predetermined reliability of a sensor in a predetermined scene, the predetermined reliability being defined in advance as a distance-dependent function, based on the estimation result of the false detection,

wherein the target is detected based on the estimated reliability based on the predetermined reliability of the sensor, the false detection estimation results, and the output data.

14 . A target detection method that detects a target based on a plurality of observation values output from a plurality of types of sensors, the target detection method comprising:

processing fusion and outputting a prediction value of the target after fusion;

estimating a false detection for each target based on the observation value and the prediction value and outputting a false detection estimation result;

calculating a false detection rate for each sensor based on the false detection estimation result, the false detection being determined using an average or statistical process of false detection estimation results over a plurality of time steps; and

correcting a predetermined reliability of the sensor, the predetermined reliability being defined in advance as a distance-dependent function, by applying a correction based on the averaged false detection rate and outputting the corrected reliability,

wherein the fusion processing step processes the fusion based on the prediction value, the false detection estimation result, and the corrected reliability.